Upload folder using huggingface_hub

.ipynb_checkpoints/train_results-checkpoint.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.979631425800194,
+    "num_input_tokens_seen": 100663296,
+    "total_flos": 4.2827022437921587e+18,
+    "train_loss": 0.3106601850595325,
+    "train_runtime": 8133.8849,
+    "train_samples_per_second": 12.157,
+    "train_steps_per_second": 0.047
+}

.ipynb_checkpoints/trainer_log-checkpoint.jsonl

@@ -0,0 +1,193 @@
+{"current_steps": 2, "total_steps": 384, "loss": 0.831, "learning_rate": 0.0001, "epoch": 0.015518913676042677, "percentage": 0.52, "elapsed_time": "0:00:43", "remaining_time": "2:18:17", "throughput": "12068.40", "total_tokens": 524288}
+{"current_steps": 4, "total_steps": 384, "loss": 0.7398, "learning_rate": 9.999323662872997e-05, "epoch": 0.031037827352085354, "percentage": 1.04, "elapsed_time": "0:01:25", "remaining_time": "2:15:43", "throughput": "12232.95", "total_tokens": 1048576}
+{"current_steps": 6, "total_steps": 384, "loss": 0.6438, "learning_rate": 9.99729483446475e-05, "epoch": 0.04655674102812803, "percentage": 1.56, "elapsed_time": "0:02:08", "remaining_time": "2:14:25", "throughput": "12285.60", "total_tokens": 1572864}
+{"current_steps": 8, "total_steps": 384, "loss": 0.6032, "learning_rate": 9.993914063644052e-05, "epoch": 0.06207565470417071, "percentage": 2.08, "elapsed_time": "0:02:50", "remaining_time": "2:13:28", "throughput": "12307.51", "total_tokens": 2097152}
+{"current_steps": 10, "total_steps": 384, "loss": 0.5433, "learning_rate": 9.989182265027232e-05, "epoch": 0.07759456838021339, "percentage": 2.6, "elapsed_time": "0:03:32", "remaining_time": "2:12:35", "throughput": "12323.95", "total_tokens": 2621440}
+{"current_steps": 12, "total_steps": 384, "loss": 0.5228, "learning_rate": 9.98310071873072e-05, "epoch": 0.09311348205625607, "percentage": 3.12, "elapsed_time": "0:04:15", "remaining_time": "2:11:47", "throughput": "12332.99", "total_tokens": 3145728}
+{"current_steps": 14, "total_steps": 384, "loss": 0.4702, "learning_rate": 9.97567107002474e-05, "epoch": 0.10863239573229874, "percentage": 3.65, "elapsed_time": "0:04:57", "remaining_time": "2:10:58", "throughput": "12341.83", "total_tokens": 3670016}
+{"current_steps": 16, "total_steps": 384, "loss": 0.4574, "learning_rate": 9.966895328888194e-05, "epoch": 0.12415130940834142, "percentage": 4.17, "elapsed_time": "0:05:39", "remaining_time": "2:10:13", "throughput": "12347.21", "total_tokens": 4194304}
+{"current_steps": 18, "total_steps": 384, "loss": 0.5093, "learning_rate": 9.956775869464901e-05, "epoch": 0.1396702230843841, "percentage": 4.69, "elapsed_time": "0:06:22", "remaining_time": "2:09:28", "throughput": "12350.26", "total_tokens": 4718592}
+{"current_steps": 20, "total_steps": 384, "loss": 0.4771, "learning_rate": 9.945315429421306e-05, "epoch": 0.15518913676042678, "percentage": 5.21, "elapsed_time": "0:07:04", "remaining_time": "2:08:44", "throughput": "12352.92", "total_tokens": 5242880}
+{"current_steps": 22, "total_steps": 384, "loss": 0.4343, "learning_rate": 9.932517109205849e-05, "epoch": 0.17070805043646944, "percentage": 5.73, "elapsed_time": "0:07:46", "remaining_time": "2:08:00", "throughput": "12355.21", "total_tokens": 5767168}
+{"current_steps": 24, "total_steps": 384, "loss": 0.4455, "learning_rate": 9.918384371210176e-05, "epoch": 0.18622696411251213, "percentage": 6.25, "elapsed_time": "0:08:29", "remaining_time": "2:07:17", "throughput": "12356.26", "total_tokens": 6291456}
+{"current_steps": 26, "total_steps": 384, "loss": 0.4669, "learning_rate": 9.902921038832455e-05, "epoch": 0.2017458777885548, "percentage": 6.77, "elapsed_time": "0:09:11", "remaining_time": "2:06:35", "throughput": "12356.01", "total_tokens": 6815744}
+{"current_steps": 28, "total_steps": 384, "loss": 0.4723, "learning_rate": 9.886131295443003e-05, "epoch": 0.21726479146459748, "percentage": 7.29, "elapsed_time": "0:09:53", "remaining_time": "2:05:51", "throughput": "12357.59", "total_tokens": 7340032}
+{"current_steps": 30, "total_steps": 384, "loss": 0.4364, "learning_rate": 9.868019683252543e-05, "epoch": 0.23278370514064015, "percentage": 7.81, "elapsed_time": "0:10:36", "remaining_time": "2:05:09", "throughput": "12358.33", "total_tokens": 7864320}
+{"current_steps": 32, "total_steps": 384, "loss": 0.4013, "learning_rate": 9.848591102083375e-05, "epoch": 0.24830261881668284, "percentage": 8.33, "elapsed_time": "0:11:18", "remaining_time": "2:04:25", "throughput": "12360.25", "total_tokens": 8388608}
+{"current_steps": 34, "total_steps": 384, "loss": 0.3875, "learning_rate": 9.82785080804381e-05, "epoch": 0.2638215324927255, "percentage": 8.85, "elapsed_time": "0:12:01", "remaining_time": "2:03:42", "throughput": "12360.97", "total_tokens": 8912896}
+{"current_steps": 36, "total_steps": 384, "loss": 0.4187, "learning_rate": 9.805804412106198e-05, "epoch": 0.2793404461687682, "percentage": 9.38, "elapsed_time": "0:12:43", "remaining_time": "2:02:59", "throughput": "12361.99", "total_tokens": 9437184}
+{"current_steps": 38, "total_steps": 384, "loss": 0.3981, "learning_rate": 9.782457878588977e-05, "epoch": 0.2948593598448109, "percentage": 9.9, "elapsed_time": "0:13:25", "remaining_time": "2:02:16", "throughput": "12363.00", "total_tokens": 9961472}
+{"current_steps": 40, "total_steps": 384, "loss": 0.4121, "learning_rate": 9.757817523543109e-05, "epoch": 0.31037827352085356, "percentage": 10.42, "elapsed_time": "0:14:08", "remaining_time": "2:01:34", "throughput": "12363.06", "total_tokens": 10485760}
+{"current_steps": 42, "total_steps": 384, "loss": 0.392, "learning_rate": 9.731890013043368e-05, "epoch": 0.3258971871968962, "percentage": 10.94, "elapsed_time": "0:14:50", "remaining_time": "2:00:51", "throughput": "12363.66", "total_tokens": 11010048}
+{"current_steps": 44, "total_steps": 384, "loss": 0.3845, "learning_rate": 9.704682361384941e-05, "epoch": 0.3414161008729389, "percentage": 11.46, "elapsed_time": "0:15:32", "remaining_time": "2:00:08", "throughput": "12365.26", "total_tokens": 11534336}
+{"current_steps": 46, "total_steps": 384, "loss": 0.397, "learning_rate": 9.676201929185809e-05, "epoch": 0.3569350145489816, "percentage": 11.98, "elapsed_time": "0:16:15", "remaining_time": "1:59:25", "throughput": "12365.45", "total_tokens": 12058624}
+{"current_steps": 48, "total_steps": 384, "loss": 0.3753, "learning_rate": 9.646456421395446e-05, "epoch": 0.37245392822502427, "percentage": 12.5, "elapsed_time": "0:16:57", "remaining_time": "1:58:42", "throughput": "12365.80", "total_tokens": 12582912}
+{"current_steps": 50, "total_steps": 384, "loss": 0.387, "learning_rate": 9.615453885210369e-05, "epoch": 0.3879728419010669, "percentage": 13.02, "elapsed_time": "0:17:39", "remaining_time": "1:58:00", "throughput": "12366.58", "total_tokens": 13107200}
+{"current_steps": 52, "total_steps": 384, "loss": 0.3724, "learning_rate": 9.583202707897074e-05, "epoch": 0.4034917555771096, "percentage": 13.54, "elapsed_time": "0:18:22", "remaining_time": "1:57:17", "throughput": "12367.11", "total_tokens": 13631488}
+{"current_steps": 54, "total_steps": 384, "loss": 0.4394, "learning_rate": 9.549711614523007e-05, "epoch": 0.4190106692531523, "percentage": 14.06, "elapsed_time": "0:19:04", "remaining_time": "1:56:34", "throughput": "12367.54", "total_tokens": 14155776}
+{"current_steps": 56, "total_steps": 384, "loss": 0.4177, "learning_rate": 9.514989665596114e-05, "epoch": 0.43452958292919497, "percentage": 14.58, "elapsed_time": "0:19:46", "remaining_time": "1:55:52", "throughput": "12368.03", "total_tokens": 14680064}
+{"current_steps": 58, "total_steps": 384, "loss": 0.3939, "learning_rate": 9.479046254613673e-05, "epoch": 0.45004849660523766, "percentage": 15.1, "elapsed_time": "0:20:29", "remaining_time": "1:55:09", "throughput": "12368.21", "total_tokens": 15204352}
+{"current_steps": 60, "total_steps": 384, "loss": 0.4207, "learning_rate": 9.441891105521006e-05, "epoch": 0.4655674102812803, "percentage": 15.62, "elapsed_time": "0:21:11", "remaining_time": "1:54:26", "throughput": "12368.89", "total_tokens": 15728640}
+{"current_steps": 62, "total_steps": 384, "loss": 0.3653, "learning_rate": 9.403534270080829e-05, "epoch": 0.481086323957323, "percentage": 16.15, "elapsed_time": "0:21:53", "remaining_time": "1:53:44", "throughput": "12369.17", "total_tokens": 16252928}
+{"current_steps": 64, "total_steps": 384, "loss": 0.3925, "learning_rate": 9.3639861251539e-05, "epoch": 0.49660523763336567, "percentage": 16.67, "elapsed_time": "0:22:36", "remaining_time": "1:53:01", "throughput": "12369.62", "total_tokens": 16777216}
+{"current_steps": 66, "total_steps": 384, "loss": 0.3982, "learning_rate": 9.323257369891703e-05, "epoch": 0.5121241513094084, "percentage": 17.19, "elapsed_time": "0:23:18", "remaining_time": "1:52:19", "throughput": "12369.99", "total_tokens": 17301504}
+{"current_steps": 68, "total_steps": 384, "loss": 0.3709, "learning_rate": 9.281359022841965e-05, "epoch": 0.527643064985451, "percentage": 17.71, "elapsed_time": "0:24:01", "remaining_time": "1:51:36", "throughput": "12370.31", "total_tokens": 17825792}
+{"current_steps": 70, "total_steps": 384, "loss": 0.3744, "learning_rate": 9.238302418967756e-05, "epoch": 0.5431619786614937, "percentage": 18.23, "elapsed_time": "0:24:43", "remaining_time": "1:50:54", "throughput": "12370.44", "total_tokens": 18350080}
+{"current_steps": 72, "total_steps": 384, "loss": 0.3929, "learning_rate": 9.194099206580982e-05, "epoch": 0.5586808923375364, "percentage": 18.75, "elapsed_time": "0:25:25", "remaining_time": "1:50:11", "throughput": "12370.64", "total_tokens": 18874368}
+{"current_steps": 74, "total_steps": 384, "loss": 0.3716, "learning_rate": 9.148761344191109e-05, "epoch": 0.574199806013579, "percentage": 19.27, "elapsed_time": "0:26:08", "remaining_time": "1:49:29", "throughput": "12370.73", "total_tokens": 19398656}
+{"current_steps": 76, "total_steps": 384, "loss": 0.3959, "learning_rate": 9.102301097269974e-05, "epoch": 0.5897187196896218, "percentage": 19.79, "elapsed_time": "0:26:50", "remaining_time": "1:48:46", "throughput": "12371.11", "total_tokens": 19922944}
+{"current_steps": 78, "total_steps": 384, "loss": 0.3514, "learning_rate": 9.054731034933549e-05, "epoch": 0.6052376333656644, "percentage": 20.31, "elapsed_time": "0:27:32", "remaining_time": "1:48:04", "throughput": "12371.15", "total_tokens": 20447232}
+{"current_steps": 80, "total_steps": 384, "loss": 0.3767, "learning_rate": 9.006064026541548e-05, "epoch": 0.6207565470417071, "percentage": 20.83, "elapsed_time": "0:28:15", "remaining_time": "1:47:21", "throughput": "12371.38", "total_tokens": 20971520}
+{"current_steps": 82, "total_steps": 384, "loss": 0.371, "learning_rate": 8.956313238215824e-05, "epoch": 0.6362754607177498, "percentage": 21.35, "elapsed_time": "0:28:57", "remaining_time": "1:46:39", "throughput": "12371.34", "total_tokens": 21495808}
+{"current_steps": 84, "total_steps": 384, "loss": 0.3529, "learning_rate": 8.905492129278478e-05, "epoch": 0.6517943743937924, "percentage": 21.88, "elapsed_time": "0:29:39", "remaining_time": "1:45:56", "throughput": "12371.72", "total_tokens": 22020096}
+{"current_steps": 86, "total_steps": 384, "loss": 0.3044, "learning_rate": 8.853614448610631e-05, "epoch": 0.6673132880698351, "percentage": 22.4, "elapsed_time": "0:30:22", "remaining_time": "1:45:14", "throughput": "12371.87", "total_tokens": 22544384}
+{"current_steps": 88, "total_steps": 384, "loss": 0.3532, "learning_rate": 8.800694230932884e-05, "epoch": 0.6828322017458778, "percentage": 22.92, "elapsed_time": "0:31:04", "remaining_time": "1:44:31", "throughput": "12372.26", "total_tokens": 23068672}
+{"current_steps": 90, "total_steps": 384, "loss": 0.3461, "learning_rate": 8.74674579300843e-05, "epoch": 0.6983511154219205, "percentage": 23.44, "elapsed_time": "0:31:46", "remaining_time": "1:43:49", "throughput": "12371.97", "total_tokens": 23592960}
+{"current_steps": 92, "total_steps": 384, "loss": 0.3513, "learning_rate": 8.691783729769874e-05, "epoch": 0.7138700290979632, "percentage": 23.96, "elapsed_time": "0:32:29", "remaining_time": "1:43:07", "throughput": "12371.69", "total_tokens": 24117248}
+{"current_steps": 94, "total_steps": 384, "loss": 0.3842, "learning_rate": 8.635822910370792e-05, "epoch": 0.7293889427740058, "percentage": 24.48, "elapsed_time": "0:33:11", "remaining_time": "1:42:24", "throughput": "12371.92", "total_tokens": 24641536}
+{"current_steps": 96, "total_steps": 384, "loss": 0.363, "learning_rate": 8.578878474163115e-05, "epoch": 0.7449078564500485, "percentage": 25.0, "elapsed_time": "0:33:54", "remaining_time": "1:41:42", "throughput": "12372.14", "total_tokens": 25165824}
+{"current_steps": 98, "total_steps": 384, "loss": 0.3079, "learning_rate": 8.520965826601394e-05, "epoch": 0.7604267701260912, "percentage": 25.52, "elapsed_time": "0:34:36", "remaining_time": "1:40:59", "throughput": "12372.67", "total_tokens": 25690112}
+{"current_steps": 100, "total_steps": 384, "loss": 0.3769, "learning_rate": 8.462100635075097e-05, "epoch": 0.7759456838021338, "percentage": 26.04, "elapsed_time": "0:35:18", "remaining_time": "1:40:17", "throughput": "12372.59", "total_tokens": 26214400}
+{"current_steps": 102, "total_steps": 384, "loss": 0.3907, "learning_rate": 8.40229882467003e-05, "epoch": 0.7914645974781765, "percentage": 26.56, "elapsed_time": "0:36:01", "remaining_time": "1:39:34", "throughput": "12372.64", "total_tokens": 26738688}
+{"current_steps": 104, "total_steps": 384, "loss": 0.3457, "learning_rate": 8.341576573860048e-05, "epoch": 0.8069835111542192, "percentage": 27.08, "elapsed_time": "0:36:43", "remaining_time": "1:38:52", "throughput": "12372.69", "total_tokens": 27262976}
+{"current_steps": 106, "total_steps": 384, "loss": 0.3889, "learning_rate": 8.279950310130217e-05, "epoch": 0.8225024248302619, "percentage": 27.6, "elapsed_time": "0:37:25", "remaining_time": "1:38:09", "throughput": "12373.02", "total_tokens": 27787264}
+{"current_steps": 108, "total_steps": 384, "loss": 0.3142, "learning_rate": 8.2174367055326e-05, "epoch": 0.8380213385063046, "percentage": 28.12, "elapsed_time": "0:38:08", "remaining_time": "1:37:27", "throughput": "12373.10", "total_tokens": 28311552}
+{"current_steps": 110, "total_steps": 384, "loss": 0.3299, "learning_rate": 8.154052672175887e-05, "epoch": 0.8535402521823472, "percentage": 28.65, "elapsed_time": "0:38:50", "remaining_time": "1:36:45", "throughput": "12373.25", "total_tokens": 28835840}
+{"current_steps": 112, "total_steps": 384, "loss": 0.3425, "learning_rate": 8.089815357650089e-05, "epoch": 0.8690591658583899, "percentage": 29.17, "elapsed_time": "0:39:32", "remaining_time": "1:36:02", "throughput": "12373.26", "total_tokens": 29360128}
+{"current_steps": 114, "total_steps": 384, "loss": 0.3363, "learning_rate": 8.024742140387506e-05, "epoch": 0.8845780795344326, "percentage": 29.69, "elapsed_time": "0:40:15", "remaining_time": "1:35:20", "throughput": "12373.27", "total_tokens": 29884416}
+{"current_steps": 116, "total_steps": 384, "loss": 0.3725, "learning_rate": 7.95885062496126e-05, "epoch": 0.9000969932104753, "percentage": 30.21, "elapsed_time": "0:40:57", "remaining_time": "1:34:37", "throughput": "12373.41", "total_tokens": 30408704}
+{"current_steps": 118, "total_steps": 384, "loss": 0.3397, "learning_rate": 7.892158637322646e-05, "epoch": 0.915615906886518, "percentage": 30.73, "elapsed_time": "0:41:39", "remaining_time": "1:33:55", "throughput": "12373.69", "total_tokens": 30932992}
+{"current_steps": 120, "total_steps": 384, "loss": 0.2812, "learning_rate": 7.824684219978591e-05, "epoch": 0.9311348205625606, "percentage": 31.25, "elapsed_time": "0:42:22", "remaining_time": "1:33:12", "throughput": "12373.85", "total_tokens": 31457280}
+{"current_steps": 122, "total_steps": 384, "loss": 0.3555, "learning_rate": 7.756445627110523e-05, "epoch": 0.9466537342386033, "percentage": 31.77, "elapsed_time": "0:43:04", "remaining_time": "1:32:30", "throughput": "12373.80", "total_tokens": 31981568}
+{"current_steps": 124, "total_steps": 384, "loss": 0.3362, "learning_rate": 7.687461319635981e-05, "epoch": 0.962172647914646, "percentage": 32.29, "elapsed_time": "0:43:46", "remaining_time": "1:31:48", "throughput": "12373.83", "total_tokens": 32505856}
+{"current_steps": 126, "total_steps": 384, "loss": 0.3133, "learning_rate": 7.6177499602143e-05, "epoch": 0.9776915615906887, "percentage": 32.81, "elapsed_time": "0:44:29", "remaining_time": "1:31:05", "throughput": "12374.00", "total_tokens": 33030144}
+{"current_steps": 128, "total_steps": 384, "loss": 0.3119, "learning_rate": 7.547330408197695e-05, "epoch": 0.9932104752667313, "percentage": 33.33, "elapsed_time": "0:45:11", "remaining_time": "1:30:23", "throughput": "12374.26", "total_tokens": 33554432}
+{"current_steps": 130, "total_steps": 384, "loss": 0.3117, "learning_rate": 7.476221714529167e-05, "epoch": 1.008729388942774, "percentage": 33.85, "elapsed_time": "0:45:54", "remaining_time": "1:29:40", "throughput": "12374.25", "total_tokens": 34078720}
+{"current_steps": 132, "total_steps": 384, "loss": 0.329, "learning_rate": 7.404443116588548e-05, "epoch": 1.0242483026188167, "percentage": 34.38, "elapsed_time": "0:46:36", "remaining_time": "1:28:58", "throughput": "12374.33", "total_tokens": 34603008}
+{"current_steps": 134, "total_steps": 384, "loss": 0.279, "learning_rate": 7.332014032988123e-05, "epoch": 1.0397672162948595, "percentage": 34.9, "elapsed_time": "0:47:18", "remaining_time": "1:28:16", "throughput": "12374.33", "total_tokens": 35127296}
+{"current_steps": 136, "total_steps": 384, "loss": 0.2682, "learning_rate": 7.258954058319216e-05, "epoch": 1.055286129970902, "percentage": 35.42, "elapsed_time": "0:48:01", "remaining_time": "1:27:33", "throughput": "12374.30", "total_tokens": 35651584}
+{"current_steps": 138, "total_steps": 384, "loss": 0.293, "learning_rate": 7.185282957851175e-05, "epoch": 1.0708050436469447, "percentage": 35.94, "elapsed_time": "0:48:43", "remaining_time": "1:26:51", "throughput": "12374.23", "total_tokens": 36175872}
+{"current_steps": 140, "total_steps": 384, "loss": 0.315, "learning_rate": 7.111020662184174e-05, "epoch": 1.0863239573229875, "percentage": 36.46, "elapsed_time": "0:49:25", "remaining_time": "1:26:08", "throughput": "12374.40", "total_tokens": 36700160}
+{"current_steps": 142, "total_steps": 384, "loss": 0.289, "learning_rate": 7.036187261857289e-05, "epoch": 1.10184287099903, "percentage": 36.98, "elapsed_time": "0:50:08", "remaining_time": "1:25:26", "throughput": "12374.16", "total_tokens": 37224448}
+{"current_steps": 144, "total_steps": 384, "loss": 0.2808, "learning_rate": 6.960803001913314e-05, "epoch": 1.1173617846750727, "percentage": 37.5, "elapsed_time": "0:50:50", "remaining_time": "1:24:44", "throughput": "12374.30", "total_tokens": 37748736}
+{"current_steps": 146, "total_steps": 384, "loss": 0.318, "learning_rate": 6.884888276421766e-05, "epoch": 1.1328806983511155, "percentage": 38.02, "elapsed_time": "0:51:32", "remaining_time": "1:24:01", "throughput": "12374.33", "total_tokens": 38273024}
+{"current_steps": 148, "total_steps": 384, "loss": 0.2685, "learning_rate": 6.808463622961578e-05, "epoch": 1.148399612027158, "percentage": 38.54, "elapsed_time": "0:52:15", "remaining_time": "1:23:19", "throughput": "12374.43", "total_tokens": 38797312}
+{"current_steps": 150, "total_steps": 384, "loss": 0.3121, "learning_rate": 6.731549717064974e-05, "epoch": 1.1639185257032008, "percentage": 39.06, "elapsed_time": "0:52:57", "remaining_time": "1:22:37", "throughput": "12374.58", "total_tokens": 39321600}
+{"current_steps": 152, "total_steps": 384, "loss": 0.2835, "learning_rate": 6.654167366624009e-05, "epoch": 1.1794374393792435, "percentage": 39.58, "elapsed_time": "0:53:39", "remaining_time": "1:21:54", "throughput": "12374.63", "total_tokens": 39845888}
+{"current_steps": 154, "total_steps": 384, "loss": 0.2905, "learning_rate": 6.576337506261314e-05, "epoch": 1.1949563530552862, "percentage": 40.1, "elapsed_time": "0:54:22", "remaining_time": "1:21:12", "throughput": "12375.02", "total_tokens": 40370176}
+{"current_steps": 156, "total_steps": 384, "loss": 0.3277, "learning_rate": 6.498081191666548e-05, "epoch": 1.2104752667313288, "percentage": 40.62, "elapsed_time": "0:55:04", "remaining_time": "1:20:29", "throughput": "12375.10", "total_tokens": 40894464}
+{"current_steps": 158, "total_steps": 384, "loss": 0.2788, "learning_rate": 6.419419593900108e-05, "epoch": 1.2259941804073715, "percentage": 41.15, "elapsed_time": "0:55:46", "remaining_time": "1:19:47", "throughput": "12375.10", "total_tokens": 41418752}
+{"current_steps": 160, "total_steps": 384, "loss": 0.2971, "learning_rate": 6.340373993665607e-05, "epoch": 1.2415130940834143, "percentage": 41.67, "elapsed_time": "0:56:29", "remaining_time": "1:19:05", "throughput": "12375.12", "total_tokens": 41943040}
+{"current_steps": 162, "total_steps": 384, "loss": 0.287, "learning_rate": 6.260965775552712e-05, "epoch": 1.2570320077594568, "percentage": 42.19, "elapsed_time": "0:57:11", "remaining_time": "1:18:22", "throughput": "12374.98", "total_tokens": 42467328}
+{"current_steps": 164, "total_steps": 384, "loss": 0.3196, "learning_rate": 6.181216422251862e-05, "epoch": 1.2725509214354995, "percentage": 42.71, "elapsed_time": "0:57:54", "remaining_time": "1:17:40", "throughput": "12375.00", "total_tokens": 42991616}
+{"current_steps": 166, "total_steps": 384, "loss": 0.3021, "learning_rate": 6.101147508742455e-05, "epoch": 1.2880698351115423, "percentage": 43.23, "elapsed_time": "0:58:36", "remaining_time": "1:16:57", "throughput": "12375.01", "total_tokens": 43515904}
+{"current_steps": 168, "total_steps": 384, "loss": 0.2329, "learning_rate": 6.0207806964560584e-05, "epoch": 1.3035887487875848, "percentage": 43.75, "elapsed_time": "0:59:18", "remaining_time": "1:16:15", "throughput": "12375.04", "total_tokens": 44040192}
+{"current_steps": 170, "total_steps": 384, "loss": 0.2803, "learning_rate": 5.940137727416246e-05, "epoch": 1.3191076624636275, "percentage": 44.27, "elapsed_time": "1:00:01", "remaining_time": "1:15:33", "throughput": "12375.12", "total_tokens": 44564480}
+{"current_steps": 172, "total_steps": 384, "loss": 0.2744, "learning_rate": 5.8592404183566144e-05, "epoch": 1.3346265761396703, "percentage": 44.79, "elapsed_time": "1:00:43", "remaining_time": "1:14:50", "throughput": "12375.21", "total_tokens": 45088768}
+{"current_steps": 174, "total_steps": 384, "loss": 0.3332, "learning_rate": 5.778110654818601e-05, "epoch": 1.3501454898157128, "percentage": 45.31, "elapsed_time": "1:01:25", "remaining_time": "1:14:08", "throughput": "12375.49", "total_tokens": 45613056}
+{"current_steps": 176, "total_steps": 384, "loss": 0.3223, "learning_rate": 5.6967703852306786e-05, "epoch": 1.3656644034917556, "percentage": 45.83, "elapsed_time": "1:02:08", "remaining_time": "1:13:25", "throughput": "12375.42", "total_tokens": 46137344}
+{"current_steps": 178, "total_steps": 384, "loss": 0.3127, "learning_rate": 5.6152416149705455e-05, "epoch": 1.3811833171677983, "percentage": 46.35, "elapsed_time": "1:02:50", "remaining_time": "1:12:43", "throughput": "12375.48", "total_tokens": 46661632}
+{"current_steps": 180, "total_steps": 384, "loss": 0.2908, "learning_rate": 5.5335464004118986e-05, "epoch": 1.3967022308438408, "percentage": 46.88, "elapsed_time": "1:03:32", "remaining_time": "1:12:01", "throughput": "12375.67", "total_tokens": 47185920}
+{"current_steps": 182, "total_steps": 384, "loss": 0.2918, "learning_rate": 5.4517068429574215e-05, "epoch": 1.4122211445198836, "percentage": 47.4, "elapsed_time": "1:04:15", "remaining_time": "1:11:18", "throughput": "12375.66", "total_tokens": 47710208}
+{"current_steps": 184, "total_steps": 384, "loss": 0.268, "learning_rate": 5.3697450830595774e-05, "epoch": 1.4277400581959263, "percentage": 47.92, "elapsed_time": "1:04:57", "remaining_time": "1:10:36", "throughput": "12375.75", "total_tokens": 48234496}
+{"current_steps": 186, "total_steps": 384, "loss": 0.2862, "learning_rate": 5.287683294230855e-05, "epoch": 1.4432589718719688, "percentage": 48.44, "elapsed_time": "1:05:39", "remaining_time": "1:09:54", "throughput": "12375.71", "total_tokens": 48758784}
+{"current_steps": 188, "total_steps": 384, "loss": 0.3054, "learning_rate": 5.205543677045049e-05, "epoch": 1.4587778855480116, "percentage": 48.96, "elapsed_time": "1:06:22", "remaining_time": "1:09:11", "throughput": "12375.67", "total_tokens": 49283072}
+{"current_steps": 190, "total_steps": 384, "loss": 0.2814, "learning_rate": 5.1233484531312414e-05, "epoch": 1.4742967992240543, "percentage": 49.48, "elapsed_time": "1:07:04", "remaining_time": "1:08:29", "throughput": "12375.72", "total_tokens": 49807360}
+{"current_steps": 192, "total_steps": 384, "loss": 0.2703, "learning_rate": 5.0411198591620676e-05, "epoch": 1.489815712900097, "percentage": 50.0, "elapsed_time": "1:07:46", "remaining_time": "1:07:46", "throughput": "12375.63", "total_tokens": 50331648}
+{"current_steps": 194, "total_steps": 384, "loss": 0.2689, "learning_rate": 4.958880140837933e-05, "epoch": 1.5053346265761398, "percentage": 50.52, "elapsed_time": "1:08:29", "remaining_time": "1:07:04", "throughput": "12375.75", "total_tokens": 50855936}
+{"current_steps": 196, "total_steps": 384, "loss": 0.3013, "learning_rate": 4.876651546868759e-05, "epoch": 1.5208535402521823, "percentage": 51.04, "elapsed_time": "1:09:11", "remaining_time": "1:06:22", "throughput": "12375.76", "total_tokens": 51380224}
+{"current_steps": 198, "total_steps": 384, "loss": 0.2751, "learning_rate": 4.794456322954952e-05, "epoch": 1.536372453928225, "percentage": 51.56, "elapsed_time": "1:09:54", "remaining_time": "1:05:39", "throughput": "12375.72", "total_tokens": 51904512}
+{"current_steps": 200, "total_steps": 384, "loss": 0.3178, "learning_rate": 4.712316705769145e-05, "epoch": 1.5518913676042678, "percentage": 52.08, "elapsed_time": "1:10:36", "remaining_time": "1:04:57", "throughput": "12375.77", "total_tokens": 52428800}
+{"current_steps": 202, "total_steps": 384, "loss": 0.2742, "learning_rate": 4.630254916940424e-05, "epoch": 1.5674102812803103, "percentage": 52.6, "elapsed_time": "1:11:18", "remaining_time": "1:04:15", "throughput": "12375.80", "total_tokens": 52953088}
+{"current_steps": 204, "total_steps": 384, "loss": 0.2751, "learning_rate": 4.548293157042581e-05, "epoch": 1.582929194956353, "percentage": 53.12, "elapsed_time": "1:12:01", "remaining_time": "1:03:32", "throughput": "12375.84", "total_tokens": 53477376}
+{"current_steps": 206, "total_steps": 384, "loss": 0.3256, "learning_rate": 4.466453599588103e-05, "epoch": 1.5984481086323958, "percentage": 53.65, "elapsed_time": "1:12:43", "remaining_time": "1:02:50", "throughput": "12375.76", "total_tokens": 54001664}
+{"current_steps": 208, "total_steps": 384, "loss": 0.2603, "learning_rate": 4.384758385029457e-05, "epoch": 1.6139670223084384, "percentage": 54.17, "elapsed_time": "1:13:25", "remaining_time": "1:02:08", "throughput": "12375.86", "total_tokens": 54525952}
+{"current_steps": 210, "total_steps": 384, "loss": 0.2598, "learning_rate": 4.3032296147693225e-05, "epoch": 1.629485935984481, "percentage": 54.69, "elapsed_time": "1:14:08", "remaining_time": "1:01:25", "throughput": "12375.97", "total_tokens": 55050240}
+{"current_steps": 212, "total_steps": 384, "loss": 0.2811, "learning_rate": 4.2218893451814005e-05, "epoch": 1.6450048496605238, "percentage": 55.21, "elapsed_time": "1:14:50", "remaining_time": "1:00:43", "throughput": "12376.02", "total_tokens": 55574528}
+{"current_steps": 214, "total_steps": 384, "loss": 0.2386, "learning_rate": 4.140759581643386e-05, "epoch": 1.6605237633365664, "percentage": 55.73, "elapsed_time": "1:15:32", "remaining_time": "1:00:00", "throughput": "12375.99", "total_tokens": 56098816}
+{"current_steps": 216, "total_steps": 384, "loss": 0.2999, "learning_rate": 4.059862272583755e-05, "epoch": 1.6760426770126091, "percentage": 56.25, "elapsed_time": "1:16:15", "remaining_time": "0:59:18", "throughput": "12375.93", "total_tokens": 56623104}
+{"current_steps": 218, "total_steps": 384, "loss": 0.2857, "learning_rate": 3.979219303543942e-05, "epoch": 1.6915615906886519, "percentage": 56.77, "elapsed_time": "1:16:57", "remaining_time": "0:58:36", "throughput": "12375.82", "total_tokens": 57147392}
+{"current_steps": 220, "total_steps": 384, "loss": 0.2533, "learning_rate": 3.898852491257546e-05, "epoch": 1.7070805043646944, "percentage": 57.29, "elapsed_time": "1:17:40", "remaining_time": "0:57:53", "throughput": "12375.79", "total_tokens": 57671680}
+{"current_steps": 222, "total_steps": 384, "loss": 0.306, "learning_rate": 3.818783577748138e-05, "epoch": 1.7225994180407371, "percentage": 57.81, "elapsed_time": "1:18:22", "remaining_time": "0:57:11", "throughput": "12375.96", "total_tokens": 58195968}
+{"current_steps": 224, "total_steps": 384, "loss": 0.2594, "learning_rate": 3.739034224447289e-05, "epoch": 1.7381183317167799, "percentage": 58.33, "elapsed_time": "1:19:04", "remaining_time": "0:56:29", "throughput": "12376.04", "total_tokens": 58720256}
+{"current_steps": 226, "total_steps": 384, "loss": 0.284, "learning_rate": 3.659626006334395e-05, "epoch": 1.7536372453928224, "percentage": 58.85, "elapsed_time": "1:19:47", "remaining_time": "0:55:46", "throughput": "12376.05", "total_tokens": 59244544}
+{"current_steps": 228, "total_steps": 384, "loss": 0.33, "learning_rate": 3.580580406099893e-05, "epoch": 1.7691561590688651, "percentage": 59.38, "elapsed_time": "1:20:29", "remaining_time": "0:55:04", "throughput": "12376.03", "total_tokens": 59768832}
+{"current_steps": 230, "total_steps": 384, "loss": 0.2968, "learning_rate": 3.501918808333453e-05, "epoch": 1.7846750727449079, "percentage": 59.9, "elapsed_time": "1:21:11", "remaining_time": "0:54:21", "throughput": "12375.98", "total_tokens": 60293120}
+{"current_steps": 232, "total_steps": 384, "loss": 0.2836, "learning_rate": 3.4236624937386876e-05, "epoch": 1.8001939864209504, "percentage": 60.42, "elapsed_time": "1:21:54", "remaining_time": "0:53:39", "throughput": "12376.10", "total_tokens": 60817408}
+{"current_steps": 234, "total_steps": 384, "loss": 0.2452, "learning_rate": 3.3458326333759925e-05, "epoch": 1.8157129000969934, "percentage": 60.94, "elapsed_time": "1:22:36", "remaining_time": "0:52:57", "throughput": "12376.14", "total_tokens": 61341696}
+{"current_steps": 236, "total_steps": 384, "loss": 0.2526, "learning_rate": 3.268450282935026e-05, "epoch": 1.831231813773036, "percentage": 61.46, "elapsed_time": "1:23:18", "remaining_time": "0:52:14", "throughput": "12376.09", "total_tokens": 61865984}
+{"current_steps": 238, "total_steps": 384, "loss": 0.2578, "learning_rate": 3.191536377038422e-05, "epoch": 1.8467507274490784, "percentage": 61.98, "elapsed_time": "1:24:01", "remaining_time": "0:51:32", "throughput": "12376.15", "total_tokens": 62390272}
+{"current_steps": 240, "total_steps": 384, "loss": 0.2895, "learning_rate": 3.115111723578235e-05, "epoch": 1.8622696411251214, "percentage": 62.5, "elapsed_time": "1:24:43", "remaining_time": "0:50:50", "throughput": "12376.22", "total_tokens": 62914560}
+{"current_steps": 242, "total_steps": 384, "loss": 0.3047, "learning_rate": 3.0391969980866875e-05, "epoch": 1.877788554801164, "percentage": 63.02, "elapsed_time": "1:25:25", "remaining_time": "0:50:07", "throughput": "12376.20", "total_tokens": 63438848}
+{"current_steps": 244, "total_steps": 384, "loss": 0.2958, "learning_rate": 2.963812738142713e-05, "epoch": 1.8933074684772064, "percentage": 63.54, "elapsed_time": "1:26:08", "remaining_time": "0:49:25", "throughput": "12376.13", "total_tokens": 63963136}
+{"current_steps": 246, "total_steps": 384, "loss": 0.2598, "learning_rate": 2.888979337815828e-05, "epoch": 1.9088263821532494, "percentage": 64.06, "elapsed_time": "1:26:50", "remaining_time": "0:48:43", "throughput": "12376.10", "total_tokens": 64487424}
+{"current_steps": 248, "total_steps": 384, "loss": 0.2699, "learning_rate": 2.8147170421488272e-05, "epoch": 1.924345295829292, "percentage": 64.58, "elapsed_time": "1:27:33", "remaining_time": "0:48:00", "throughput": "12376.09", "total_tokens": 65011712}
+{"current_steps": 250, "total_steps": 384, "loss": 0.2827, "learning_rate": 2.7410459416807853e-05, "epoch": 1.9398642095053347, "percentage": 65.1, "elapsed_time": "1:28:15", "remaining_time": "0:47:18", "throughput": "12376.20", "total_tokens": 65536000}
+{"current_steps": 252, "total_steps": 384, "loss": 0.3119, "learning_rate": 2.6679859670118783e-05, "epoch": 1.9553831231813774, "percentage": 65.62, "elapsed_time": "1:28:57", "remaining_time": "0:46:35", "throughput": "12376.24", "total_tokens": 66060288}
+{"current_steps": 254, "total_steps": 384, "loss": 0.2837, "learning_rate": 2.5955568834114524e-05, "epoch": 1.97090203685742, "percentage": 66.15, "elapsed_time": "1:29:40", "remaining_time": "0:45:53", "throughput": "12376.19", "total_tokens": 66584576}
+{"current_steps": 256, "total_steps": 384, "loss": 0.2511, "learning_rate": 2.5237782854708348e-05, "epoch": 1.9864209505334627, "percentage": 66.67, "elapsed_time": "1:30:22", "remaining_time": "0:45:11", "throughput": "12376.12", "total_tokens": 67108864}
+{"current_steps": 258, "total_steps": 384, "loss": 0.2501, "learning_rate": 2.452669591802307e-05, "epoch": 2.0019398642095054, "percentage": 67.19, "elapsed_time": "1:31:04", "remaining_time": "0:44:28", "throughput": "12376.06", "total_tokens": 67633152}
+{"current_steps": 260, "total_steps": 384, "loss": 0.2296, "learning_rate": 2.3822500397857018e-05, "epoch": 2.017458777885548, "percentage": 67.71, "elapsed_time": "1:31:47", "remaining_time": "0:43:46", "throughput": "12376.11", "total_tokens": 68157440}
+{"current_steps": 262, "total_steps": 384, "loss": 0.2333, "learning_rate": 2.3125386803640187e-05, "epoch": 2.0329776915615905, "percentage": 68.23, "elapsed_time": "1:32:29", "remaining_time": "0:43:04", "throughput": "12376.14", "total_tokens": 68681728}
+{"current_steps": 264, "total_steps": 384, "loss": 0.2119, "learning_rate": 2.2435543728894792e-05, "epoch": 2.0484966052376334, "percentage": 68.75, "elapsed_time": "1:33:11", "remaining_time": "0:42:21", "throughput": "12376.08", "total_tokens": 69206016}
+{"current_steps": 266, "total_steps": 384, "loss": 0.2676, "learning_rate": 2.175315780021411e-05, "epoch": 2.064015518913676, "percentage": 69.27, "elapsed_time": "1:33:54", "remaining_time": "0:41:39", "throughput": "12376.02", "total_tokens": 69730304}
+{"current_steps": 268, "total_steps": 384, "loss": 0.2285, "learning_rate": 2.1078413626773546e-05, "epoch": 2.079534432589719, "percentage": 69.79, "elapsed_time": "1:34:36", "remaining_time": "0:40:57", "throughput": "12376.08", "total_tokens": 70254592}
+{"current_steps": 270, "total_steps": 384, "loss": 0.2281, "learning_rate": 2.0411493750387423e-05, "epoch": 2.0950533462657615, "percentage": 70.31, "elapsed_time": "1:35:18", "remaining_time": "0:40:14", "throughput": "12376.12", "total_tokens": 70778880}
+{"current_steps": 272, "total_steps": 384, "loss": 0.2701, "learning_rate": 1.9752578596124954e-05, "epoch": 2.110572259941804, "percentage": 70.83, "elapsed_time": "1:36:01", "remaining_time": "0:39:32", "throughput": "12376.07", "total_tokens": 71303168}
+{"current_steps": 274, "total_steps": 384, "loss": 0.2033, "learning_rate": 1.9101846423499116e-05, "epoch": 2.126091173617847, "percentage": 71.35, "elapsed_time": "1:36:43", "remaining_time": "0:38:49", "throughput": "12375.95", "total_tokens": 71827456}
+{"current_steps": 276, "total_steps": 384, "loss": 0.2489, "learning_rate": 1.8459473278241126e-05, "epoch": 2.1416100872938895, "percentage": 71.88, "elapsed_time": "1:37:26", "remaining_time": "0:38:07", "throughput": "12375.99", "total_tokens": 72351744}
+{"current_steps": 278, "total_steps": 384, "loss": 0.2294, "learning_rate": 1.7825632944674015e-05, "epoch": 2.157129000969932, "percentage": 72.4, "elapsed_time": "1:38:08", "remaining_time": "0:37:25", "throughput": "12375.97", "total_tokens": 72876032}
+{"current_steps": 280, "total_steps": 384, "loss": 0.2452, "learning_rate": 1.7200496898697832e-05, "epoch": 2.172647914645975, "percentage": 72.92, "elapsed_time": "1:38:50", "remaining_time": "0:36:42", "throughput": "12375.92", "total_tokens": 73400320}
+{"current_steps": 282, "total_steps": 384, "loss": 0.242, "learning_rate": 1.6584234261399534e-05, "epoch": 2.1881668283220175, "percentage": 73.44, "elapsed_time": "1:39:33", "remaining_time": "0:36:00", "throughput": "12375.92", "total_tokens": 73924608}
+{"current_steps": 284, "total_steps": 384, "loss": 0.2894, "learning_rate": 1.5977011753299725e-05, "epoch": 2.20368574199806, "percentage": 73.96, "elapsed_time": "1:40:15", "remaining_time": "0:35:18", "throughput": "12376.01", "total_tokens": 74448896}
+{"current_steps": 286, "total_steps": 384, "loss": 0.231, "learning_rate": 1.537899364924905e-05, "epoch": 2.219204655674103, "percentage": 74.48, "elapsed_time": "1:40:57", "remaining_time": "0:34:35", "throughput": "12376.10", "total_tokens": 74973184}
+{"current_steps": 288, "total_steps": 384, "loss": 0.2412, "learning_rate": 1.4790341733986085e-05, "epoch": 2.2347235693501455, "percentage": 75.0, "elapsed_time": "1:41:40", "remaining_time": "0:33:53", "throughput": "12376.22", "total_tokens": 75497472}
+{"current_steps": 290, "total_steps": 384, "loss": 0.2464, "learning_rate": 1.4211215258368866e-05, "epoch": 2.250242483026188, "percentage": 75.52, "elapsed_time": "1:42:22", "remaining_time": "0:33:11", "throughput": "12376.23", "total_tokens": 76021760}
+{"current_steps": 292, "total_steps": 384, "loss": 0.2231, "learning_rate": 1.3641770896292084e-05, "epoch": 2.265761396702231, "percentage": 76.04, "elapsed_time": "1:43:04", "remaining_time": "0:32:28", "throughput": "12376.27", "total_tokens": 76546048}
+{"current_steps": 294, "total_steps": 384, "loss": 0.2432, "learning_rate": 1.3082162702301276e-05, "epoch": 2.2812803103782735, "percentage": 76.56, "elapsed_time": "1:43:47", "remaining_time": "0:31:46", "throughput": "12376.31", "total_tokens": 77070336}
+{"current_steps": 296, "total_steps": 384, "loss": 0.2147, "learning_rate": 1.253254206991572e-05, "epoch": 2.296799224054316, "percentage": 77.08, "elapsed_time": "1:44:29", "remaining_time": "0:31:03", "throughput": "12376.31", "total_tokens": 77594624}
+{"current_steps": 298, "total_steps": 384, "loss": 0.249, "learning_rate": 1.1993057690671173e-05, "epoch": 2.312318137730359, "percentage": 77.6, "elapsed_time": "1:45:11", "remaining_time": "0:30:21", "throughput": "12376.43", "total_tokens": 78118912}
+{"current_steps": 300, "total_steps": 384, "loss": 0.2362, "learning_rate": 1.1463855513893695e-05, "epoch": 2.3278370514064015, "percentage": 78.12, "elapsed_time": "1:45:54", "remaining_time": "0:29:39", "throughput": "12376.44", "total_tokens": 78643200}
+{"current_steps": 302, "total_steps": 384, "loss": 0.2232, "learning_rate": 1.0945078707215222e-05, "epoch": 2.343355965082444, "percentage": 78.65, "elapsed_time": "1:46:36", "remaining_time": "0:28:56", "throughput": "12376.47", "total_tokens": 79167488}
+{"current_steps": 304, "total_steps": 384, "loss": 0.2569, "learning_rate": 1.0436867617841768e-05, "epoch": 2.358874878758487, "percentage": 79.17, "elapsed_time": "1:47:18", "remaining_time": "0:28:14", "throughput": "12376.49", "total_tokens": 79691776}
+{"current_steps": 306, "total_steps": 384, "loss": 0.214, "learning_rate": 9.939359734584553e-06, "epoch": 2.3743937924345295, "percentage": 79.69, "elapsed_time": "1:48:01", "remaining_time": "0:27:32", "throughput": "12376.52", "total_tokens": 80216064}
+{"current_steps": 308, "total_steps": 384, "loss": 0.2451, "learning_rate": 9.452689650664515e-06, "epoch": 2.3899127061105725, "percentage": 80.21, "elapsed_time": "1:48:43", "remaining_time": "0:26:49", "throughput": "12376.53", "total_tokens": 80740352}
+{"current_steps": 310, "total_steps": 384, "loss": 0.2288, "learning_rate": 8.976989027300264e-06, "epoch": 2.405431619786615, "percentage": 80.73, "elapsed_time": "1:49:25", "remaining_time": "0:26:07", "throughput": "12376.63", "total_tokens": 81264640}
+{"current_steps": 312, "total_steps": 384, "loss": 0.2332, "learning_rate": 8.51238655808892e-06, "epoch": 2.4209505334626575, "percentage": 81.25, "elapsed_time": "1:50:08", "remaining_time": "0:25:25", "throughput": "12376.58", "total_tokens": 81788928}
+{"current_steps": 314, "total_steps": 384, "loss": 0.202, "learning_rate": 8.059007934190194e-06, "epoch": 2.4364694471387, "percentage": 81.77, "elapsed_time": "1:50:50", "remaining_time": "0:24:42", "throughput": "12376.66", "total_tokens": 82313216}
+{"current_steps": 316, "total_steps": 384, "loss": 0.227, "learning_rate": 7.61697581032243e-06, "epoch": 2.451988360814743, "percentage": 82.29, "elapsed_time": "1:51:33", "remaining_time": "0:24:00", "throughput": "12376.73", "total_tokens": 82837504}
+{"current_steps": 318, "total_steps": 384, "loss": 0.2429, "learning_rate": 7.186409771580354e-06, "epoch": 2.4675072744907856, "percentage": 82.81, "elapsed_time": "1:52:15", "remaining_time": "0:23:17", "throughput": "12376.77", "total_tokens": 83361792}
+{"current_steps": 320, "total_steps": 384, "loss": 0.2147, "learning_rate": 6.76742630108298e-06, "epoch": 2.4830261881668285, "percentage": 83.33, "elapsed_time": "1:52:57", "remaining_time": "0:22:35", "throughput": "12376.72", "total_tokens": 83886080}
+{"current_steps": 322, "total_steps": 384, "loss": 0.2423, "learning_rate": 6.3601387484610145e-06, "epoch": 2.498545101842871, "percentage": 83.85, "elapsed_time": "1:53:40", "remaining_time": "0:21:53", "throughput": "12376.78", "total_tokens": 84410368}
+{"current_steps": 324, "total_steps": 384, "loss": 0.2828, "learning_rate": 5.9646572991917116e-06, "epoch": 2.5140640155189136, "percentage": 84.38, "elapsed_time": "1:54:22", "remaining_time": "0:21:10", "throughput": "12376.78", "total_tokens": 84934656}
+{"current_steps": 326, "total_steps": 384, "loss": 0.2461, "learning_rate": 5.581088944789953e-06, "epoch": 2.529582929194956, "percentage": 84.9, "elapsed_time": "1:55:04", "remaining_time": "0:20:28", "throughput": "12376.78", "total_tokens": 85458944}
+{"current_steps": 328, "total_steps": 384, "loss": 0.296, "learning_rate": 5.209537453863289e-06, "epoch": 2.545101842870999, "percentage": 85.42, "elapsed_time": "1:55:47", "remaining_time": "0:19:46", "throughput": "12376.71", "total_tokens": 85983232}
+{"current_steps": 330, "total_steps": 384, "loss": 0.2061, "learning_rate": 4.850103344038853e-06, "epoch": 2.5606207565470416, "percentage": 85.94, "elapsed_time": "1:56:29", "remaining_time": "0:19:03", "throughput": "12376.82", "total_tokens": 86507520}
+{"current_steps": 332, "total_steps": 384, "loss": 0.2323, "learning_rate": 4.502883854769935e-06, "epoch": 2.5761396702230845, "percentage": 86.46, "elapsed_time": "1:57:11", "remaining_time": "0:18:21", "throughput": "12376.90", "total_tokens": 87031808}
+{"current_steps": 334, "total_steps": 384, "loss": 0.2156, "learning_rate": 4.167972921029262e-06, "epoch": 2.591658583899127, "percentage": 86.98, "elapsed_time": "1:57:54", "remaining_time": "0:17:39", "throughput": "12376.92", "total_tokens": 87556096}
+{"current_steps": 336, "total_steps": 384, "loss": 0.2393, "learning_rate": 3.845461147896323e-06, "epoch": 2.6071774975751696, "percentage": 87.5, "elapsed_time": "1:58:36", "remaining_time": "0:16:56", "throughput": "12376.97", "total_tokens": 88080384}
+{"current_steps": 338, "total_steps": 384, "loss": 0.2165, "learning_rate": 3.535435786045538e-06, "epoch": 2.6226964112512126, "percentage": 88.02, "elapsed_time": "1:59:18", "remaining_time": "0:16:14", "throughput": "12377.00", "total_tokens": 88604672}
+{"current_steps": 340, "total_steps": 384, "loss": 0.2313, "learning_rate": 3.2379807081419187e-06, "epoch": 2.638215324927255, "percentage": 88.54, "elapsed_time": "2:00:01", "remaining_time": "0:15:31", "throughput": "12377.04", "total_tokens": 89128960}
+{"current_steps": 342, "total_steps": 384, "loss": 0.2336, "learning_rate": 2.9531763861505966e-06, "epoch": 2.653734238603298, "percentage": 89.06, "elapsed_time": "2:00:43", "remaining_time": "0:14:49", "throughput": "12377.01", "total_tokens": 89653248}
+{"current_steps": 344, "total_steps": 384, "loss": 0.2311, "learning_rate": 2.6810998695663282e-06, "epoch": 2.6692531522793406, "percentage": 89.58, "elapsed_time": "2:01:25", "remaining_time": "0:14:07", "throughput": "12376.99", "total_tokens": 90177536}
+{"current_steps": 346, "total_steps": 384, "loss": 0.213, "learning_rate": 2.4218247645689307e-06, "epoch": 2.684772065955383, "percentage": 90.1, "elapsed_time": "2:02:08", "remaining_time": "0:13:24", "throughput": "12376.99", "total_tokens": 90701824}
+{"current_steps": 348, "total_steps": 384, "loss": 0.2364, "learning_rate": 2.1754212141102346e-06, "epoch": 2.7002909796314256, "percentage": 90.62, "elapsed_time": "2:02:50", "remaining_time": "0:12:42", "throughput": "12377.02", "total_tokens": 91226112}
+{"current_steps": 350, "total_steps": 384, "loss": 0.2147, "learning_rate": 1.941955878938029e-06, "epoch": 2.7158098933074686, "percentage": 91.15, "elapsed_time": "2:03:32", "remaining_time": "0:12:00", "throughput": "12376.97", "total_tokens": 91750400}
+{"current_steps": 352, "total_steps": 384, "loss": 0.2316, "learning_rate": 1.7214919195619127e-06, "epoch": 2.731328806983511, "percentage": 91.67, "elapsed_time": "2:04:15", "remaining_time": "0:11:17", "throughput": "12377.00", "total_tokens": 92274688}
+{"current_steps": 354, "total_steps": 384, "loss": 0.2263, "learning_rate": 1.514088979166256e-06, "epoch": 2.746847720659554, "percentage": 92.19, "elapsed_time": "2:04:57", "remaining_time": "0:10:35", "throughput": "12376.97", "total_tokens": 92798976}
+{"current_steps": 356, "total_steps": 384, "loss": 0.2323, "learning_rate": 1.3198031674745813e-06, "epoch": 2.7623666343355966, "percentage": 92.71, "elapsed_time": "2:05:40", "remaining_time": "0:09:53", "throughput": "12376.99", "total_tokens": 93323264}
+{"current_steps": 358, "total_steps": 384, "loss": 0.2246, "learning_rate": 1.138687045569975e-06, "epoch": 2.777885548011639, "percentage": 93.23, "elapsed_time": "2:06:22", "remaining_time": "0:09:10", "throughput": "12376.92", "total_tokens": 93847552}
+{"current_steps": 360, "total_steps": 384, "loss": 0.2287, "learning_rate": 9.707896116754488e-07, "epoch": 2.7934044616876816, "percentage": 93.75, "elapsed_time": "2:07:04", "remaining_time": "0:08:28", "throughput": "12376.95", "total_tokens": 94371840}
+{"current_steps": 362, "total_steps": 384, "loss": 0.2081, "learning_rate": 8.161562878982398e-07, "epoch": 2.8089233753637246, "percentage": 94.27, "elapsed_time": "2:07:47", "remaining_time": "0:07:45", "throughput": "12376.94", "total_tokens": 94896128}
+{"current_steps": 364, "total_steps": 384, "loss": 0.226, "learning_rate": 6.74828907941516e-07, "epoch": 2.824442289039767, "percentage": 94.79, "elapsed_time": "2:08:29", "remaining_time": "0:07:03", "throughput": "12377.00", "total_tokens": 95420416}
+{"current_steps": 366, "total_steps": 384, "loss": 0.273, "learning_rate": 5.468457057869358e-07, "epoch": 2.83996120271581, "percentage": 95.31, "elapsed_time": "2:09:11", "remaining_time": "0:06:21", "throughput": "12377.06", "total_tokens": 95944704}
+{"current_steps": 368, "total_steps": 384, "loss": 0.2634, "learning_rate": 4.322413053509944e-07, "epoch": 2.8554801163918526, "percentage": 95.83, "elapsed_time": "2:09:54", "remaining_time": "0:05:38", "throughput": "12377.12", "total_tokens": 96468992}
+{"current_steps": 370, "total_steps": 384, "loss": 0.2592, "learning_rate": 3.3104671111806593e-07, "epoch": 2.870999030067895, "percentage": 96.35, "elapsed_time": "2:10:36", "remaining_time": "0:04:56", "throughput": "12377.13", "total_tokens": 96993280}
+{"current_steps": 372, "total_steps": 384, "loss": 0.2566, "learning_rate": 2.432892997526026e-07, "epoch": 2.8865179437439377, "percentage": 96.88, "elapsed_time": "2:11:18", "remaining_time": "0:04:14", "throughput": "12377.08", "total_tokens": 97517568}
+{"current_steps": 374, "total_steps": 384, "loss": 0.2575, "learning_rate": 1.6899281269279755e-07, "epoch": 2.9020368574199806, "percentage": 97.4, "elapsed_time": "2:12:01", "remaining_time": "0:03:31", "throughput": "12377.14", "total_tokens": 98041856}
+{"current_steps": 376, "total_steps": 384, "loss": 0.2482, "learning_rate": 1.0817734972768944e-07, "epoch": 2.917555771096023, "percentage": 97.92, "elapsed_time": "2:12:43", "remaining_time": "0:02:49", "throughput": "12377.10", "total_tokens": 98566144}
+{"current_steps": 378, "total_steps": 384, "loss": 0.2483, "learning_rate": 6.085936355947897e-08, "epoch": 2.933074684772066, "percentage": 98.44, "elapsed_time": "2:13:25", "remaining_time": "0:02:07", "throughput": "12377.12", "total_tokens": 99090432}
+{"current_steps": 380, "total_steps": 384, "loss": 0.2359, "learning_rate": 2.7051655352494652e-08, "epoch": 2.9485935984481086, "percentage": 98.96, "elapsed_time": "2:14:08", "remaining_time": "0:01:24", "throughput": "12377.19", "total_tokens": 99614720}
+{"current_steps": 382, "total_steps": 384, "loss": 0.2434, "learning_rate": 6.763371270035457e-09, "epoch": 2.964112512124151, "percentage": 99.48, "elapsed_time": "2:14:50", "remaining_time": "0:00:42", "throughput": "12377.19", "total_tokens": 100139008}
+{"current_steps": 384, "total_steps": 384, "loss": 0.2042, "learning_rate": 0.0, "epoch": 2.979631425800194, "percentage": 100.0, "elapsed_time": "2:15:33", "remaining_time": "0:00:00", "throughput": "12377.13", "total_tokens": 100663296}
+{"current_steps": 384, "total_steps": 384, "epoch": 2.979631425800194, "percentage": 100.0, "elapsed_time": "2:15:33", "remaining_time": "0:00:00", "throughput": "12375.80", "total_tokens": 100663296}

README.md

@@ -0,0 +1,65 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_08-16-2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_08-16-2
+
+This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) on the cangjie dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2599
+- Num Input Tokens Seen: 100663296
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.4
+- Pytorch 2.1.0.post2+cxx11.abi
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc79010938f3826491a6a6df853188abeccfe64cc8565a430780d29125a1f08
+size 80792096

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.979631425800194,
+    "eval_loss": 0.259890079498291,
+    "eval_runtime": 44.8481,
+    "eval_samples_per_second": 38.686,
+    "eval_steps_per_second": 1.226,
+    "num_input_tokens_seen": 100663296,
+    "perplexity": 1.2967875352947666,
+    "total_flos": 4.2827022437921587e+18,
+    "train_loss": 0.3106601850595325,
+    "train_runtime": 8133.8849,
+    "train_samples_per_second": 12.157,
+    "train_steps_per_second": 0.047
+}

checkpoint-384/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-384/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-384/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc79010938f3826491a6a6df853188abeccfe64cc8565a430780d29125a1f08
+size 80792096

checkpoint-384/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-384/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e72aff6d15f10da879db50605ceb2b1e0f1609e0880d830b7face4aecd1b051
+size 161809770

checkpoint-384/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbca9c2d9e6a73f24b063968418b0f980d6818e216929fc691b258aba7226946
+size 14000

checkpoint-384/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694061e381a06c682d6993c0a92851af911ac20d4880def923b1f5736dd94994
+size 14000

checkpoint-384/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5504ac37e31ccf2f556b6461472c3f1356c3c676d4ede0bc4dee5c5f9eeea2ea
+size 14000

checkpoint-384/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3f288bd93660b49606bfd36b754ab0ad981d9f4cd51e66a6dcbc870278f21a
+size 14000

checkpoint-384/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925e818c9ac2f6a5fe081861a9799d91c2af3d033ee48ef8ebdcef04774df7db
+size 14000

checkpoint-384/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3bb28ec8b2772c7049a98fe10c289b59baf606df693c16fa421f753347b58e
+size 14000

checkpoint-384/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417598f8dc6a79bcab75027f8f18250e80244fc0733440e359061ef9d6479cd4
+size 14000

checkpoint-384/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8816faca16df8b692dcc366cb27029f36cb1d5c483f66d8f8319ff109692d92
+size 14000

checkpoint-384/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bb0d3fb3dc7b4e69c47f5823681b7ee6adc9cae9703bb8e00a2f65220bc91d
+size 1064

checkpoint-384/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-384/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-384/trainer_state.json

@@ -0,0 +1,1569 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.979631425800194,
+  "eval_steps": 5000,
+  "global_step": 384,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015518913676042677,
+      "grad_norm": 0.416015625,
+      "learning_rate": 0.0001,
+      "loss": 0.831,
+      "num_input_tokens_seen": 524288,
+      "step": 2
+    },
+    {
+      "epoch": 0.031037827352085354,
+      "grad_norm": 0.49609375,
+      "learning_rate": 9.999323662872997e-05,
+      "loss": 0.7398,
+      "num_input_tokens_seen": 1048576,
+      "step": 4
+    },
+    {
+      "epoch": 0.04655674102812803,
+      "grad_norm": 0.333984375,
+      "learning_rate": 9.99729483446475e-05,
+      "loss": 0.6438,
+      "num_input_tokens_seen": 1572864,
+      "step": 6
+    },
+    {
+      "epoch": 0.06207565470417071,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.993914063644052e-05,
+      "loss": 0.6032,
+      "num_input_tokens_seen": 2097152,
+      "step": 8
+    },
+    {
+      "epoch": 0.07759456838021339,
+      "grad_norm": 0.314453125,
+      "learning_rate": 9.989182265027232e-05,
+      "loss": 0.5433,
+      "num_input_tokens_seen": 2621440,
+      "step": 10
+    },
+    {
+      "epoch": 0.09311348205625607,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 9.98310071873072e-05,
+      "loss": 0.5228,
+      "num_input_tokens_seen": 3145728,
+      "step": 12
+    },
+    {
+      "epoch": 0.10863239573229874,
+      "grad_norm": 0.3359375,
+      "learning_rate": 9.97567107002474e-05,
+      "loss": 0.4702,
+      "num_input_tokens_seen": 3670016,
+      "step": 14
+    },
+    {
+      "epoch": 0.12415130940834142,
+      "grad_norm": 0.2109375,
+      "learning_rate": 9.966895328888194e-05,
+      "loss": 0.4574,
+      "num_input_tokens_seen": 4194304,
+      "step": 16
+    },
+    {
+      "epoch": 0.1396702230843841,
+      "grad_norm": 0.224609375,
+      "learning_rate": 9.956775869464901e-05,
+      "loss": 0.5093,
+      "num_input_tokens_seen": 4718592,
+      "step": 18
+    },
+    {
+      "epoch": 0.15518913676042678,
+      "grad_norm": 0.25390625,
+      "learning_rate": 9.945315429421306e-05,
+      "loss": 0.4771,
+      "num_input_tokens_seen": 5242880,
+      "step": 20
+    },
+    {
+      "epoch": 0.17070805043646944,
+      "grad_norm": 0.201171875,
+      "learning_rate": 9.932517109205849e-05,
+      "loss": 0.4343,
+      "num_input_tokens_seen": 5767168,
+      "step": 22
+    },
+    {
+      "epoch": 0.18622696411251213,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 9.918384371210176e-05,
+      "loss": 0.4455,
+      "num_input_tokens_seen": 6291456,
+      "step": 24
+    },
+    {
+      "epoch": 0.2017458777885548,
+      "grad_norm": 3.265625,
+      "learning_rate": 9.902921038832455e-05,
+      "loss": 0.4669,
+      "num_input_tokens_seen": 6815744,
+      "step": 26
+    },
+    {
+      "epoch": 0.21726479146459748,
+      "grad_norm": 2.421875,
+      "learning_rate": 9.886131295443003e-05,
+      "loss": 0.4723,
+      "num_input_tokens_seen": 7340032,
+      "step": 28
+    },
+    {
+      "epoch": 0.23278370514064015,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 9.868019683252543e-05,
+      "loss": 0.4364,
+      "num_input_tokens_seen": 7864320,
+      "step": 30
+    },
+    {
+      "epoch": 0.24830261881668284,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.848591102083375e-05,
+      "loss": 0.4013,
+      "num_input_tokens_seen": 8388608,
+      "step": 32
+    },
+    {
+      "epoch": 0.2638215324927255,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 9.82785080804381e-05,
+      "loss": 0.3875,
+      "num_input_tokens_seen": 8912896,
+      "step": 34
+    },
+    {
+      "epoch": 0.2793404461687682,
+      "grad_norm": 0.125,
+      "learning_rate": 9.805804412106198e-05,
+      "loss": 0.4187,
+      "num_input_tokens_seen": 9437184,
+      "step": 36
+    },
+    {
+      "epoch": 0.2948593598448109,
+      "grad_norm": 0.12255859375,
+      "learning_rate": 9.782457878588977e-05,
+      "loss": 0.3981,
+      "num_input_tokens_seen": 9961472,
+      "step": 38
+    },
+    {
+      "epoch": 0.31037827352085356,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 9.757817523543109e-05,
+      "loss": 0.4121,
+      "num_input_tokens_seen": 10485760,
+      "step": 40
+    },
+    {
+      "epoch": 0.3258971871968962,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 9.731890013043368e-05,
+      "loss": 0.392,
+      "num_input_tokens_seen": 11010048,
+      "step": 42
+    },
+    {
+      "epoch": 0.3414161008729389,
+      "grad_norm": 0.10546875,
+      "learning_rate": 9.704682361384941e-05,
+      "loss": 0.3845,
+      "num_input_tokens_seen": 11534336,
+      "step": 44
+    },
+    {
+      "epoch": 0.3569350145489816,
+      "grad_norm": 0.0859375,
+      "learning_rate": 9.676201929185809e-05,
+      "loss": 0.397,
+      "num_input_tokens_seen": 12058624,
+      "step": 46
+    },
+    {
+      "epoch": 0.37245392822502427,
+      "grad_norm": 0.083984375,
+      "learning_rate": 9.646456421395446e-05,
+      "loss": 0.3753,
+      "num_input_tokens_seen": 12582912,
+      "step": 48
+    },
+    {
+      "epoch": 0.3879728419010669,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 9.615453885210369e-05,
+      "loss": 0.387,
+      "num_input_tokens_seen": 13107200,
+      "step": 50
+    },
+    {
+      "epoch": 0.4034917555771096,
+      "grad_norm": 0.0703125,
+      "learning_rate": 9.583202707897074e-05,
+      "loss": 0.3724,
+      "num_input_tokens_seen": 13631488,
+      "step": 52
+    },
+    {
+      "epoch": 0.4190106692531523,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 9.549711614523007e-05,
+      "loss": 0.4394,
+      "num_input_tokens_seen": 14155776,
+      "step": 54
+    },
+    {
+      "epoch": 0.43452958292919497,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 9.514989665596114e-05,
+      "loss": 0.4177,
+      "num_input_tokens_seen": 14680064,
+      "step": 56
+    },
+    {
+      "epoch": 0.45004849660523766,
+      "grad_norm": 0.078125,
+      "learning_rate": 9.479046254613673e-05,
+      "loss": 0.3939,
+      "num_input_tokens_seen": 15204352,
+      "step": 58
+    },
+    {
+      "epoch": 0.4655674102812803,
+      "grad_norm": 0.076171875,
+      "learning_rate": 9.441891105521006e-05,
+      "loss": 0.4207,
+      "num_input_tokens_seen": 15728640,
+      "step": 60
+    },
+    {
+      "epoch": 0.481086323957323,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 9.403534270080829e-05,
+      "loss": 0.3653,
+      "num_input_tokens_seen": 16252928,
+      "step": 62
+    },
+    {
+      "epoch": 0.49660523763336567,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 9.3639861251539e-05,
+      "loss": 0.3925,
+      "num_input_tokens_seen": 16777216,
+      "step": 64
+    },
+    {
+      "epoch": 0.5121241513094084,
+      "grad_norm": 0.0859375,
+      "learning_rate": 9.323257369891703e-05,
+      "loss": 0.3982,
+      "num_input_tokens_seen": 17301504,
+      "step": 66
+    },
+    {
+      "epoch": 0.527643064985451,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 9.281359022841965e-05,
+      "loss": 0.3709,
+      "num_input_tokens_seen": 17825792,
+      "step": 68
+    },
+    {
+      "epoch": 0.5431619786614937,
+      "grad_norm": 0.068359375,
+      "learning_rate": 9.238302418967756e-05,
+      "loss": 0.3744,
+      "num_input_tokens_seen": 18350080,
+      "step": 70
+    },
+    {
+      "epoch": 0.5586808923375364,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 9.194099206580982e-05,
+      "loss": 0.3929,
+      "num_input_tokens_seen": 18874368,
+      "step": 72
+    },
+    {
+      "epoch": 0.574199806013579,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 9.148761344191109e-05,
+      "loss": 0.3716,
+      "num_input_tokens_seen": 19398656,
+      "step": 74
+    },
+    {
+      "epoch": 0.5897187196896218,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 9.102301097269974e-05,
+      "loss": 0.3959,
+      "num_input_tokens_seen": 19922944,
+      "step": 76
+    },
+    {
+      "epoch": 0.6052376333656644,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 9.054731034933549e-05,
+      "loss": 0.3514,
+      "num_input_tokens_seen": 20447232,
+      "step": 78
+    },
+    {
+      "epoch": 0.6207565470417071,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 9.006064026541548e-05,
+      "loss": 0.3767,
+      "num_input_tokens_seen": 20971520,
+      "step": 80
+    },
+    {
+      "epoch": 0.6362754607177498,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 8.956313238215824e-05,
+      "loss": 0.371,
+      "num_input_tokens_seen": 21495808,
+      "step": 82
+    },
+    {
+      "epoch": 0.6517943743937924,
+      "grad_norm": 0.1171875,
+      "learning_rate": 8.905492129278478e-05,
+      "loss": 0.3529,
+      "num_input_tokens_seen": 22020096,
+      "step": 84
+    },
+    {
+      "epoch": 0.6673132880698351,
+      "grad_norm": 0.06640625,
+      "learning_rate": 8.853614448610631e-05,
+      "loss": 0.3044,
+      "num_input_tokens_seen": 22544384,
+      "step": 86
+    },
+    {
+      "epoch": 0.6828322017458778,
+      "grad_norm": 0.072265625,
+      "learning_rate": 8.800694230932884e-05,
+      "loss": 0.3532,
+      "num_input_tokens_seen": 23068672,
+      "step": 88
+    },
+    {
+      "epoch": 0.6983511154219205,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 8.74674579300843e-05,
+      "loss": 0.3461,
+      "num_input_tokens_seen": 23592960,
+      "step": 90
+    },
+    {
+      "epoch": 0.7138700290979632,
+      "grad_norm": 0.0693359375,
+      "learning_rate": 8.691783729769874e-05,
+      "loss": 0.3513,
+      "num_input_tokens_seen": 24117248,
+      "step": 92
+    },
+    {
+      "epoch": 0.7293889427740058,
+      "grad_norm": 0.06689453125,
+      "learning_rate": 8.635822910370792e-05,
+      "loss": 0.3842,
+      "num_input_tokens_seen": 24641536,
+      "step": 94
+    },
+    {
+      "epoch": 0.7449078564500485,
+      "grad_norm": 0.11083984375,
+      "learning_rate": 8.578878474163115e-05,
+      "loss": 0.363,
+      "num_input_tokens_seen": 25165824,
+      "step": 96
+    },
+    {
+      "epoch": 0.7604267701260912,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 8.520965826601394e-05,
+      "loss": 0.3079,
+      "num_input_tokens_seen": 25690112,
+      "step": 98
+    },
+    {
+      "epoch": 0.7759456838021338,
+      "grad_norm": 0.08203125,
+      "learning_rate": 8.462100635075097e-05,
+      "loss": 0.3769,
+      "num_input_tokens_seen": 26214400,
+      "step": 100
+    },
+    {
+      "epoch": 0.7914645974781765,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 8.40229882467003e-05,
+      "loss": 0.3907,
+      "num_input_tokens_seen": 26738688,
+      "step": 102
+    },
+    {
+      "epoch": 0.8069835111542192,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 8.341576573860048e-05,
+      "loss": 0.3457,
+      "num_input_tokens_seen": 27262976,
+      "step": 104
+    },
+    {
+      "epoch": 0.8225024248302619,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 8.279950310130217e-05,
+      "loss": 0.3889,
+      "num_input_tokens_seen": 27787264,
+      "step": 106
+    },
+    {
+      "epoch": 0.8380213385063046,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 8.2174367055326e-05,
+      "loss": 0.3142,
+      "num_input_tokens_seen": 28311552,
+      "step": 108
+    },
+    {
+      "epoch": 0.8535402521823472,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 8.154052672175887e-05,
+      "loss": 0.3299,
+      "num_input_tokens_seen": 28835840,
+      "step": 110
+    },
+    {
+      "epoch": 0.8690591658583899,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 8.089815357650089e-05,
+      "loss": 0.3425,
+      "num_input_tokens_seen": 29360128,
+      "step": 112
+    },
+    {
+      "epoch": 0.8845780795344326,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 8.024742140387506e-05,
+      "loss": 0.3363,
+      "num_input_tokens_seen": 29884416,
+      "step": 114
+    },
+    {
+      "epoch": 0.9000969932104753,
+      "grad_norm": 0.083984375,
+      "learning_rate": 7.95885062496126e-05,
+      "loss": 0.3725,
+      "num_input_tokens_seen": 30408704,
+      "step": 116
+    },
+    {
+      "epoch": 0.915615906886518,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 7.892158637322646e-05,
+      "loss": 0.3397,
+      "num_input_tokens_seen": 30932992,
+      "step": 118
+    },
+    {
+      "epoch": 0.9311348205625606,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 7.824684219978591e-05,
+      "loss": 0.2812,
+      "num_input_tokens_seen": 31457280,
+      "step": 120
+    },
+    {
+      "epoch": 0.9466537342386033,
+      "grad_norm": 0.1015625,
+      "learning_rate": 7.756445627110523e-05,
+      "loss": 0.3555,
+      "num_input_tokens_seen": 31981568,
+      "step": 122
+    },
+    {
+      "epoch": 0.962172647914646,
+      "grad_norm": 0.072265625,
+      "learning_rate": 7.687461319635981e-05,
+      "loss": 0.3362,
+      "num_input_tokens_seen": 32505856,
+      "step": 124
+    },
+    {
+      "epoch": 0.9776915615906887,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 7.6177499602143e-05,
+      "loss": 0.3133,
+      "num_input_tokens_seen": 33030144,
+      "step": 126
+    },
+    {
+      "epoch": 0.9932104752667313,
+      "grad_norm": 0.06982421875,
+      "learning_rate": 7.547330408197695e-05,
+      "loss": 0.3119,
+      "num_input_tokens_seen": 33554432,
+      "step": 128
+    },
+    {
+      "epoch": 1.008729388942774,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 7.476221714529167e-05,
+      "loss": 0.3117,
+      "num_input_tokens_seen": 34078720,
+      "step": 130
+    },
+    {
+      "epoch": 1.0242483026188167,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 7.404443116588548e-05,
+      "loss": 0.329,
+      "num_input_tokens_seen": 34603008,
+      "step": 132
+    },
+    {
+      "epoch": 1.0397672162948595,
+      "grad_norm": 0.078125,
+      "learning_rate": 7.332014032988123e-05,
+      "loss": 0.279,
+      "num_input_tokens_seen": 35127296,
+      "step": 134
+    },
+    {
+      "epoch": 1.055286129970902,
+      "grad_norm": 0.0703125,
+      "learning_rate": 7.258954058319216e-05,
+      "loss": 0.2682,
+      "num_input_tokens_seen": 35651584,
+      "step": 136
+    },
+    {
+      "epoch": 1.0708050436469447,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 7.185282957851175e-05,
+      "loss": 0.293,
+      "num_input_tokens_seen": 36175872,
+      "step": 138
+    },
+    {
+      "epoch": 1.0863239573229875,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 7.111020662184174e-05,
+      "loss": 0.315,
+      "num_input_tokens_seen": 36700160,
+      "step": 140
+    },
+    {
+      "epoch": 1.10184287099903,
+      "grad_norm": 0.072265625,
+      "learning_rate": 7.036187261857289e-05,
+      "loss": 0.289,
+      "num_input_tokens_seen": 37224448,
+      "step": 142
+    },
+    {
+      "epoch": 1.1173617846750727,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 6.960803001913314e-05,
+      "loss": 0.2808,
+      "num_input_tokens_seen": 37748736,
+      "step": 144
+    },
+    {
+      "epoch": 1.1328806983511155,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 6.884888276421766e-05,
+      "loss": 0.318,
+      "num_input_tokens_seen": 38273024,
+      "step": 146
+    },
+    {
+      "epoch": 1.148399612027158,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 6.808463622961578e-05,
+      "loss": 0.2685,
+      "num_input_tokens_seen": 38797312,
+      "step": 148
+    },
+    {
+      "epoch": 1.1639185257032008,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 6.731549717064974e-05,
+      "loss": 0.3121,
+      "num_input_tokens_seen": 39321600,
+      "step": 150
+    },
+    {
+      "epoch": 1.1794374393792435,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 6.654167366624009e-05,
+      "loss": 0.2835,
+      "num_input_tokens_seen": 39845888,
+      "step": 152
+    },
+    {
+      "epoch": 1.1949563530552862,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 6.576337506261314e-05,
+      "loss": 0.2905,
+      "num_input_tokens_seen": 40370176,
+      "step": 154
+    },
+    {
+      "epoch": 1.2104752667313288,
+      "grad_norm": 0.08984375,
+      "learning_rate": 6.498081191666548e-05,
+      "loss": 0.3277,
+      "num_input_tokens_seen": 40894464,
+      "step": 156
+    },
+    {
+      "epoch": 1.2259941804073715,
+      "grad_norm": 0.0859375,
+      "learning_rate": 6.419419593900108e-05,
+      "loss": 0.2788,
+      "num_input_tokens_seen": 41418752,
+      "step": 158
+    },
+    {
+      "epoch": 1.2415130940834143,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 6.340373993665607e-05,
+      "loss": 0.2971,
+      "num_input_tokens_seen": 41943040,
+      "step": 160
+    },
+    {
+      "epoch": 1.2570320077594568,
+      "grad_norm": 0.091796875,
+      "learning_rate": 6.260965775552712e-05,
+      "loss": 0.287,
+      "num_input_tokens_seen": 42467328,
+      "step": 162
+    },
+    {
+      "epoch": 1.2725509214354995,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 6.181216422251862e-05,
+      "loss": 0.3196,
+      "num_input_tokens_seen": 42991616,
+      "step": 164
+    },
+    {
+      "epoch": 1.2880698351115423,
+      "grad_norm": 0.083984375,
+      "learning_rate": 6.101147508742455e-05,
+      "loss": 0.3021,
+      "num_input_tokens_seen": 43515904,
+      "step": 166
+    },
+    {
+      "epoch": 1.3035887487875848,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 6.0207806964560584e-05,
+      "loss": 0.2329,
+      "num_input_tokens_seen": 44040192,
+      "step": 168
+    },
+    {
+      "epoch": 1.3191076624636275,
+      "grad_norm": 0.08984375,
+      "learning_rate": 5.940137727416246e-05,
+      "loss": 0.2803,
+      "num_input_tokens_seen": 44564480,
+      "step": 170
+    },
+    {
+      "epoch": 1.3346265761396703,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 5.8592404183566144e-05,
+      "loss": 0.2744,
+      "num_input_tokens_seen": 45088768,
+      "step": 172
+    },
+    {
+      "epoch": 1.3501454898157128,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 5.778110654818601e-05,
+      "loss": 0.3332,
+      "num_input_tokens_seen": 45613056,
+      "step": 174
+    },
+    {
+      "epoch": 1.3656644034917556,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 5.6967703852306786e-05,
+      "loss": 0.3223,
+      "num_input_tokens_seen": 46137344,
+      "step": 176
+    },
+    {
+      "epoch": 1.3811833171677983,
+      "grad_norm": 0.083984375,
+      "learning_rate": 5.6152416149705455e-05,
+      "loss": 0.3127,
+      "num_input_tokens_seen": 46661632,
+      "step": 178
+    },
+    {
+      "epoch": 1.3967022308438408,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 5.5335464004118986e-05,
+      "loss": 0.2908,
+      "num_input_tokens_seen": 47185920,
+      "step": 180
+    },
+    {
+      "epoch": 1.4122211445198836,
+      "grad_norm": 0.08984375,
+      "learning_rate": 5.4517068429574215e-05,
+      "loss": 0.2918,
+      "num_input_tokens_seen": 47710208,
+      "step": 182
+    },
+    {
+      "epoch": 1.4277400581959263,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 5.3697450830595774e-05,
+      "loss": 0.268,
+      "num_input_tokens_seen": 48234496,
+      "step": 184
+    },
+    {
+      "epoch": 1.4432589718719688,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 5.287683294230855e-05,
+      "loss": 0.2862,
+      "num_input_tokens_seen": 48758784,
+      "step": 186
+    },
+    {
+      "epoch": 1.4587778855480116,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 5.205543677045049e-05,
+      "loss": 0.3054,
+      "num_input_tokens_seen": 49283072,
+      "step": 188
+    },
+    {
+      "epoch": 1.4742967992240543,
+      "grad_norm": 0.087890625,
+      "learning_rate": 5.1233484531312414e-05,
+      "loss": 0.2814,
+      "num_input_tokens_seen": 49807360,
+      "step": 190
+    },
+    {
+      "epoch": 1.489815712900097,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 5.0411198591620676e-05,
+      "loss": 0.2703,
+      "num_input_tokens_seen": 50331648,
+      "step": 192
+    },
+    {
+      "epoch": 1.5053346265761398,
+      "grad_norm": 0.11181640625,
+      "learning_rate": 4.958880140837933e-05,
+      "loss": 0.2689,
+      "num_input_tokens_seen": 50855936,
+      "step": 194
+    },
+    {
+      "epoch": 1.5208535402521823,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 4.876651546868759e-05,
+      "loss": 0.3013,
+      "num_input_tokens_seen": 51380224,
+      "step": 196
+    },
+    {
+      "epoch": 1.536372453928225,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 4.794456322954952e-05,
+      "loss": 0.2751,
+      "num_input_tokens_seen": 51904512,
+      "step": 198
+    },
+    {
+      "epoch": 1.5518913676042678,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 4.712316705769145e-05,
+      "loss": 0.3178,
+      "num_input_tokens_seen": 52428800,
+      "step": 200
+    },
+    {
+      "epoch": 1.5674102812803103,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 4.630254916940424e-05,
+      "loss": 0.2742,
+      "num_input_tokens_seen": 52953088,
+      "step": 202
+    },
+    {
+      "epoch": 1.582929194956353,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 4.548293157042581e-05,
+      "loss": 0.2751,
+      "num_input_tokens_seen": 53477376,
+      "step": 204
+    },
+    {
+      "epoch": 1.5984481086323958,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 4.466453599588103e-05,
+      "loss": 0.3256,
+      "num_input_tokens_seen": 54001664,
+      "step": 206
+    },
+    {
+      "epoch": 1.6139670223084384,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 4.384758385029457e-05,
+      "loss": 0.2603,
+      "num_input_tokens_seen": 54525952,
+      "step": 208
+    },
+    {
+      "epoch": 1.629485935984481,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 4.3032296147693225e-05,
+      "loss": 0.2598,
+      "num_input_tokens_seen": 55050240,
+      "step": 210
+    },
+    {
+      "epoch": 1.6450048496605238,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 4.2218893451814005e-05,
+      "loss": 0.2811,
+      "num_input_tokens_seen": 55574528,
+      "step": 212
+    },
+    {
+      "epoch": 1.6605237633365664,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 4.140759581643386e-05,
+      "loss": 0.2386,
+      "num_input_tokens_seen": 56098816,
+      "step": 214
+    },
+    {
+      "epoch": 1.6760426770126091,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 4.059862272583755e-05,
+      "loss": 0.2999,
+      "num_input_tokens_seen": 56623104,
+      "step": 216
+    },
+    {
+      "epoch": 1.6915615906886519,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 3.979219303543942e-05,
+      "loss": 0.2857,
+      "num_input_tokens_seen": 57147392,
+      "step": 218
+    },
+    {
+      "epoch": 1.7070805043646944,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 3.898852491257546e-05,
+      "loss": 0.2533,
+      "num_input_tokens_seen": 57671680,
+      "step": 220
+    },
+    {
+      "epoch": 1.7225994180407371,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 3.818783577748138e-05,
+      "loss": 0.306,
+      "num_input_tokens_seen": 58195968,
+      "step": 222
+    },
+    {
+      "epoch": 1.7381183317167799,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 3.739034224447289e-05,
+      "loss": 0.2594,
+      "num_input_tokens_seen": 58720256,
+      "step": 224
+    },
+    {
+      "epoch": 1.7536372453928224,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 3.659626006334395e-05,
+      "loss": 0.284,
+      "num_input_tokens_seen": 59244544,
+      "step": 226
+    },
+    {
+      "epoch": 1.7691561590688651,
+      "grad_norm": 0.10546875,
+      "learning_rate": 3.580580406099893e-05,
+      "loss": 0.33,
+      "num_input_tokens_seen": 59768832,
+      "step": 228
+    },
+    {
+      "epoch": 1.7846750727449079,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 3.501918808333453e-05,
+      "loss": 0.2968,
+      "num_input_tokens_seen": 60293120,
+      "step": 230
+    },
+    {
+      "epoch": 1.8001939864209504,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 3.4236624937386876e-05,
+      "loss": 0.2836,
+      "num_input_tokens_seen": 60817408,
+      "step": 232
+    },
+    {
+      "epoch": 1.8157129000969934,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 3.3458326333759925e-05,
+      "loss": 0.2452,
+      "num_input_tokens_seen": 61341696,
+      "step": 234
+    },
+    {
+      "epoch": 1.831231813773036,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 3.268450282935026e-05,
+      "loss": 0.2526,
+      "num_input_tokens_seen": 61865984,
+      "step": 236
+    },
+    {
+      "epoch": 1.8467507274490784,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 3.191536377038422e-05,
+      "loss": 0.2578,
+      "num_input_tokens_seen": 62390272,
+      "step": 238
+    },
+    {
+      "epoch": 1.8622696411251214,
+      "grad_norm": 0.09375,
+      "learning_rate": 3.115111723578235e-05,
+      "loss": 0.2895,
+      "num_input_tokens_seen": 62914560,
+      "step": 240
+    },
+    {
+      "epoch": 1.877788554801164,
+      "grad_norm": 0.134765625,
+      "learning_rate": 3.0391969980866875e-05,
+      "loss": 0.3047,
+      "num_input_tokens_seen": 63438848,
+      "step": 242
+    },
+    {
+      "epoch": 1.8933074684772064,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 2.963812738142713e-05,
+      "loss": 0.2958,
+      "num_input_tokens_seen": 63963136,
+      "step": 244
+    },
+    {
+      "epoch": 1.9088263821532494,
+      "grad_norm": 0.1015625,
+      "learning_rate": 2.888979337815828e-05,
+      "loss": 0.2598,
+      "num_input_tokens_seen": 64487424,
+      "step": 246
+    },
+    {
+      "epoch": 1.924345295829292,
+      "grad_norm": 0.09375,
+      "learning_rate": 2.8147170421488272e-05,
+      "loss": 0.2699,
+      "num_input_tokens_seen": 65011712,
+      "step": 248
+    },
+    {
+      "epoch": 1.9398642095053347,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 2.7410459416807853e-05,
+      "loss": 0.2827,
+      "num_input_tokens_seen": 65536000,
+      "step": 250
+    },
+    {
+      "epoch": 1.9553831231813774,
+      "grad_norm": 0.1953125,
+      "learning_rate": 2.6679859670118783e-05,
+      "loss": 0.3119,
+      "num_input_tokens_seen": 66060288,
+      "step": 252
+    },
+    {
+      "epoch": 1.97090203685742,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 2.5955568834114524e-05,
+      "loss": 0.2837,
+      "num_input_tokens_seen": 66584576,
+      "step": 254
+    },
+    {
+      "epoch": 1.9864209505334627,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 2.5237782854708348e-05,
+      "loss": 0.2511,
+      "num_input_tokens_seen": 67108864,
+      "step": 256
+    },
+    {
+      "epoch": 2.0019398642095054,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 2.452669591802307e-05,
+      "loss": 0.2501,
+      "num_input_tokens_seen": 67633152,
+      "step": 258
+    },
+    {
+      "epoch": 2.017458777885548,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 2.3822500397857018e-05,
+      "loss": 0.2296,
+      "num_input_tokens_seen": 68157440,
+      "step": 260
+    },
+    {
+      "epoch": 2.0329776915615905,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 2.3125386803640187e-05,
+      "loss": 0.2333,
+      "num_input_tokens_seen": 68681728,
+      "step": 262
+    },
+    {
+      "epoch": 2.0484966052376334,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 2.2435543728894792e-05,
+      "loss": 0.2119,
+      "num_input_tokens_seen": 69206016,
+      "step": 264
+    },
+    {
+      "epoch": 2.064015518913676,
+      "grad_norm": 0.099609375,
+      "learning_rate": 2.175315780021411e-05,
+      "loss": 0.2676,
+      "num_input_tokens_seen": 69730304,
+      "step": 266
+    },
+    {
+      "epoch": 2.079534432589719,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 2.1078413626773546e-05,
+      "loss": 0.2285,
+      "num_input_tokens_seen": 70254592,
+      "step": 268
+    },
+    {
+      "epoch": 2.0950533462657615,
+      "grad_norm": 0.10546875,
+      "learning_rate": 2.0411493750387423e-05,
+      "loss": 0.2281,
+      "num_input_tokens_seen": 70778880,
+      "step": 270
+    },
+    {
+      "epoch": 2.110572259941804,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 1.9752578596124954e-05,
+      "loss": 0.2701,
+      "num_input_tokens_seen": 71303168,
+      "step": 272
+    },
+    {
+      "epoch": 2.126091173617847,
+      "grad_norm": 0.08984375,
+      "learning_rate": 1.9101846423499116e-05,
+      "loss": 0.2033,
+      "num_input_tokens_seen": 71827456,
+      "step": 274
+    },
+    {
+      "epoch": 2.1416100872938895,
+      "grad_norm": 0.10546875,
+      "learning_rate": 1.8459473278241126e-05,
+      "loss": 0.2489,
+      "num_input_tokens_seen": 72351744,
+      "step": 276
+    },
+    {
+      "epoch": 2.157129000969932,
+      "grad_norm": 0.1015625,
+      "learning_rate": 1.7825632944674015e-05,
+      "loss": 0.2294,
+      "num_input_tokens_seen": 72876032,
+      "step": 278
+    },
+    {
+      "epoch": 2.172647914645975,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 1.7200496898697832e-05,
+      "loss": 0.2452,
+      "num_input_tokens_seen": 73400320,
+      "step": 280
+    },
+    {
+      "epoch": 2.1881668283220175,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.6584234261399534e-05,
+      "loss": 0.242,
+      "num_input_tokens_seen": 73924608,
+      "step": 282
+    },
+    {
+      "epoch": 2.20368574199806,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 1.5977011753299725e-05,
+      "loss": 0.2894,
+      "num_input_tokens_seen": 74448896,
+      "step": 284
+    },
+    {
+      "epoch": 2.219204655674103,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 1.537899364924905e-05,
+      "loss": 0.231,
+      "num_input_tokens_seen": 74973184,
+      "step": 286
+    },
+    {
+      "epoch": 2.2347235693501455,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 1.4790341733986085e-05,
+      "loss": 0.2412,
+      "num_input_tokens_seen": 75497472,
+      "step": 288
+    },
+    {
+      "epoch": 2.250242483026188,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 1.4211215258368866e-05,
+      "loss": 0.2464,
+      "num_input_tokens_seen": 76021760,
+      "step": 290
+    },
+    {
+      "epoch": 2.265761396702231,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 1.3641770896292084e-05,
+      "loss": 0.2231,
+      "num_input_tokens_seen": 76546048,
+      "step": 292
+    },
+    {
+      "epoch": 2.2812803103782735,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 1.3082162702301276e-05,
+      "loss": 0.2432,
+      "num_input_tokens_seen": 77070336,
+      "step": 294
+    },
+    {
+      "epoch": 2.296799224054316,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.253254206991572e-05,
+      "loss": 0.2147,
+      "num_input_tokens_seen": 77594624,
+      "step": 296
+    },
+    {
+      "epoch": 2.312318137730359,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 1.1993057690671173e-05,
+      "loss": 0.249,
+      "num_input_tokens_seen": 78118912,
+      "step": 298
+    },
+    {
+      "epoch": 2.3278370514064015,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 1.1463855513893695e-05,
+      "loss": 0.2362,
+      "num_input_tokens_seen": 78643200,
+      "step": 300
+    },
+    {
+      "epoch": 2.343355965082444,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 1.0945078707215222e-05,
+      "loss": 0.2232,
+      "num_input_tokens_seen": 79167488,
+      "step": 302
+    },
+    {
+      "epoch": 2.358874878758487,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 1.0436867617841768e-05,
+      "loss": 0.2569,
+      "num_input_tokens_seen": 79691776,
+      "step": 304
+    },
+    {
+      "epoch": 2.3743937924345295,
+      "grad_norm": 0.10546875,
+      "learning_rate": 9.939359734584553e-06,
+      "loss": 0.214,
+      "num_input_tokens_seen": 80216064,
+      "step": 306
+    },
+    {
+      "epoch": 2.3899127061105725,
+      "grad_norm": 0.09765625,
+      "learning_rate": 9.452689650664515e-06,
+      "loss": 0.2451,
+      "num_input_tokens_seen": 80740352,
+      "step": 308
+    },
+    {
+      "epoch": 2.405431619786615,
+      "grad_norm": 0.09375,
+      "learning_rate": 8.976989027300264e-06,
+      "loss": 0.2288,
+      "num_input_tokens_seen": 81264640,
+      "step": 310
+    },
+    {
+      "epoch": 2.4209505334626575,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 8.51238655808892e-06,
+      "loss": 0.2332,
+      "num_input_tokens_seen": 81788928,
+      "step": 312
+    },
+    {
+      "epoch": 2.4364694471387,
+      "grad_norm": 0.095703125,
+      "learning_rate": 8.059007934190194e-06,
+      "loss": 0.202,
+      "num_input_tokens_seen": 82313216,
+      "step": 314
+    },
+    {
+      "epoch": 2.451988360814743,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 7.61697581032243e-06,
+      "loss": 0.227,
+      "num_input_tokens_seen": 82837504,
+      "step": 316
+    },
+    {
+      "epoch": 2.4675072744907856,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 7.186409771580354e-06,
+      "loss": 0.2429,
+      "num_input_tokens_seen": 83361792,
+      "step": 318
+    },
+    {
+      "epoch": 2.4830261881668285,
+      "grad_norm": 0.09375,
+      "learning_rate": 6.76742630108298e-06,
+      "loss": 0.2147,
+      "num_input_tokens_seen": 83886080,
+      "step": 320
+    },
+    {
+      "epoch": 2.498545101842871,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 6.3601387484610145e-06,
+      "loss": 0.2423,
+      "num_input_tokens_seen": 84410368,
+      "step": 322
+    },
+    {
+      "epoch": 2.5140640155189136,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 5.9646572991917116e-06,
+      "loss": 0.2828,
+      "num_input_tokens_seen": 84934656,
+      "step": 324
+    },
+    {
+      "epoch": 2.529582929194956,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 5.581088944789953e-06,
+      "loss": 0.2461,
+      "num_input_tokens_seen": 85458944,
+      "step": 326
+    },
+    {
+      "epoch": 2.545101842870999,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 5.209537453863289e-06,
+      "loss": 0.296,
+      "num_input_tokens_seen": 85983232,
+      "step": 328
+    },
+    {
+      "epoch": 2.5606207565470416,
+      "grad_norm": 0.08984375,
+      "learning_rate": 4.850103344038853e-06,
+      "loss": 0.2061,
+      "num_input_tokens_seen": 86507520,
+      "step": 330
+    },
+    {
+      "epoch": 2.5761396702230845,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 4.502883854769935e-06,
+      "loss": 0.2323,
+      "num_input_tokens_seen": 87031808,
+      "step": 332
+    },
+    {
+      "epoch": 2.591658583899127,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 4.167972921029262e-06,
+      "loss": 0.2156,
+      "num_input_tokens_seen": 87556096,
+      "step": 334
+    },
+    {
+      "epoch": 2.6071774975751696,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 3.845461147896323e-06,
+      "loss": 0.2393,
+      "num_input_tokens_seen": 88080384,
+      "step": 336
+    },
+    {
+      "epoch": 2.6226964112512126,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 3.535435786045538e-06,
+      "loss": 0.2165,
+      "num_input_tokens_seen": 88604672,
+      "step": 338
+    },
+    {
+      "epoch": 2.638215324927255,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 3.2379807081419187e-06,
+      "loss": 0.2313,
+      "num_input_tokens_seen": 89128960,
+      "step": 340
+    },
+    {
+      "epoch": 2.653734238603298,
+      "grad_norm": 0.099609375,
+      "learning_rate": 2.9531763861505966e-06,
+      "loss": 0.2336,
+      "num_input_tokens_seen": 89653248,
+      "step": 342
+    },
+    {
+      "epoch": 2.6692531522793406,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 2.6810998695663282e-06,
+      "loss": 0.2311,
+      "num_input_tokens_seen": 90177536,
+      "step": 344
+    },
+    {
+      "epoch": 2.684772065955383,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 2.4218247645689307e-06,
+      "loss": 0.213,
+      "num_input_tokens_seen": 90701824,
+      "step": 346
+    },
+    {
+      "epoch": 2.7002909796314256,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 2.1754212141102346e-06,
+      "loss": 0.2364,
+      "num_input_tokens_seen": 91226112,
+      "step": 348
+    },
+    {
+      "epoch": 2.7158098933074686,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 1.941955878938029e-06,
+      "loss": 0.2147,
+      "num_input_tokens_seen": 91750400,
+      "step": 350
+    },
+    {
+      "epoch": 2.731328806983511,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 1.7214919195619127e-06,
+      "loss": 0.2316,
+      "num_input_tokens_seen": 92274688,
+      "step": 352
+    },
+    {
+      "epoch": 2.746847720659554,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 1.514088979166256e-06,
+      "loss": 0.2263,
+      "num_input_tokens_seen": 92798976,
+      "step": 354
+    },
+    {
+      "epoch": 2.7623666343355966,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.3198031674745813e-06,
+      "loss": 0.2323,
+      "num_input_tokens_seen": 93323264,
+      "step": 356
+    },
+    {
+      "epoch": 2.777885548011639,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 1.138687045569975e-06,
+      "loss": 0.2246,
+      "num_input_tokens_seen": 93847552,
+      "step": 358
+    },
+    {
+      "epoch": 2.7934044616876816,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 9.707896116754488e-07,
+      "loss": 0.2287,
+      "num_input_tokens_seen": 94371840,
+      "step": 360
+    },
+    {
+      "epoch": 2.8089233753637246,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 8.161562878982398e-07,
+      "loss": 0.2081,
+      "num_input_tokens_seen": 94896128,
+      "step": 362
+    },
+    {
+      "epoch": 2.824442289039767,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 6.74828907941516e-07,
+      "loss": 0.226,
+      "num_input_tokens_seen": 95420416,
+      "step": 364
+    },
+    {
+      "epoch": 2.83996120271581,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 5.468457057869358e-07,
+      "loss": 0.273,
+      "num_input_tokens_seen": 95944704,
+      "step": 366
+    },
+    {
+      "epoch": 2.8554801163918526,
+      "grad_norm": 0.107421875,
+      "learning_rate": 4.322413053509944e-07,
+      "loss": 0.2634,
+      "num_input_tokens_seen": 96468992,
+      "step": 368
+    },
+    {
+      "epoch": 2.870999030067895,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 3.3104671111806593e-07,
+      "loss": 0.2592,
+      "num_input_tokens_seen": 96993280,
+      "step": 370
+    },
+    {
+      "epoch": 2.8865179437439377,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 2.432892997526026e-07,
+      "loss": 0.2566,
+      "num_input_tokens_seen": 97517568,
+      "step": 372
+    },
+    {
+      "epoch": 2.9020368574199806,
+      "grad_norm": 0.099609375,
+      "learning_rate": 1.6899281269279755e-07,
+      "loss": 0.2575,
+      "num_input_tokens_seen": 98041856,
+      "step": 374
+    },
+    {
+      "epoch": 2.917555771096023,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.0817734972768944e-07,
+      "loss": 0.2482,
+      "num_input_tokens_seen": 98566144,
+      "step": 376
+    },
+    {
+      "epoch": 2.933074684772066,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 6.085936355947897e-08,
+      "loss": 0.2483,
+      "num_input_tokens_seen": 99090432,
+      "step": 378
+    },
+    {
+      "epoch": 2.9485935984481086,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 2.7051655352494652e-08,
+      "loss": 0.2359,
+      "num_input_tokens_seen": 99614720,
+      "step": 380
+    },
+    {
+      "epoch": 2.964112512124151,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 6.763371270035457e-09,
+      "loss": 0.2434,
+      "num_input_tokens_seen": 100139008,
+      "step": 382
+    },
+    {
+      "epoch": 2.979631425800194,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 0.0,
+      "loss": 0.2042,
+      "num_input_tokens_seen": 100663296,
+      "step": 384
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 384,
+  "num_input_tokens_seen": 100663296,
+  "num_train_epochs": 3,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.2827022437921587e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-384/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641fd8445c27c8de50beaa5c1f0c27c0a3d158ba94db539f56dbd8c858546757
+size 5368

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.979631425800194,
+    "eval_loss": 0.259890079498291,
+    "eval_runtime": 44.8481,
+    "eval_samples_per_second": 38.686,
+    "eval_steps_per_second": 1.226,
+    "num_input_tokens_seen": 100663296,
+    "perplexity": 1.2967875352947666
+}

llamaboard_config.yaml

@@ -0,0 +1,67 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Qwen2-7B-Chat
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: qwen
+top.visual_inputs: false
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 4
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 1024
+train.dataset:
+- cangjie
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: '1.0e-4'
+train.logging_steps: 2
+train.lora_alpha: 32
+train.lora_dropout: 0.1
+train.lora_rank: 8
+train.lora_target: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
+train.loraplus_lr_ratio: 16
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.optim: adamw_torch
+train.packing: true
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 5000
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Pre-Training
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0.05
+train.warmup_steps: 2

running_log.txt

@@ -0,0 +1,749 @@
+08/16/2024 12:33:49 - WARNING - llamafactory.hparams.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+08/16/2024 12:33:49 - INFO - llamafactory.hparams.parser - Process rank: 6, device: xpu:6, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:49 - WARNING - llamafactory.hparams.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+08/16/2024 12:33:49 - INFO - llamafactory.hparams.parser - Process rank: 1, device: xpu:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:49 - WARNING - llamafactory.hparams.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+08/16/2024 12:33:49 - INFO - llamafactory.hparams.parser - Process rank: 2, device: xpu:2, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:50 - WARNING - llamafactory.hparams.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+08/16/2024 12:33:50 - INFO - llamafactory.hparams.parser - Process rank: 7, device: xpu:7, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:50 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+08/16/2024 12:33:50 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+[WARNING|parser.py:296] 2024-08-16 12:33:50,245 >> `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+[INFO|parser.py:348] 2024-08-16 12:33:50,246 >> Process rank: 0, device: xpu:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:50 - WARNING - llamafactory.hparams.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+08/16/2024 12:33:50 - INFO - llamafactory.hparams.parser - Process rank: 4, device: xpu:4, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:50 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+08/16/2024 12:33:50 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-16 12:33:50,368 >> loading file vocab.json from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/vocab.json
+
+08/16/2024 12:33:50 - WARNING - llamafactory.hparams.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+08/16/2024 12:33:50 - INFO - llamafactory.hparams.parser - Process rank: 5, device: xpu:5, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:50 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-16 12:33:50,368 >> loading file merges.txt from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/merges.txt
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-16 12:33:50,368 >> loading file tokenizer.json from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/tokenizer.json
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-16 12:33:50,368 >> loading file added_tokens.json from cache at None
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-16 12:33:50,368 >> loading file special_tokens_map.json from cache at None
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-16 12:33:50,368 >> loading file tokenizer_config.json from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2533] 2024-08-16 12:33:50,597 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|template.py:270] 2024-08-16 12:33:50,597 >> Replace eos token: <|im_end|>
+
+[INFO|loader.py:52] 2024-08-16 12:33:50,598 >> Loading dataset cangjie.json...
+
+08/16/2024 12:33:50 - WARNING - llamafactory.hparams.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+08/16/2024 12:33:50 - INFO - llamafactory.hparams.parser - Process rank: 3, device: xpu:3, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+08/16/2024 12:33:50 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+08/16/2024 12:33:51 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+08/16/2024 12:33:52 - INFO - llamafactory.data.loader - Loading dataset cangjie.json...
+
+08/16/2024 12:33:52 - INFO - llamafactory.data.loader - Loading dataset cangjie.json...
+
+08/16/2024 12:33:52 - INFO - llamafactory.data.loader - Loading dataset cangjie.json...
+
+08/16/2024 12:33:52 - INFO - llamafactory.data.loader - Loading dataset cangjie.json...
+
+08/16/2024 12:33:52 - INFO - llamafactory.data.loader - Loading dataset cangjie.json...
+
+08/16/2024 12:33:52 - INFO - llamafactory.data.loader - Loading dataset cangjie.json...
+
+08/16/2024 12:33:52 - INFO - llamafactory.data.loader - Loading dataset cangjie.json...
+
+[INFO|configuration_utils.py:733] 2024-08-16 12:33:53,975 >> loading configuration file config.json from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json
+
+[INFO|configuration_utils.py:800] 2024-08-16 12:33:53,979 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|modeling_utils.py:3644] 2024-08-16 12:33:54,043 >> loading weights file model.safetensors from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/model.safetensors.index.json
+
+[INFO|modeling_utils.py:1572] 2024-08-16 12:33:54,047 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|configuration_utils.py:1038] 2024-08-16 12:33:54,052 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+08/16/2024 12:34:40 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+08/16/2024 12:34:40 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
+
+08/16/2024 12:34:40 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+08/16/2024 12:34:40 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+08/16/2024 12:34:40 - WARNING - bitsandbytes.cextension - The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:34:40 - INFO - llamafactory.model.loader - trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+08/16/2024 12:34:40 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+08/16/2024 12:34:57 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+08/16/2024 12:34:57 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
+
+08/16/2024 12:34:57 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+08/16/2024 12:34:57 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+08/16/2024 12:34:57 - WARNING - bitsandbytes.cextension - The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:34:57 - INFO - llamafactory.model.loader - trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+08/16/2024 12:34:58 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+08/16/2024 12:34:58 - WARNING - bitsandbytes.cextension - The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.loader - trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+08/16/2024 12:34:58 - WARNING - bitsandbytes.cextension - The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:34:58 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+08/16/2024 12:34:58 - WARNING - bitsandbytes.cextension - The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:34:58 - INFO - llamafactory.model.loader - trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+[INFO|modeling_utils.py:4473] 2024-08-16 12:34:59,011 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+[INFO|modeling_utils.py:4481] 2024-08-16 12:34:59,011 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-7B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
+
+[INFO|configuration_utils.py:993] 2024-08-16 12:34:59,106 >> loading configuration file generation_config.json from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/generation_config.json
+
+[INFO|configuration_utils.py:1038] 2024-08-16 12:34:59,106 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8
+}
+
+
+08/16/2024 12:34:59 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+[INFO|checkpointing.py:103] 2024-08-16 12:34:59,217 >> Gradient checkpointing enabled.
+
+[INFO|attention.py:86] 2024-08-16 12:34:59,217 >> Using vanilla attention implementation.
+
+[INFO|adapter.py:302] 2024-08-16 12:34:59,217 >> Upcasting trainable params to float32.
+
+[INFO|adapter.py:158] 2024-08-16 12:34:59,218 >> Fine-tuning method: LoRA
+
+[WARNING|cextension.py:101] 2024-08-16 12:34:59,228 >> The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:34:59 - INFO - llamafactory.model.loader - trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+08/16/2024 12:34:59 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+08/16/2024 12:34:59 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
+
+08/16/2024 12:34:59 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+08/16/2024 12:34:59 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+08/16/2024 12:34:59 - WARNING - bitsandbytes.cextension - The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:34:59 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+[INFO|loader.py:196] 2024-08-16 12:34:59,540 >> trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+[INFO|trainer.py:648] 2024-08-16 12:34:59,550 >> Using auto half precision backend
+
+[INFO|trainer_utils.py:305] 2024-08-16 12:34:59,691 >> Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+08/16/2024 12:34:59 - INFO - llamafactory.model.loader - trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+08/16/2024 12:34:59 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+08/16/2024 12:35:00 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+08/16/2024 12:35:00 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
+
+08/16/2024 12:35:00 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+08/16/2024 12:35:00 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+08/16/2024 12:35:00 - WARNING - bitsandbytes.cextension - The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+
+08/16/2024 12:35:00 - INFO - llamafactory.model.loader - trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+08/16/2024 12:35:00 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.
+
+[INFO|trainer.py:2134] 2024-08-16 12:35:19,204 >> ***** Running training *****
+
+[INFO|trainer.py:2135] 2024-08-16 12:35:19,206 >>   Num examples = 32,962
+
+[INFO|trainer.py:2136] 2024-08-16 12:35:19,206 >>   Num Epochs = 3
+
+[INFO|trainer.py:2137] 2024-08-16 12:35:19,206 >>   Instantaneous batch size per device = 4
+
+[INFO|trainer.py:2140] 2024-08-16 12:35:19,206 >>   Total train batch size (w. parallel, distributed & accumulation) = 256
+
+[INFO|trainer.py:2141] 2024-08-16 12:35:19,206 >>   Gradient Accumulation steps = 8
+
+[INFO|trainer.py:2142] 2024-08-16 12:35:19,206 >>   Total optimization steps = 384
+
+[INFO|trainer.py:2143] 2024-08-16 12:35:19,210 >>   Number of trainable parameters = 20,185,088
+
+[INFO|callbacks.py:312] 2024-08-16 12:36:02,659 >> {'loss': 0.8310, 'learning_rate': 1.0000e-04, 'epoch': 0.02, 'throughput': 12068.40}
+
+[INFO|callbacks.py:312] 2024-08-16 12:36:44,933 >> {'loss': 0.7398, 'learning_rate': 9.9993e-05, 'epoch': 0.03, 'throughput': 12232.95}
+
+[INFO|callbacks.py:312] 2024-08-16 12:37:27,241 >> {'loss': 0.6438, 'learning_rate': 9.9973e-05, 'epoch': 0.05, 'throughput': 12285.60}
+
+[INFO|callbacks.py:312] 2024-08-16 12:38:09,612 >> {'loss': 0.6032, 'learning_rate': 9.9939e-05, 'epoch': 0.06, 'throughput': 12307.51}
+
+[INFO|callbacks.py:312] 2024-08-16 12:38:51,927 >> {'loss': 0.5433, 'learning_rate': 9.9892e-05, 'epoch': 0.08, 'throughput': 12323.95}
+
+[INFO|callbacks.py:312] 2024-08-16 12:39:34,282 >> {'loss': 0.5228, 'learning_rate': 9.9831e-05, 'epoch': 0.09, 'throughput': 12332.99}
+
+[INFO|callbacks.py:312] 2024-08-16 12:40:16,580 >> {'loss': 0.4702, 'learning_rate': 9.9757e-05, 'epoch': 0.11, 'throughput': 12341.83}
+
+[INFO|callbacks.py:312] 2024-08-16 12:40:58,913 >> {'loss': 0.4574, 'learning_rate': 9.9669e-05, 'epoch': 0.12, 'throughput': 12347.21}
+
+[INFO|callbacks.py:312] 2024-08-16 12:41:41,280 >> {'loss': 0.5093, 'learning_rate': 9.9568e-05, 'epoch': 0.14, 'throughput': 12350.26}
+
+[INFO|callbacks.py:312] 2024-08-16 12:42:23,640 >> {'loss': 0.4771, 'learning_rate': 9.9453e-05, 'epoch': 0.16, 'throughput': 12352.92}
+
+[INFO|callbacks.py:312] 2024-08-16 12:43:05,996 >> {'loss': 0.4343, 'learning_rate': 9.9325e-05, 'epoch': 0.17, 'throughput': 12355.21}
+
+[INFO|callbacks.py:312] 2024-08-16 12:43:48,388 >> {'loss': 0.4455, 'learning_rate': 9.9184e-05, 'epoch': 0.19, 'throughput': 12356.26}
+
+[INFO|callbacks.py:312] 2024-08-16 12:44:30,830 >> {'loss': 0.4669, 'learning_rate': 9.9029e-05, 'epoch': 0.20, 'throughput': 12356.01}
+
+[INFO|callbacks.py:312] 2024-08-16 12:45:13,185 >> {'loss': 0.4723, 'learning_rate': 9.8861e-05, 'epoch': 0.22, 'throughput': 12357.59}
+
+[INFO|callbacks.py:312] 2024-08-16 12:45:55,574 >> {'loss': 0.4364, 'learning_rate': 9.8680e-05, 'epoch': 0.23, 'throughput': 12358.33}
+
+[INFO|callbacks.py:312] 2024-08-16 12:46:37,892 >> {'loss': 0.4013, 'learning_rate': 9.8486e-05, 'epoch': 0.25, 'throughput': 12360.25}
+
+[INFO|callbacks.py:312] 2024-08-16 12:47:20,267 >> {'loss': 0.3875, 'learning_rate': 9.8279e-05, 'epoch': 0.26, 'throughput': 12360.97}
+
+[INFO|callbacks.py:312] 2024-08-16 12:48:02,620 >> {'loss': 0.4187, 'learning_rate': 9.8058e-05, 'epoch': 0.28, 'throughput': 12361.99}
+
+[INFO|callbacks.py:312] 2024-08-16 12:48:44,965 >> {'loss': 0.3981, 'learning_rate': 9.7825e-05, 'epoch': 0.29, 'throughput': 12363.00}
+
+[INFO|callbacks.py:312] 2024-08-16 12:49:27,368 >> {'loss': 0.4121, 'learning_rate': 9.7578e-05, 'epoch': 0.31, 'throughput': 12363.06}
+
+[INFO|callbacks.py:312] 2024-08-16 12:50:09,733 >> {'loss': 0.3920, 'learning_rate': 9.7319e-05, 'epoch': 0.33, 'throughput': 12363.66}
+
+[INFO|callbacks.py:312] 2024-08-16 12:50:52,018 >> {'loss': 0.3845, 'learning_rate': 9.7047e-05, 'epoch': 0.34, 'throughput': 12365.26}
+
+[INFO|callbacks.py:312] 2024-08-16 12:51:34,403 >> {'loss': 0.3970, 'learning_rate': 9.6762e-05, 'epoch': 0.36, 'throughput': 12365.45}
+
+[INFO|callbacks.py:312] 2024-08-16 12:52:16,774 >> {'loss': 0.3753, 'learning_rate': 9.6465e-05, 'epoch': 0.37, 'throughput': 12365.80}
+
+[INFO|callbacks.py:312] 2024-08-16 12:52:59,105 >> {'loss': 0.3870, 'learning_rate': 9.6155e-05, 'epoch': 0.39, 'throughput': 12366.58}
+
+[INFO|callbacks.py:312] 2024-08-16 12:53:41,453 >> {'loss': 0.3724, 'learning_rate': 9.5832e-05, 'epoch': 0.40, 'throughput': 12367.11}
+
+[INFO|callbacks.py:312] 2024-08-16 12:54:23,808 >> {'loss': 0.4394, 'learning_rate': 9.5497e-05, 'epoch': 0.42, 'throughput': 12367.54}
+
+[INFO|callbacks.py:312] 2024-08-16 12:55:06,153 >> {'loss': 0.4177, 'learning_rate': 9.5150e-05, 'epoch': 0.43, 'throughput': 12368.03}
+
+[INFO|callbacks.py:312] 2024-08-16 12:55:48,525 >> {'loss': 0.3939, 'learning_rate': 9.4790e-05, 'epoch': 0.45, 'throughput': 12368.21}
+
+[INFO|callbacks.py:312] 2024-08-16 12:56:30,845 >> {'loss': 0.4207, 'learning_rate': 9.4419e-05, 'epoch': 0.47, 'throughput': 12368.89}
+
+[INFO|callbacks.py:312] 2024-08-16 12:57:13,203 >> {'loss': 0.3653, 'learning_rate': 9.4035e-05, 'epoch': 0.48, 'throughput': 12369.17}
+
+[INFO|callbacks.py:312] 2024-08-16 12:57:55,540 >> {'loss': 0.3925, 'learning_rate': 9.3640e-05, 'epoch': 0.50, 'throughput': 12369.62}
+
+[INFO|callbacks.py:312] 2024-08-16 12:58:37,884 >> {'loss': 0.3982, 'learning_rate': 9.3233e-05, 'epoch': 0.51, 'throughput': 12369.99}
+
+[INFO|callbacks.py:312] 2024-08-16 12:59:20,230 >> {'loss': 0.3709, 'learning_rate': 9.2814e-05, 'epoch': 0.53, 'throughput': 12370.31}
+
+[INFO|callbacks.py:312] 2024-08-16 13:00:02,597 >> {'loss': 0.3744, 'learning_rate': 9.2383e-05, 'epoch': 0.54, 'throughput': 12370.44}
+
+[INFO|callbacks.py:312] 2024-08-16 13:00:44,955 >> {'loss': 0.3929, 'learning_rate': 9.1941e-05, 'epoch': 0.56, 'throughput': 12370.64}
+
+[INFO|callbacks.py:312] 2024-08-16 13:01:27,325 >> {'loss': 0.3716, 'learning_rate': 9.1488e-05, 'epoch': 0.57, 'throughput': 12370.73}
+
+[INFO|callbacks.py:312] 2024-08-16 13:02:09,657 >> {'loss': 0.3959, 'learning_rate': 9.1023e-05, 'epoch': 0.59, 'throughput': 12371.11}
+
+[INFO|callbacks.py:312] 2024-08-16 13:02:52,031 >> {'loss': 0.3514, 'learning_rate': 9.0547e-05, 'epoch': 0.61, 'throughput': 12371.15}
+
+[INFO|callbacks.py:312] 2024-08-16 13:03:34,381 >> {'loss': 0.3767, 'learning_rate': 9.0061e-05, 'epoch': 0.62, 'throughput': 12371.38}
+
+[INFO|callbacks.py:312] 2024-08-16 13:04:16,765 >> {'loss': 0.3710, 'learning_rate': 8.9563e-05, 'epoch': 0.64, 'throughput': 12371.34}
+
+[INFO|callbacks.py:312] 2024-08-16 13:04:59,089 >> {'loss': 0.3529, 'learning_rate': 8.9055e-05, 'epoch': 0.65, 'throughput': 12371.72}
+
+[INFO|callbacks.py:312] 2024-08-16 13:05:41,445 >> {'loss': 0.3044, 'learning_rate': 8.8536e-05, 'epoch': 0.67, 'throughput': 12371.87}
+
+[INFO|callbacks.py:312] 2024-08-16 13:06:23,764 >> {'loss': 0.3532, 'learning_rate': 8.8007e-05, 'epoch': 0.68, 'throughput': 12372.26}
+
+[INFO|callbacks.py:312] 2024-08-16 13:07:06,185 >> {'loss': 0.3461, 'learning_rate': 8.7467e-05, 'epoch': 0.70, 'throughput': 12371.97}
+
+[INFO|callbacks.py:312] 2024-08-16 13:07:48,606 >> {'loss': 0.3513, 'learning_rate': 8.6918e-05, 'epoch': 0.71, 'throughput': 12371.69}
+
+[INFO|callbacks.py:312] 2024-08-16 13:08:30,947 >> {'loss': 0.3842, 'learning_rate': 8.6358e-05, 'epoch': 0.73, 'throughput': 12371.92}
+
+[INFO|callbacks.py:312] 2024-08-16 13:09:13,288 >> {'loss': 0.3630, 'learning_rate': 8.5789e-05, 'epoch': 0.74, 'throughput': 12372.14}
+
+[INFO|callbacks.py:312] 2024-08-16 13:09:55,576 >> {'loss': 0.3079, 'learning_rate': 8.5210e-05, 'epoch': 0.76, 'throughput': 12372.67}
+
+[INFO|callbacks.py:312] 2024-08-16 13:10:37,964 >> {'loss': 0.3769, 'learning_rate': 8.4621e-05, 'epoch': 0.78, 'throughput': 12372.59}
+
+[INFO|callbacks.py:312] 2024-08-16 13:11:20,331 >> {'loss': 0.3907, 'learning_rate': 8.4023e-05, 'epoch': 0.79, 'throughput': 12372.64}
+
+[INFO|callbacks.py:312] 2024-08-16 13:12:02,695 >> {'loss': 0.3457, 'learning_rate': 8.3416e-05, 'epoch': 0.81, 'throughput': 12372.69}
+
+[INFO|callbacks.py:312] 2024-08-16 13:12:45,011 >> {'loss': 0.3889, 'learning_rate': 8.2800e-05, 'epoch': 0.82, 'throughput': 12373.02}
+
+[INFO|callbacks.py:312] 2024-08-16 13:13:27,369 >> {'loss': 0.3142, 'learning_rate': 8.2174e-05, 'epoch': 0.84, 'throughput': 12373.10}
+
+[INFO|callbacks.py:312] 2024-08-16 13:14:09,715 >> {'loss': 0.3299, 'learning_rate': 8.1541e-05, 'epoch': 0.85, 'throughput': 12373.25}
+
+[INFO|callbacks.py:312] 2024-08-16 13:14:52,085 >> {'loss': 0.3425, 'learning_rate': 8.0898e-05, 'epoch': 0.87, 'throughput': 12373.26}
+
+[INFO|callbacks.py:312] 2024-08-16 13:15:34,456 >> {'loss': 0.3363, 'learning_rate': 8.0247e-05, 'epoch': 0.88, 'throughput': 12373.27}
+
+[INFO|callbacks.py:312] 2024-08-16 13:16:16,801 >> {'loss': 0.3725, 'learning_rate': 7.9589e-05, 'epoch': 0.90, 'throughput': 12373.41}
+
+[INFO|callbacks.py:312] 2024-08-16 13:16:59,117 >> {'loss': 0.3397, 'learning_rate': 7.8922e-05, 'epoch': 0.92, 'throughput': 12373.69}
+
+[INFO|callbacks.py:312] 2024-08-16 13:17:41,455 >> {'loss': 0.2812, 'learning_rate': 7.8247e-05, 'epoch': 0.93, 'throughput': 12373.85}
+
+[INFO|callbacks.py:312] 2024-08-16 13:18:23,836 >> {'loss': 0.3555, 'learning_rate': 7.7564e-05, 'epoch': 0.95, 'throughput': 12373.80}
+
+[INFO|callbacks.py:312] 2024-08-16 13:19:06,200 >> {'loss': 0.3362, 'learning_rate': 7.6875e-05, 'epoch': 0.96, 'throughput': 12373.83}
+
+[INFO|callbacks.py:312] 2024-08-16 13:19:48,535 >> {'loss': 0.3133, 'learning_rate': 7.6177e-05, 'epoch': 0.98, 'throughput': 12374.00}
+
+[INFO|callbacks.py:312] 2024-08-16 13:20:30,848 >> {'loss': 0.3119, 'learning_rate': 7.5473e-05, 'epoch': 0.99, 'throughput': 12374.26}
+
+[INFO|callbacks.py:312] 2024-08-16 13:21:13,219 >> {'loss': 0.3117, 'learning_rate': 7.4762e-05, 'epoch': 1.01, 'throughput': 12374.25}
+
+[INFO|callbacks.py:312] 2024-08-16 13:21:55,569 >> {'loss': 0.3290, 'learning_rate': 7.4044e-05, 'epoch': 1.02, 'throughput': 12374.33}
+
+[INFO|callbacks.py:312] 2024-08-16 13:22:37,938 >> {'loss': 0.2790, 'learning_rate': 7.3320e-05, 'epoch': 1.04, 'throughput': 12374.33}
+
+[INFO|callbacks.py:312] 2024-08-16 13:23:20,316 >> {'loss': 0.2682, 'learning_rate': 7.2590e-05, 'epoch': 1.06, 'throughput': 12374.30}
+
+[INFO|callbacks.py:312] 2024-08-16 13:24:02,700 >> {'loss': 0.2930, 'learning_rate': 7.1853e-05, 'epoch': 1.07, 'throughput': 12374.23}
+
+[INFO|callbacks.py:312] 2024-08-16 13:24:45,029 >> {'loss': 0.3150, 'learning_rate': 7.1110e-05, 'epoch': 1.09, 'throughput': 12374.40}
+
+[INFO|callbacks.py:312] 2024-08-16 13:25:27,456 >> {'loss': 0.2890, 'learning_rate': 7.0362e-05, 'epoch': 1.10, 'throughput': 12374.16}
+
+[INFO|callbacks.py:312] 2024-08-16 13:26:09,792 >> {'loss': 0.2808, 'learning_rate': 6.9608e-05, 'epoch': 1.12, 'throughput': 12374.30}
+
+[INFO|callbacks.py:312] 2024-08-16 13:26:52,153 >> {'loss': 0.3180, 'learning_rate': 6.8849e-05, 'epoch': 1.13, 'throughput': 12374.33}
+
+[INFO|callbacks.py:312] 2024-08-16 13:27:34,497 >> {'loss': 0.2685, 'learning_rate': 6.8085e-05, 'epoch': 1.15, 'throughput': 12374.43}
+
+[INFO|callbacks.py:312] 2024-08-16 13:28:16,828 >> {'loss': 0.3121, 'learning_rate': 6.7315e-05, 'epoch': 1.16, 'throughput': 12374.58}
+
+[INFO|callbacks.py:312] 2024-08-16 13:28:59,183 >> {'loss': 0.2835, 'learning_rate': 6.6542e-05, 'epoch': 1.18, 'throughput': 12374.63}
+
+[INFO|callbacks.py:312] 2024-08-16 13:29:41,447 >> {'loss': 0.2905, 'learning_rate': 6.5763e-05, 'epoch': 1.19, 'throughput': 12375.02}
+
+[INFO|callbacks.py:312] 2024-08-16 13:30:23,793 >> {'loss': 0.3277, 'learning_rate': 6.4981e-05, 'epoch': 1.21, 'throughput': 12375.10}
+
+[INFO|callbacks.py:312] 2024-08-16 13:31:06,159 >> {'loss': 0.2788, 'learning_rate': 6.4194e-05, 'epoch': 1.23, 'throughput': 12375.10}
+
+[INFO|callbacks.py:312] 2024-08-16 13:31:48,520 >> {'loss': 0.2971, 'learning_rate': 6.3404e-05, 'epoch': 1.24, 'throughput': 12375.12}
+
+[INFO|callbacks.py:312] 2024-08-16 13:32:30,924 >> {'loss': 0.2870, 'learning_rate': 6.2610e-05, 'epoch': 1.26, 'throughput': 12374.98}
+
+[INFO|callbacks.py:312] 2024-08-16 13:33:13,286 >> {'loss': 0.3196, 'learning_rate': 6.1812e-05, 'epoch': 1.27, 'throughput': 12375.00}
+
+[INFO|callbacks.py:312] 2024-08-16 13:33:55,649 >> {'loss': 0.3021, 'learning_rate': 6.1011e-05, 'epoch': 1.29, 'throughput': 12375.01}
+
+[INFO|callbacks.py:312] 2024-08-16 13:34:38,007 >> {'loss': 0.2329, 'learning_rate': 6.0208e-05, 'epoch': 1.30, 'throughput': 12375.04}
+
+[INFO|callbacks.py:312] 2024-08-16 13:35:20,352 >> {'loss': 0.2803, 'learning_rate': 5.9401e-05, 'epoch': 1.32, 'throughput': 12375.12}
+
+[INFO|callbacks.py:312] 2024-08-16 13:36:02,691 >> {'loss': 0.2744, 'learning_rate': 5.8592e-05, 'epoch': 1.33, 'throughput': 12375.21}
+
+[INFO|callbacks.py:312] 2024-08-16 13:36:44,975 >> {'loss': 0.3332, 'learning_rate': 5.7781e-05, 'epoch': 1.35, 'throughput': 12375.49}
+
+[INFO|callbacks.py:312] 2024-08-16 13:37:27,361 >> {'loss': 0.3223, 'learning_rate': 5.6968e-05, 'epoch': 1.37, 'throughput': 12375.42}
+
+[INFO|callbacks.py:312] 2024-08-16 13:38:09,707 >> {'loss': 0.3127, 'learning_rate': 5.6152e-05, 'epoch': 1.38, 'throughput': 12375.48}
+
+[INFO|callbacks.py:312] 2024-08-16 13:38:52,014 >> {'loss': 0.2908, 'learning_rate': 5.5335e-05, 'epoch': 1.40, 'throughput': 12375.67}
+
+[INFO|callbacks.py:312] 2024-08-16 13:39:34,381 >> {'loss': 0.2918, 'learning_rate': 5.4517e-05, 'epoch': 1.41, 'throughput': 12375.66}
+
+[INFO|callbacks.py:312] 2024-08-16 13:40:16,717 >> {'loss': 0.2680, 'learning_rate': 5.3697e-05, 'epoch': 1.43, 'throughput': 12375.75}
+
+[INFO|callbacks.py:312] 2024-08-16 13:40:59,093 >> {'loss': 0.2862, 'learning_rate': 5.2877e-05, 'epoch': 1.44, 'throughput': 12375.71}
+
+[INFO|callbacks.py:312] 2024-08-16 13:41:41,470 >> {'loss': 0.3054, 'learning_rate': 5.2055e-05, 'epoch': 1.46, 'throughput': 12375.67}
+
+[INFO|callbacks.py:312] 2024-08-16 13:42:23,818 >> {'loss': 0.2814, 'learning_rate': 5.1233e-05, 'epoch': 1.47, 'throughput': 12375.72}
+
+[INFO|callbacks.py:312] 2024-08-16 13:43:06,212 >> {'loss': 0.2703, 'learning_rate': 5.0411e-05, 'epoch': 1.49, 'throughput': 12375.63}
+
+[INFO|callbacks.py:312] 2024-08-16 13:43:48,537 >> {'loss': 0.2689, 'learning_rate': 4.9589e-05, 'epoch': 1.51, 'throughput': 12375.75}
+
+[INFO|callbacks.py:312] 2024-08-16 13:44:30,897 >> {'loss': 0.3013, 'learning_rate': 4.8767e-05, 'epoch': 1.52, 'throughput': 12375.76}
+
+[INFO|callbacks.py:312] 2024-08-16 13:45:13,277 >> {'loss': 0.2751, 'learning_rate': 4.7945e-05, 'epoch': 1.54, 'throughput': 12375.72}
+
+[INFO|callbacks.py:312] 2024-08-16 13:45:55,623 >> {'loss': 0.3178, 'learning_rate': 4.7123e-05, 'epoch': 1.55, 'throughput': 12375.77}
+
+[INFO|callbacks.py:312] 2024-08-16 13:46:37,977 >> {'loss': 0.2742, 'learning_rate': 4.6303e-05, 'epoch': 1.57, 'throughput': 12375.80}
+
+[INFO|callbacks.py:312] 2024-08-16 13:47:20,326 >> {'loss': 0.2751, 'learning_rate': 4.5483e-05, 'epoch': 1.58, 'throughput': 12375.84}
+
+[INFO|callbacks.py:312] 2024-08-16 13:48:02,717 >> {'loss': 0.3256, 'learning_rate': 4.4665e-05, 'epoch': 1.60, 'throughput': 12375.76}
+
+[INFO|callbacks.py:312] 2024-08-16 13:48:45,048 >> {'loss': 0.2603, 'learning_rate': 4.3848e-05, 'epoch': 1.61, 'throughput': 12375.86}
+
+[INFO|callbacks.py:312] 2024-08-16 13:49:27,372 >> {'loss': 0.2598, 'learning_rate': 4.3032e-05, 'epoch': 1.63, 'throughput': 12375.97}
+
+[INFO|callbacks.py:312] 2024-08-16 13:50:09,716 >> {'loss': 0.2811, 'learning_rate': 4.2219e-05, 'epoch': 1.65, 'throughput': 12376.02}
+
+[INFO|callbacks.py:312] 2024-08-16 13:50:52,092 >> {'loss': 0.2386, 'learning_rate': 4.1408e-05, 'epoch': 1.66, 'throughput': 12375.99}
+
+[INFO|callbacks.py:312] 2024-08-16 13:51:34,476 >> {'loss': 0.2999, 'learning_rate': 4.0599e-05, 'epoch': 1.68, 'throughput': 12375.93}
+
+[INFO|callbacks.py:312] 2024-08-16 13:52:16,880 >> {'loss': 0.2857, 'learning_rate': 3.9792e-05, 'epoch': 1.69, 'throughput': 12375.82}
+
+[INFO|callbacks.py:312] 2024-08-16 13:52:59,255 >> {'loss': 0.2533, 'learning_rate': 3.8989e-05, 'epoch': 1.71, 'throughput': 12375.79}
+
+[INFO|callbacks.py:312] 2024-08-16 13:53:41,557 >> {'loss': 0.3060, 'learning_rate': 3.8188e-05, 'epoch': 1.72, 'throughput': 12375.96}
+
+[INFO|callbacks.py:312] 2024-08-16 13:54:23,889 >> {'loss': 0.2594, 'learning_rate': 3.7390e-05, 'epoch': 1.74, 'throughput': 12376.04}
+
+[INFO|callbacks.py:312] 2024-08-16 13:55:06,247 >> {'loss': 0.2840, 'learning_rate': 3.6596e-05, 'epoch': 1.75, 'throughput': 12376.05}
+
+[INFO|callbacks.py:312] 2024-08-16 13:55:48,620 >> {'loss': 0.3300, 'learning_rate': 3.5806e-05, 'epoch': 1.77, 'throughput': 12376.03}
+
+[INFO|callbacks.py:312] 2024-08-16 13:56:31,000 >> {'loss': 0.2968, 'learning_rate': 3.5019e-05, 'epoch': 1.78, 'throughput': 12375.98}
+
+[INFO|callbacks.py:312] 2024-08-16 13:57:13,317 >> {'loss': 0.2836, 'learning_rate': 3.4237e-05, 'epoch': 1.80, 'throughput': 12376.10}
+
+[INFO|callbacks.py:312] 2024-08-16 13:57:55,663 >> {'loss': 0.2452, 'learning_rate': 3.3458e-05, 'epoch': 1.82, 'throughput': 12376.14}
+
+[INFO|callbacks.py:312] 2024-08-16 13:58:38,049 >> {'loss': 0.2526, 'learning_rate': 3.2685e-05, 'epoch': 1.83, 'throughput': 12376.09}
+
+[INFO|callbacks.py:312] 2024-08-16 13:59:20,385 >> {'loss': 0.2578, 'learning_rate': 3.1915e-05, 'epoch': 1.85, 'throughput': 12376.15}
+
+[INFO|callbacks.py:312] 2024-08-16 14:00:02,721 >> {'loss': 0.2895, 'learning_rate': 3.1151e-05, 'epoch': 1.86, 'throughput': 12376.22}
+
+[INFO|callbacks.py:312] 2024-08-16 14:00:45,089 >> {'loss': 0.3047, 'learning_rate': 3.0392e-05, 'epoch': 1.88, 'throughput': 12376.20}
+
+[INFO|callbacks.py:312] 2024-08-16 14:01:27,480 >> {'loss': 0.2958, 'learning_rate': 2.9638e-05, 'epoch': 1.89, 'throughput': 12376.13}
+
+[INFO|callbacks.py:312] 2024-08-16 14:02:09,856 >> {'loss': 0.2598, 'learning_rate': 2.8890e-05, 'epoch': 1.91, 'throughput': 12376.10}
+
+[INFO|callbacks.py:312] 2024-08-16 14:02:52,224 >> {'loss': 0.2699, 'learning_rate': 2.8147e-05, 'epoch': 1.92, 'throughput': 12376.09}
+
+[INFO|callbacks.py:312] 2024-08-16 14:03:34,541 >> {'loss': 0.2827, 'learning_rate': 2.7410e-05, 'epoch': 1.94, 'throughput': 12376.20}
+
+[INFO|callbacks.py:312] 2024-08-16 14:04:16,887 >> {'loss': 0.3119, 'learning_rate': 2.6680e-05, 'epoch': 1.96, 'throughput': 12376.24}
+
+[INFO|callbacks.py:312] 2024-08-16 14:04:59,273 >> {'loss': 0.2837, 'learning_rate': 2.5956e-05, 'epoch': 1.97, 'throughput': 12376.19}
+
+[INFO|callbacks.py:312] 2024-08-16 14:05:41,665 >> {'loss': 0.2511, 'learning_rate': 2.5238e-05, 'epoch': 1.99, 'throughput': 12376.12}
+
+[INFO|callbacks.py:312] 2024-08-16 14:06:24,053 >> {'loss': 0.2501, 'learning_rate': 2.4527e-05, 'epoch': 2.00, 'throughput': 12376.06}
+
+[INFO|callbacks.py:312] 2024-08-16 14:07:06,393 >> {'loss': 0.2296, 'learning_rate': 2.3823e-05, 'epoch': 2.02, 'throughput': 12376.11}
+
+[INFO|callbacks.py:312] 2024-08-16 14:07:48,745 >> {'loss': 0.2333, 'learning_rate': 2.3125e-05, 'epoch': 2.03, 'throughput': 12376.14}
+
+[INFO|callbacks.py:312] 2024-08-16 14:08:31,135 >> {'loss': 0.2119, 'learning_rate': 2.2436e-05, 'epoch': 2.05, 'throughput': 12376.08}
+
+[INFO|callbacks.py:312] 2024-08-16 14:09:13,523 >> {'loss': 0.2676, 'learning_rate': 2.1753e-05, 'epoch': 2.06, 'throughput': 12376.02}
+
+[INFO|callbacks.py:312] 2024-08-16 14:09:55,858 >> {'loss': 0.2285, 'learning_rate': 2.1078e-05, 'epoch': 2.08, 'throughput': 12376.08}
+
+[INFO|callbacks.py:312] 2024-08-16 14:10:38,203 >> {'loss': 0.2281, 'learning_rate': 2.0411e-05, 'epoch': 2.10, 'throughput': 12376.12}
+
+[INFO|callbacks.py:312] 2024-08-16 14:11:20,589 >> {'loss': 0.2701, 'learning_rate': 1.9753e-05, 'epoch': 2.11, 'throughput': 12376.07}
+
+[INFO|callbacks.py:312] 2024-08-16 14:12:03,007 >> {'loss': 0.2033, 'learning_rate': 1.9102e-05, 'epoch': 2.13, 'throughput': 12375.95}
+
+[INFO|callbacks.py:312] 2024-08-16 14:12:45,356 >> {'loss': 0.2489, 'learning_rate': 1.8459e-05, 'epoch': 2.14, 'throughput': 12375.99}
+
+[INFO|callbacks.py:312] 2024-08-16 14:13:27,726 >> {'loss': 0.2294, 'learning_rate': 1.7826e-05, 'epoch': 2.16, 'throughput': 12375.97}
+
+[INFO|callbacks.py:312] 2024-08-16 14:14:10,114 >> {'loss': 0.2452, 'learning_rate': 1.7200e-05, 'epoch': 2.17, 'throughput': 12375.92}
+
+[INFO|callbacks.py:312] 2024-08-16 14:14:52,477 >> {'loss': 0.2420, 'learning_rate': 1.6584e-05, 'epoch': 2.19, 'throughput': 12375.92}
+
+[INFO|callbacks.py:312] 2024-08-16 14:15:34,799 >> {'loss': 0.2894, 'learning_rate': 1.5977e-05, 'epoch': 2.20, 'throughput': 12376.01}
+
+[INFO|callbacks.py:312] 2024-08-16 14:16:17,116 >> {'loss': 0.2310, 'learning_rate': 1.5379e-05, 'epoch': 2.22, 'throughput': 12376.10}
+
+[INFO|callbacks.py:312] 2024-08-16 14:16:59,419 >> {'loss': 0.2412, 'learning_rate': 1.4790e-05, 'epoch': 2.23, 'throughput': 12376.22}
+
+[INFO|callbacks.py:312] 2024-08-16 14:17:41,780 >> {'loss': 0.2464, 'learning_rate': 1.4211e-05, 'epoch': 2.25, 'throughput': 12376.23}
+
+[INFO|callbacks.py:312] 2024-08-16 14:18:24,121 >> {'loss': 0.2231, 'learning_rate': 1.3642e-05, 'epoch': 2.27, 'throughput': 12376.27}
+
+[INFO|callbacks.py:312] 2024-08-16 14:19:06,463 >> {'loss': 0.2432, 'learning_rate': 1.3082e-05, 'epoch': 2.28, 'throughput': 12376.31}
+
+[INFO|callbacks.py:312] 2024-08-16 14:19:48,827 >> {'loss': 0.2147, 'learning_rate': 1.2533e-05, 'epoch': 2.30, 'throughput': 12376.31}
+
+[INFO|callbacks.py:312] 2024-08-16 14:20:31,125 >> {'loss': 0.2490, 'learning_rate': 1.1993e-05, 'epoch': 2.31, 'throughput': 12376.43}
+
+[INFO|callbacks.py:312] 2024-08-16 14:21:13,484 >> {'loss': 0.2362, 'learning_rate': 1.1464e-05, 'epoch': 2.33, 'throughput': 12376.44}
+
+[INFO|callbacks.py:312] 2024-08-16 14:21:55,830 >> {'loss': 0.2232, 'learning_rate': 1.0945e-05, 'epoch': 2.34, 'throughput': 12376.47}
+
+[INFO|callbacks.py:312] 2024-08-16 14:22:38,180 >> {'loss': 0.2569, 'learning_rate': 1.0437e-05, 'epoch': 2.36, 'throughput': 12376.49}
+
+[INFO|callbacks.py:312] 2024-08-16 14:23:20,529 >> {'loss': 0.2140, 'learning_rate': 9.9394e-06, 'epoch': 2.37, 'throughput': 12376.52}
+
+[INFO|callbacks.py:312] 2024-08-16 14:24:02,885 >> {'loss': 0.2451, 'learning_rate': 9.4527e-06, 'epoch': 2.39, 'throughput': 12376.53}
+
+[INFO|callbacks.py:312] 2024-08-16 14:24:45,189 >> {'loss': 0.2288, 'learning_rate': 8.9770e-06, 'epoch': 2.41, 'throughput': 12376.63}
+
+[INFO|callbacks.py:312] 2024-08-16 14:25:27,580 >> {'loss': 0.2332, 'learning_rate': 8.5124e-06, 'epoch': 2.42, 'throughput': 12376.58}
+
+[INFO|callbacks.py:312] 2024-08-16 14:26:09,900 >> {'loss': 0.2020, 'learning_rate': 8.0590e-06, 'epoch': 2.44, 'throughput': 12376.66}
+
+[INFO|callbacks.py:312] 2024-08-16 14:26:52,220 >> {'loss': 0.2270, 'learning_rate': 7.6170e-06, 'epoch': 2.45, 'throughput': 12376.73}
+
+[INFO|callbacks.py:312] 2024-08-16 14:27:34,558 >> {'loss': 0.2429, 'learning_rate': 7.1864e-06, 'epoch': 2.47, 'throughput': 12376.77}
+
+[INFO|callbacks.py:312] 2024-08-16 14:28:16,947 >> {'loss': 0.2147, 'learning_rate': 6.7674e-06, 'epoch': 2.48, 'throughput': 12376.72}
+
+[INFO|callbacks.py:312] 2024-08-16 14:28:59,276 >> {'loss': 0.2423, 'learning_rate': 6.3601e-06, 'epoch': 2.50, 'throughput': 12376.78}
+
+[INFO|callbacks.py:312] 2024-08-16 14:29:41,633 >> {'loss': 0.2828, 'learning_rate': 5.9647e-06, 'epoch': 2.51, 'throughput': 12376.78}
+
+[INFO|callbacks.py:312] 2024-08-16 14:30:23,993 >> {'loss': 0.2461, 'learning_rate': 5.5811e-06, 'epoch': 2.53, 'throughput': 12376.78}
+
+[INFO|callbacks.py:312] 2024-08-16 14:31:06,397 >> {'loss': 0.2960, 'learning_rate': 5.2095e-06, 'epoch': 2.55, 'throughput': 12376.71}
+
+[INFO|callbacks.py:312] 2024-08-16 14:31:48,695 >> {'loss': 0.2061, 'learning_rate': 4.8501e-06, 'epoch': 2.56, 'throughput': 12376.82}
+
+[INFO|callbacks.py:312] 2024-08-16 14:32:31,012 >> {'loss': 0.2323, 'learning_rate': 4.5029e-06, 'epoch': 2.58, 'throughput': 12376.90}
+
+[INFO|callbacks.py:312] 2024-08-16 14:33:13,360 >> {'loss': 0.2156, 'learning_rate': 4.1680e-06, 'epoch': 2.59, 'throughput': 12376.92}
+
+[INFO|callbacks.py:312] 2024-08-16 14:33:55,692 >> {'loss': 0.2393, 'learning_rate': 3.8455e-06, 'epoch': 2.61, 'throughput': 12376.97}
+
+[INFO|callbacks.py:312] 2024-08-16 14:34:38,031 >> {'loss': 0.2165, 'learning_rate': 3.5354e-06, 'epoch': 2.62, 'throughput': 12377.00}
+
+[INFO|callbacks.py:312] 2024-08-16 14:35:20,371 >> {'loss': 0.2313, 'learning_rate': 3.2380e-06, 'epoch': 2.64, 'throughput': 12377.04}
+
+[INFO|callbacks.py:312] 2024-08-16 14:36:02,747 >> {'loss': 0.2336, 'learning_rate': 2.9532e-06, 'epoch': 2.65, 'throughput': 12377.01}
+
+[INFO|callbacks.py:312] 2024-08-16 14:36:45,116 >> {'loss': 0.2311, 'learning_rate': 2.6811e-06, 'epoch': 2.67, 'throughput': 12376.99}
+
+[INFO|callbacks.py:312] 2024-08-16 14:37:27,476 >> {'loss': 0.2130, 'learning_rate': 2.4218e-06, 'epoch': 2.68, 'throughput': 12376.99}
+
+[INFO|callbacks.py:312] 2024-08-16 14:38:09,820 >> {'loss': 0.2364, 'learning_rate': 2.1754e-06, 'epoch': 2.70, 'throughput': 12377.02}
+
+[INFO|callbacks.py:312] 2024-08-16 14:38:52,212 >> {'loss': 0.2147, 'learning_rate': 1.9420e-06, 'epoch': 2.72, 'throughput': 12376.97}
+
+[INFO|callbacks.py:312] 2024-08-16 14:39:34,551 >> {'loss': 0.2316, 'learning_rate': 1.7215e-06, 'epoch': 2.73, 'throughput': 12377.00}
+
+[INFO|callbacks.py:312] 2024-08-16 14:40:16,929 >> {'loss': 0.2263, 'learning_rate': 1.5141e-06, 'epoch': 2.75, 'throughput': 12376.97}
+
+[INFO|callbacks.py:312] 2024-08-16 14:40:59,276 >> {'loss': 0.2323, 'learning_rate': 1.3198e-06, 'epoch': 2.76, 'throughput': 12376.99}
+
+[INFO|callbacks.py:312] 2024-08-16 14:41:41,677 >> {'loss': 0.2246, 'learning_rate': 1.1387e-06, 'epoch': 2.78, 'throughput': 12376.92}
+
+[INFO|callbacks.py:312] 2024-08-16 14:42:24,023 >> {'loss': 0.2287, 'learning_rate': 9.7079e-07, 'epoch': 2.79, 'throughput': 12376.95}
+
+[INFO|callbacks.py:312] 2024-08-16 14:43:06,390 >> {'loss': 0.2081, 'learning_rate': 8.1616e-07, 'epoch': 2.81, 'throughput': 12376.94}
+
+[INFO|callbacks.py:312] 2024-08-16 14:43:48,708 >> {'loss': 0.2260, 'learning_rate': 6.7483e-07, 'epoch': 2.82, 'throughput': 12377.00}
+
+[INFO|callbacks.py:312] 2024-08-16 14:44:31,032 >> {'loss': 0.2730, 'learning_rate': 5.4685e-07, 'epoch': 2.84, 'throughput': 12377.06}
+
+[INFO|callbacks.py:312] 2024-08-16 14:45:13,357 >> {'loss': 0.2634, 'learning_rate': 4.3224e-07, 'epoch': 2.86, 'throughput': 12377.12}
+
+[INFO|callbacks.py:312] 2024-08-16 14:45:55,708 >> {'loss': 0.2592, 'learning_rate': 3.3105e-07, 'epoch': 2.87, 'throughput': 12377.13}
+
+[INFO|callbacks.py:312] 2024-08-16 14:46:38,100 >> {'loss': 0.2566, 'learning_rate': 2.4329e-07, 'epoch': 2.89, 'throughput': 12377.08}
+
+[INFO|callbacks.py:312] 2024-08-16 14:47:20,422 >> {'loss': 0.2575, 'learning_rate': 1.6899e-07, 'epoch': 2.90, 'throughput': 12377.14}
+
+[INFO|callbacks.py:312] 2024-08-16 14:48:02,805 >> {'loss': 0.2482, 'learning_rate': 1.0818e-07, 'epoch': 2.92, 'throughput': 12377.10}
+
+[INFO|callbacks.py:312] 2024-08-16 14:48:45,154 >> {'loss': 0.2483, 'learning_rate': 6.0859e-08, 'epoch': 2.93, 'throughput': 12377.12}
+
+[INFO|callbacks.py:312] 2024-08-16 14:49:27,463 >> {'loss': 0.2359, 'learning_rate': 2.7052e-08, 'epoch': 2.95, 'throughput': 12377.19}
+
+[INFO|callbacks.py:312] 2024-08-16 14:50:09,825 >> {'loss': 0.2434, 'learning_rate': 6.7634e-09, 'epoch': 2.96, 'throughput': 12377.19}
+
+[INFO|callbacks.py:312] 2024-08-16 14:50:52,222 >> {'loss': 0.2042, 'learning_rate': 0.0000e+00, 'epoch': 2.98, 'throughput': 12377.13}
+
+[INFO|trainer.py:3503] 2024-08-16 14:50:52,226 >> Saving model checkpoint to saves/Qwen2-7B-Chat/lora/train_08-16-2/checkpoint-384
+
+[INFO|configuration_utils.py:733] 2024-08-16 14:50:52,618 >> loading configuration file config.json from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json
+
+[INFO|configuration_utils.py:800] 2024-08-16 14:50:52,622 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|tokenization_utils_base.py:2702] 2024-08-16 14:50:52,748 >> tokenizer config file saved in saves/Qwen2-7B-Chat/lora/train_08-16-2/checkpoint-384/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2711] 2024-08-16 14:50:52,750 >> Special tokens file saved in saves/Qwen2-7B-Chat/lora/train_08-16-2/checkpoint-384/special_tokens_map.json
+
+[INFO|trainer.py:2394] 2024-08-16 14:50:53,095 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|trainer.py:3503] 2024-08-16 14:50:53,100 >> Saving model checkpoint to saves/Qwen2-7B-Chat/lora/train_08-16-2
+
+[INFO|configuration_utils.py:733] 2024-08-16 14:50:53,350 >> loading configuration file config.json from cache at /home/u16abc30f4f31eb21df44af89e63a742/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json
+
+[INFO|configuration_utils.py:800] 2024-08-16 14:50:53,352 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|tokenization_utils_base.py:2702] 2024-08-16 14:50:53,458 >> tokenizer config file saved in saves/Qwen2-7B-Chat/lora/train_08-16-2/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2711] 2024-08-16 14:50:53,460 >> Special tokens file saved in saves/Qwen2-7B-Chat/lora/train_08-16-2/special_tokens_map.json
+
+[WARNING|ploting.py:89] 2024-08-16 14:50:53,677 >> No metric eval_loss to plot.
+
+[INFO|trainer.py:3819] 2024-08-16 14:50:53,683 >> 
+***** Running Evaluation *****
+
+[INFO|trainer.py:3821] 2024-08-16 14:50:53,683 >>   Num examples = 1735
+
+[INFO|trainer.py:3824] 2024-08-16 14:50:53,683 >>   Batch size = 4
+
+[INFO|modelcard.py:449] 2024-08-16 14:51:38,535 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.979631425800194,
+    "num_input_tokens_seen": 100663296,
+    "total_flos": 4.2827022437921587e+18,
+    "train_loss": 0.3106601850595325,
+    "train_runtime": 8133.8849,
+    "train_samples_per_second": 12.157,
+    "train_steps_per_second": 0.047
+}

trainer_log.jsonl

@@ -0,0 +1,193 @@
+{"current_steps": 2, "total_steps": 384, "loss": 0.831, "learning_rate": 0.0001, "epoch": 0.015518913676042677, "percentage": 0.52, "elapsed_time": "0:00:43", "remaining_time": "2:18:17", "throughput": "12068.40", "total_tokens": 524288}
+{"current_steps": 4, "total_steps": 384, "loss": 0.7398, "learning_rate": 9.999323662872997e-05, "epoch": 0.031037827352085354, "percentage": 1.04, "elapsed_time": "0:01:25", "remaining_time": "2:15:43", "throughput": "12232.95", "total_tokens": 1048576}
+{"current_steps": 6, "total_steps": 384, "loss": 0.6438, "learning_rate": 9.99729483446475e-05, "epoch": 0.04655674102812803, "percentage": 1.56, "elapsed_time": "0:02:08", "remaining_time": "2:14:25", "throughput": "12285.60", "total_tokens": 1572864}
+{"current_steps": 8, "total_steps": 384, "loss": 0.6032, "learning_rate": 9.993914063644052e-05, "epoch": 0.06207565470417071, "percentage": 2.08, "elapsed_time": "0:02:50", "remaining_time": "2:13:28", "throughput": "12307.51", "total_tokens": 2097152}
+{"current_steps": 10, "total_steps": 384, "loss": 0.5433, "learning_rate": 9.989182265027232e-05, "epoch": 0.07759456838021339, "percentage": 2.6, "elapsed_time": "0:03:32", "remaining_time": "2:12:35", "throughput": "12323.95", "total_tokens": 2621440}
+{"current_steps": 12, "total_steps": 384, "loss": 0.5228, "learning_rate": 9.98310071873072e-05, "epoch": 0.09311348205625607, "percentage": 3.12, "elapsed_time": "0:04:15", "remaining_time": "2:11:47", "throughput": "12332.99", "total_tokens": 3145728}
+{"current_steps": 14, "total_steps": 384, "loss": 0.4702, "learning_rate": 9.97567107002474e-05, "epoch": 0.10863239573229874, "percentage": 3.65, "elapsed_time": "0:04:57", "remaining_time": "2:10:58", "throughput": "12341.83", "total_tokens": 3670016}
+{"current_steps": 16, "total_steps": 384, "loss": 0.4574, "learning_rate": 9.966895328888194e-05, "epoch": 0.12415130940834142, "percentage": 4.17, "elapsed_time": "0:05:39", "remaining_time": "2:10:13", "throughput": "12347.21", "total_tokens": 4194304}
+{"current_steps": 18, "total_steps": 384, "loss": 0.5093, "learning_rate": 9.956775869464901e-05, "epoch": 0.1396702230843841, "percentage": 4.69, "elapsed_time": "0:06:22", "remaining_time": "2:09:28", "throughput": "12350.26", "total_tokens": 4718592}
+{"current_steps": 20, "total_steps": 384, "loss": 0.4771, "learning_rate": 9.945315429421306e-05, "epoch": 0.15518913676042678, "percentage": 5.21, "elapsed_time": "0:07:04", "remaining_time": "2:08:44", "throughput": "12352.92", "total_tokens": 5242880}
+{"current_steps": 22, "total_steps": 384, "loss": 0.4343, "learning_rate": 9.932517109205849e-05, "epoch": 0.17070805043646944, "percentage": 5.73, "elapsed_time": "0:07:46", "remaining_time": "2:08:00", "throughput": "12355.21", "total_tokens": 5767168}
+{"current_steps": 24, "total_steps": 384, "loss": 0.4455, "learning_rate": 9.918384371210176e-05, "epoch": 0.18622696411251213, "percentage": 6.25, "elapsed_time": "0:08:29", "remaining_time": "2:07:17", "throughput": "12356.26", "total_tokens": 6291456}
+{"current_steps": 26, "total_steps": 384, "loss": 0.4669, "learning_rate": 9.902921038832455e-05, "epoch": 0.2017458777885548, "percentage": 6.77, "elapsed_time": "0:09:11", "remaining_time": "2:06:35", "throughput": "12356.01", "total_tokens": 6815744}
+{"current_steps": 28, "total_steps": 384, "loss": 0.4723, "learning_rate": 9.886131295443003e-05, "epoch": 0.21726479146459748, "percentage": 7.29, "elapsed_time": "0:09:53", "remaining_time": "2:05:51", "throughput": "12357.59", "total_tokens": 7340032}
+{"current_steps": 30, "total_steps": 384, "loss": 0.4364, "learning_rate": 9.868019683252543e-05, "epoch": 0.23278370514064015, "percentage": 7.81, "elapsed_time": "0:10:36", "remaining_time": "2:05:09", "throughput": "12358.33", "total_tokens": 7864320}
+{"current_steps": 32, "total_steps": 384, "loss": 0.4013, "learning_rate": 9.848591102083375e-05, "epoch": 0.24830261881668284, "percentage": 8.33, "elapsed_time": "0:11:18", "remaining_time": "2:04:25", "throughput": "12360.25", "total_tokens": 8388608}
+{"current_steps": 34, "total_steps": 384, "loss": 0.3875, "learning_rate": 9.82785080804381e-05, "epoch": 0.2638215324927255, "percentage": 8.85, "elapsed_time": "0:12:01", "remaining_time": "2:03:42", "throughput": "12360.97", "total_tokens": 8912896}
+{"current_steps": 36, "total_steps": 384, "loss": 0.4187, "learning_rate": 9.805804412106198e-05, "epoch": 0.2793404461687682, "percentage": 9.38, "elapsed_time": "0:12:43", "remaining_time": "2:02:59", "throughput": "12361.99", "total_tokens": 9437184}
+{"current_steps": 38, "total_steps": 384, "loss": 0.3981, "learning_rate": 9.782457878588977e-05, "epoch": 0.2948593598448109, "percentage": 9.9, "elapsed_time": "0:13:25", "remaining_time": "2:02:16", "throughput": "12363.00", "total_tokens": 9961472}
+{"current_steps": 40, "total_steps": 384, "loss": 0.4121, "learning_rate": 9.757817523543109e-05, "epoch": 0.31037827352085356, "percentage": 10.42, "elapsed_time": "0:14:08", "remaining_time": "2:01:34", "throughput": "12363.06", "total_tokens": 10485760}
+{"current_steps": 42, "total_steps": 384, "loss": 0.392, "learning_rate": 9.731890013043368e-05, "epoch": 0.3258971871968962, "percentage": 10.94, "elapsed_time": "0:14:50", "remaining_time": "2:00:51", "throughput": "12363.66", "total_tokens": 11010048}
+{"current_steps": 44, "total_steps": 384, "loss": 0.3845, "learning_rate": 9.704682361384941e-05, "epoch": 0.3414161008729389, "percentage": 11.46, "elapsed_time": "0:15:32", "remaining_time": "2:00:08", "throughput": "12365.26", "total_tokens": 11534336}
+{"current_steps": 46, "total_steps": 384, "loss": 0.397, "learning_rate": 9.676201929185809e-05, "epoch": 0.3569350145489816, "percentage": 11.98, "elapsed_time": "0:16:15", "remaining_time": "1:59:25", "throughput": "12365.45", "total_tokens": 12058624}
+{"current_steps": 48, "total_steps": 384, "loss": 0.3753, "learning_rate": 9.646456421395446e-05, "epoch": 0.37245392822502427, "percentage": 12.5, "elapsed_time": "0:16:57", "remaining_time": "1:58:42", "throughput": "12365.80", "total_tokens": 12582912}
+{"current_steps": 50, "total_steps": 384, "loss": 0.387, "learning_rate": 9.615453885210369e-05, "epoch": 0.3879728419010669, "percentage": 13.02, "elapsed_time": "0:17:39", "remaining_time": "1:58:00", "throughput": "12366.58", "total_tokens": 13107200}
+{"current_steps": 52, "total_steps": 384, "loss": 0.3724, "learning_rate": 9.583202707897074e-05, "epoch": 0.4034917555771096, "percentage": 13.54, "elapsed_time": "0:18:22", "remaining_time": "1:57:17", "throughput": "12367.11", "total_tokens": 13631488}
+{"current_steps": 54, "total_steps": 384, "loss": 0.4394, "learning_rate": 9.549711614523007e-05, "epoch": 0.4190106692531523, "percentage": 14.06, "elapsed_time": "0:19:04", "remaining_time": "1:56:34", "throughput": "12367.54", "total_tokens": 14155776}
+{"current_steps": 56, "total_steps": 384, "loss": 0.4177, "learning_rate": 9.514989665596114e-05, "epoch": 0.43452958292919497, "percentage": 14.58, "elapsed_time": "0:19:46", "remaining_time": "1:55:52", "throughput": "12368.03", "total_tokens": 14680064}
+{"current_steps": 58, "total_steps": 384, "loss": 0.3939, "learning_rate": 9.479046254613673e-05, "epoch": 0.45004849660523766, "percentage": 15.1, "elapsed_time": "0:20:29", "remaining_time": "1:55:09", "throughput": "12368.21", "total_tokens": 15204352}
+{"current_steps": 60, "total_steps": 384, "loss": 0.4207, "learning_rate": 9.441891105521006e-05, "epoch": 0.4655674102812803, "percentage": 15.62, "elapsed_time": "0:21:11", "remaining_time": "1:54:26", "throughput": "12368.89", "total_tokens": 15728640}
+{"current_steps": 62, "total_steps": 384, "loss": 0.3653, "learning_rate": 9.403534270080829e-05, "epoch": 0.481086323957323, "percentage": 16.15, "elapsed_time": "0:21:53", "remaining_time": "1:53:44", "throughput": "12369.17", "total_tokens": 16252928}
+{"current_steps": 64, "total_steps": 384, "loss": 0.3925, "learning_rate": 9.3639861251539e-05, "epoch": 0.49660523763336567, "percentage": 16.67, "elapsed_time": "0:22:36", "remaining_time": "1:53:01", "throughput": "12369.62", "total_tokens": 16777216}
+{"current_steps": 66, "total_steps": 384, "loss": 0.3982, "learning_rate": 9.323257369891703e-05, "epoch": 0.5121241513094084, "percentage": 17.19, "elapsed_time": "0:23:18", "remaining_time": "1:52:19", "throughput": "12369.99", "total_tokens": 17301504}
+{"current_steps": 68, "total_steps": 384, "loss": 0.3709, "learning_rate": 9.281359022841965e-05, "epoch": 0.527643064985451, "percentage": 17.71, "elapsed_time": "0:24:01", "remaining_time": "1:51:36", "throughput": "12370.31", "total_tokens": 17825792}
+{"current_steps": 70, "total_steps": 384, "loss": 0.3744, "learning_rate": 9.238302418967756e-05, "epoch": 0.5431619786614937, "percentage": 18.23, "elapsed_time": "0:24:43", "remaining_time": "1:50:54", "throughput": "12370.44", "total_tokens": 18350080}
+{"current_steps": 72, "total_steps": 384, "loss": 0.3929, "learning_rate": 9.194099206580982e-05, "epoch": 0.5586808923375364, "percentage": 18.75, "elapsed_time": "0:25:25", "remaining_time": "1:50:11", "throughput": "12370.64", "total_tokens": 18874368}
+{"current_steps": 74, "total_steps": 384, "loss": 0.3716, "learning_rate": 9.148761344191109e-05, "epoch": 0.574199806013579, "percentage": 19.27, "elapsed_time": "0:26:08", "remaining_time": "1:49:29", "throughput": "12370.73", "total_tokens": 19398656}
+{"current_steps": 76, "total_steps": 384, "loss": 0.3959, "learning_rate": 9.102301097269974e-05, "epoch": 0.5897187196896218, "percentage": 19.79, "elapsed_time": "0:26:50", "remaining_time": "1:48:46", "throughput": "12371.11", "total_tokens": 19922944}
+{"current_steps": 78, "total_steps": 384, "loss": 0.3514, "learning_rate": 9.054731034933549e-05, "epoch": 0.6052376333656644, "percentage": 20.31, "elapsed_time": "0:27:32", "remaining_time": "1:48:04", "throughput": "12371.15", "total_tokens": 20447232}
+{"current_steps": 80, "total_steps": 384, "loss": 0.3767, "learning_rate": 9.006064026541548e-05, "epoch": 0.6207565470417071, "percentage": 20.83, "elapsed_time": "0:28:15", "remaining_time": "1:47:21", "throughput": "12371.38", "total_tokens": 20971520}
+{"current_steps": 82, "total_steps": 384, "loss": 0.371, "learning_rate": 8.956313238215824e-05, "epoch": 0.6362754607177498, "percentage": 21.35, "elapsed_time": "0:28:57", "remaining_time": "1:46:39", "throughput": "12371.34", "total_tokens": 21495808}
+{"current_steps": 84, "total_steps": 384, "loss": 0.3529, "learning_rate": 8.905492129278478e-05, "epoch": 0.6517943743937924, "percentage": 21.88, "elapsed_time": "0:29:39", "remaining_time": "1:45:56", "throughput": "12371.72", "total_tokens": 22020096}
+{"current_steps": 86, "total_steps": 384, "loss": 0.3044, "learning_rate": 8.853614448610631e-05, "epoch": 0.6673132880698351, "percentage": 22.4, "elapsed_time": "0:30:22", "remaining_time": "1:45:14", "throughput": "12371.87", "total_tokens": 22544384}
+{"current_steps": 88, "total_steps": 384, "loss": 0.3532, "learning_rate": 8.800694230932884e-05, "epoch": 0.6828322017458778, "percentage": 22.92, "elapsed_time": "0:31:04", "remaining_time": "1:44:31", "throughput": "12372.26", "total_tokens": 23068672}
+{"current_steps": 90, "total_steps": 384, "loss": 0.3461, "learning_rate": 8.74674579300843e-05, "epoch": 0.6983511154219205, "percentage": 23.44, "elapsed_time": "0:31:46", "remaining_time": "1:43:49", "throughput": "12371.97", "total_tokens": 23592960}
+{"current_steps": 92, "total_steps": 384, "loss": 0.3513, "learning_rate": 8.691783729769874e-05, "epoch": 0.7138700290979632, "percentage": 23.96, "elapsed_time": "0:32:29", "remaining_time": "1:43:07", "throughput": "12371.69", "total_tokens": 24117248}
+{"current_steps": 94, "total_steps": 384, "loss": 0.3842, "learning_rate": 8.635822910370792e-05, "epoch": 0.7293889427740058, "percentage": 24.48, "elapsed_time": "0:33:11", "remaining_time": "1:42:24", "throughput": "12371.92", "total_tokens": 24641536}
+{"current_steps": 96, "total_steps": 384, "loss": 0.363, "learning_rate": 8.578878474163115e-05, "epoch": 0.7449078564500485, "percentage": 25.0, "elapsed_time": "0:33:54", "remaining_time": "1:41:42", "throughput": "12372.14", "total_tokens": 25165824}
+{"current_steps": 98, "total_steps": 384, "loss": 0.3079, "learning_rate": 8.520965826601394e-05, "epoch": 0.7604267701260912, "percentage": 25.52, "elapsed_time": "0:34:36", "remaining_time": "1:40:59", "throughput": "12372.67", "total_tokens": 25690112}
+{"current_steps": 100, "total_steps": 384, "loss": 0.3769, "learning_rate": 8.462100635075097e-05, "epoch": 0.7759456838021338, "percentage": 26.04, "elapsed_time": "0:35:18", "remaining_time": "1:40:17", "throughput": "12372.59", "total_tokens": 26214400}
+{"current_steps": 102, "total_steps": 384, "loss": 0.3907, "learning_rate": 8.40229882467003e-05, "epoch": 0.7914645974781765, "percentage": 26.56, "elapsed_time": "0:36:01", "remaining_time": "1:39:34", "throughput": "12372.64", "total_tokens": 26738688}
+{"current_steps": 104, "total_steps": 384, "loss": 0.3457, "learning_rate": 8.341576573860048e-05, "epoch": 0.8069835111542192, "percentage": 27.08, "elapsed_time": "0:36:43", "remaining_time": "1:38:52", "throughput": "12372.69", "total_tokens": 27262976}
+{"current_steps": 106, "total_steps": 384, "loss": 0.3889, "learning_rate": 8.279950310130217e-05, "epoch": 0.8225024248302619, "percentage": 27.6, "elapsed_time": "0:37:25", "remaining_time": "1:38:09", "throughput": "12373.02", "total_tokens": 27787264}
+{"current_steps": 108, "total_steps": 384, "loss": 0.3142, "learning_rate": 8.2174367055326e-05, "epoch": 0.8380213385063046, "percentage": 28.12, "elapsed_time": "0:38:08", "remaining_time": "1:37:27", "throughput": "12373.10", "total_tokens": 28311552}
+{"current_steps": 110, "total_steps": 384, "loss": 0.3299, "learning_rate": 8.154052672175887e-05, "epoch": 0.8535402521823472, "percentage": 28.65, "elapsed_time": "0:38:50", "remaining_time": "1:36:45", "throughput": "12373.25", "total_tokens": 28835840}
+{"current_steps": 112, "total_steps": 384, "loss": 0.3425, "learning_rate": 8.089815357650089e-05, "epoch": 0.8690591658583899, "percentage": 29.17, "elapsed_time": "0:39:32", "remaining_time": "1:36:02", "throughput": "12373.26", "total_tokens": 29360128}
+{"current_steps": 114, "total_steps": 384, "loss": 0.3363, "learning_rate": 8.024742140387506e-05, "epoch": 0.8845780795344326, "percentage": 29.69, "elapsed_time": "0:40:15", "remaining_time": "1:35:20", "throughput": "12373.27", "total_tokens": 29884416}
+{"current_steps": 116, "total_steps": 384, "loss": 0.3725, "learning_rate": 7.95885062496126e-05, "epoch": 0.9000969932104753, "percentage": 30.21, "elapsed_time": "0:40:57", "remaining_time": "1:34:37", "throughput": "12373.41", "total_tokens": 30408704}
+{"current_steps": 118, "total_steps": 384, "loss": 0.3397, "learning_rate": 7.892158637322646e-05, "epoch": 0.915615906886518, "percentage": 30.73, "elapsed_time": "0:41:39", "remaining_time": "1:33:55", "throughput": "12373.69", "total_tokens": 30932992}
+{"current_steps": 120, "total_steps": 384, "loss": 0.2812, "learning_rate": 7.824684219978591e-05, "epoch": 0.9311348205625606, "percentage": 31.25, "elapsed_time": "0:42:22", "remaining_time": "1:33:12", "throughput": "12373.85", "total_tokens": 31457280}
+{"current_steps": 122, "total_steps": 384, "loss": 0.3555, "learning_rate": 7.756445627110523e-05, "epoch": 0.9466537342386033, "percentage": 31.77, "elapsed_time": "0:43:04", "remaining_time": "1:32:30", "throughput": "12373.80", "total_tokens": 31981568}
+{"current_steps": 124, "total_steps": 384, "loss": 0.3362, "learning_rate": 7.687461319635981e-05, "epoch": 0.962172647914646, "percentage": 32.29, "elapsed_time": "0:43:46", "remaining_time": "1:31:48", "throughput": "12373.83", "total_tokens": 32505856}
+{"current_steps": 126, "total_steps": 384, "loss": 0.3133, "learning_rate": 7.6177499602143e-05, "epoch": 0.9776915615906887, "percentage": 32.81, "elapsed_time": "0:44:29", "remaining_time": "1:31:05", "throughput": "12374.00", "total_tokens": 33030144}
+{"current_steps": 128, "total_steps": 384, "loss": 0.3119, "learning_rate": 7.547330408197695e-05, "epoch": 0.9932104752667313, "percentage": 33.33, "elapsed_time": "0:45:11", "remaining_time": "1:30:23", "throughput": "12374.26", "total_tokens": 33554432}
+{"current_steps": 130, "total_steps": 384, "loss": 0.3117, "learning_rate": 7.476221714529167e-05, "epoch": 1.008729388942774, "percentage": 33.85, "elapsed_time": "0:45:54", "remaining_time": "1:29:40", "throughput": "12374.25", "total_tokens": 34078720}
+{"current_steps": 132, "total_steps": 384, "loss": 0.329, "learning_rate": 7.404443116588548e-05, "epoch": 1.0242483026188167, "percentage": 34.38, "elapsed_time": "0:46:36", "remaining_time": "1:28:58", "throughput": "12374.33", "total_tokens": 34603008}
+{"current_steps": 134, "total_steps": 384, "loss": 0.279, "learning_rate": 7.332014032988123e-05, "epoch": 1.0397672162948595, "percentage": 34.9, "elapsed_time": "0:47:18", "remaining_time": "1:28:16", "throughput": "12374.33", "total_tokens": 35127296}
+{"current_steps": 136, "total_steps": 384, "loss": 0.2682, "learning_rate": 7.258954058319216e-05, "epoch": 1.055286129970902, "percentage": 35.42, "elapsed_time": "0:48:01", "remaining_time": "1:27:33", "throughput": "12374.30", "total_tokens": 35651584}
+{"current_steps": 138, "total_steps": 384, "loss": 0.293, "learning_rate": 7.185282957851175e-05, "epoch": 1.0708050436469447, "percentage": 35.94, "elapsed_time": "0:48:43", "remaining_time": "1:26:51", "throughput": "12374.23", "total_tokens": 36175872}
+{"current_steps": 140, "total_steps": 384, "loss": 0.315, "learning_rate": 7.111020662184174e-05, "epoch": 1.0863239573229875, "percentage": 36.46, "elapsed_time": "0:49:25", "remaining_time": "1:26:08", "throughput": "12374.40", "total_tokens": 36700160}
+{"current_steps": 142, "total_steps": 384, "loss": 0.289, "learning_rate": 7.036187261857289e-05, "epoch": 1.10184287099903, "percentage": 36.98, "elapsed_time": "0:50:08", "remaining_time": "1:25:26", "throughput": "12374.16", "total_tokens": 37224448}
+{"current_steps": 144, "total_steps": 384, "loss": 0.2808, "learning_rate": 6.960803001913314e-05, "epoch": 1.1173617846750727, "percentage": 37.5, "elapsed_time": "0:50:50", "remaining_time": "1:24:44", "throughput": "12374.30", "total_tokens": 37748736}
+{"current_steps": 146, "total_steps": 384, "loss": 0.318, "learning_rate": 6.884888276421766e-05, "epoch": 1.1328806983511155, "percentage": 38.02, "elapsed_time": "0:51:32", "remaining_time": "1:24:01", "throughput": "12374.33", "total_tokens": 38273024}
+{"current_steps": 148, "total_steps": 384, "loss": 0.2685, "learning_rate": 6.808463622961578e-05, "epoch": 1.148399612027158, "percentage": 38.54, "elapsed_time": "0:52:15", "remaining_time": "1:23:19", "throughput": "12374.43", "total_tokens": 38797312}
+{"current_steps": 150, "total_steps": 384, "loss": 0.3121, "learning_rate": 6.731549717064974e-05, "epoch": 1.1639185257032008, "percentage": 39.06, "elapsed_time": "0:52:57", "remaining_time": "1:22:37", "throughput": "12374.58", "total_tokens": 39321600}
+{"current_steps": 152, "total_steps": 384, "loss": 0.2835, "learning_rate": 6.654167366624009e-05, "epoch": 1.1794374393792435, "percentage": 39.58, "elapsed_time": "0:53:39", "remaining_time": "1:21:54", "throughput": "12374.63", "total_tokens": 39845888}
+{"current_steps": 154, "total_steps": 384, "loss": 0.2905, "learning_rate": 6.576337506261314e-05, "epoch": 1.1949563530552862, "percentage": 40.1, "elapsed_time": "0:54:22", "remaining_time": "1:21:12", "throughput": "12375.02", "total_tokens": 40370176}
+{"current_steps": 156, "total_steps": 384, "loss": 0.3277, "learning_rate": 6.498081191666548e-05, "epoch": 1.2104752667313288, "percentage": 40.62, "elapsed_time": "0:55:04", "remaining_time": "1:20:29", "throughput": "12375.10", "total_tokens": 40894464}
+{"current_steps": 158, "total_steps": 384, "loss": 0.2788, "learning_rate": 6.419419593900108e-05, "epoch": 1.2259941804073715, "percentage": 41.15, "elapsed_time": "0:55:46", "remaining_time": "1:19:47", "throughput": "12375.10", "total_tokens": 41418752}
+{"current_steps": 160, "total_steps": 384, "loss": 0.2971, "learning_rate": 6.340373993665607e-05, "epoch": 1.2415130940834143, "percentage": 41.67, "elapsed_time": "0:56:29", "remaining_time": "1:19:05", "throughput": "12375.12", "total_tokens": 41943040}
+{"current_steps": 162, "total_steps": 384, "loss": 0.287, "learning_rate": 6.260965775552712e-05, "epoch": 1.2570320077594568, "percentage": 42.19, "elapsed_time": "0:57:11", "remaining_time": "1:18:22", "throughput": "12374.98", "total_tokens": 42467328}
+{"current_steps": 164, "total_steps": 384, "loss": 0.3196, "learning_rate": 6.181216422251862e-05, "epoch": 1.2725509214354995, "percentage": 42.71, "elapsed_time": "0:57:54", "remaining_time": "1:17:40", "throughput": "12375.00", "total_tokens": 42991616}
+{"current_steps": 166, "total_steps": 384, "loss": 0.3021, "learning_rate": 6.101147508742455e-05, "epoch": 1.2880698351115423, "percentage": 43.23, "elapsed_time": "0:58:36", "remaining_time": "1:16:57", "throughput": "12375.01", "total_tokens": 43515904}
+{"current_steps": 168, "total_steps": 384, "loss": 0.2329, "learning_rate": 6.0207806964560584e-05, "epoch": 1.3035887487875848, "percentage": 43.75, "elapsed_time": "0:59:18", "remaining_time": "1:16:15", "throughput": "12375.04", "total_tokens": 44040192}
+{"current_steps": 170, "total_steps": 384, "loss": 0.2803, "learning_rate": 5.940137727416246e-05, "epoch": 1.3191076624636275, "percentage": 44.27, "elapsed_time": "1:00:01", "remaining_time": "1:15:33", "throughput": "12375.12", "total_tokens": 44564480}
+{"current_steps": 172, "total_steps": 384, "loss": 0.2744, "learning_rate": 5.8592404183566144e-05, "epoch": 1.3346265761396703, "percentage": 44.79, "elapsed_time": "1:00:43", "remaining_time": "1:14:50", "throughput": "12375.21", "total_tokens": 45088768}
+{"current_steps": 174, "total_steps": 384, "loss": 0.3332, "learning_rate": 5.778110654818601e-05, "epoch": 1.3501454898157128, "percentage": 45.31, "elapsed_time": "1:01:25", "remaining_time": "1:14:08", "throughput": "12375.49", "total_tokens": 45613056}
+{"current_steps": 176, "total_steps": 384, "loss": 0.3223, "learning_rate": 5.6967703852306786e-05, "epoch": 1.3656644034917556, "percentage": 45.83, "elapsed_time": "1:02:08", "remaining_time": "1:13:25", "throughput": "12375.42", "total_tokens": 46137344}
+{"current_steps": 178, "total_steps": 384, "loss": 0.3127, "learning_rate": 5.6152416149705455e-05, "epoch": 1.3811833171677983, "percentage": 46.35, "elapsed_time": "1:02:50", "remaining_time": "1:12:43", "throughput": "12375.48", "total_tokens": 46661632}
+{"current_steps": 180, "total_steps": 384, "loss": 0.2908, "learning_rate": 5.5335464004118986e-05, "epoch": 1.3967022308438408, "percentage": 46.88, "elapsed_time": "1:03:32", "remaining_time": "1:12:01", "throughput": "12375.67", "total_tokens": 47185920}
+{"current_steps": 182, "total_steps": 384, "loss": 0.2918, "learning_rate": 5.4517068429574215e-05, "epoch": 1.4122211445198836, "percentage": 47.4, "elapsed_time": "1:04:15", "remaining_time": "1:11:18", "throughput": "12375.66", "total_tokens": 47710208}
+{"current_steps": 184, "total_steps": 384, "loss": 0.268, "learning_rate": 5.3697450830595774e-05, "epoch": 1.4277400581959263, "percentage": 47.92, "elapsed_time": "1:04:57", "remaining_time": "1:10:36", "throughput": "12375.75", "total_tokens": 48234496}
+{"current_steps": 186, "total_steps": 384, "loss": 0.2862, "learning_rate": 5.287683294230855e-05, "epoch": 1.4432589718719688, "percentage": 48.44, "elapsed_time": "1:05:39", "remaining_time": "1:09:54", "throughput": "12375.71", "total_tokens": 48758784}
+{"current_steps": 188, "total_steps": 384, "loss": 0.3054, "learning_rate": 5.205543677045049e-05, "epoch": 1.4587778855480116, "percentage": 48.96, "elapsed_time": "1:06:22", "remaining_time": "1:09:11", "throughput": "12375.67", "total_tokens": 49283072}
+{"current_steps": 190, "total_steps": 384, "loss": 0.2814, "learning_rate": 5.1233484531312414e-05, "epoch": 1.4742967992240543, "percentage": 49.48, "elapsed_time": "1:07:04", "remaining_time": "1:08:29", "throughput": "12375.72", "total_tokens": 49807360}
+{"current_steps": 192, "total_steps": 384, "loss": 0.2703, "learning_rate": 5.0411198591620676e-05, "epoch": 1.489815712900097, "percentage": 50.0, "elapsed_time": "1:07:46", "remaining_time": "1:07:46", "throughput": "12375.63", "total_tokens": 50331648}
+{"current_steps": 194, "total_steps": 384, "loss": 0.2689, "learning_rate": 4.958880140837933e-05, "epoch": 1.5053346265761398, "percentage": 50.52, "elapsed_time": "1:08:29", "remaining_time": "1:07:04", "throughput": "12375.75", "total_tokens": 50855936}
+{"current_steps": 196, "total_steps": 384, "loss": 0.3013, "learning_rate": 4.876651546868759e-05, "epoch": 1.5208535402521823, "percentage": 51.04, "elapsed_time": "1:09:11", "remaining_time": "1:06:22", "throughput": "12375.76", "total_tokens": 51380224}
+{"current_steps": 198, "total_steps": 384, "loss": 0.2751, "learning_rate": 4.794456322954952e-05, "epoch": 1.536372453928225, "percentage": 51.56, "elapsed_time": "1:09:54", "remaining_time": "1:05:39", "throughput": "12375.72", "total_tokens": 51904512}
+{"current_steps": 200, "total_steps": 384, "loss": 0.3178, "learning_rate": 4.712316705769145e-05, "epoch": 1.5518913676042678, "percentage": 52.08, "elapsed_time": "1:10:36", "remaining_time": "1:04:57", "throughput": "12375.77", "total_tokens": 52428800}
+{"current_steps": 202, "total_steps": 384, "loss": 0.2742, "learning_rate": 4.630254916940424e-05, "epoch": 1.5674102812803103, "percentage": 52.6, "elapsed_time": "1:11:18", "remaining_time": "1:04:15", "throughput": "12375.80", "total_tokens": 52953088}
+{"current_steps": 204, "total_steps": 384, "loss": 0.2751, "learning_rate": 4.548293157042581e-05, "epoch": 1.582929194956353, "percentage": 53.12, "elapsed_time": "1:12:01", "remaining_time": "1:03:32", "throughput": "12375.84", "total_tokens": 53477376}
+{"current_steps": 206, "total_steps": 384, "loss": 0.3256, "learning_rate": 4.466453599588103e-05, "epoch": 1.5984481086323958, "percentage": 53.65, "elapsed_time": "1:12:43", "remaining_time": "1:02:50", "throughput": "12375.76", "total_tokens": 54001664}
+{"current_steps": 208, "total_steps": 384, "loss": 0.2603, "learning_rate": 4.384758385029457e-05, "epoch": 1.6139670223084384, "percentage": 54.17, "elapsed_time": "1:13:25", "remaining_time": "1:02:08", "throughput": "12375.86", "total_tokens": 54525952}
+{"current_steps": 210, "total_steps": 384, "loss": 0.2598, "learning_rate": 4.3032296147693225e-05, "epoch": 1.629485935984481, "percentage": 54.69, "elapsed_time": "1:14:08", "remaining_time": "1:01:25", "throughput": "12375.97", "total_tokens": 55050240}
+{"current_steps": 212, "total_steps": 384, "loss": 0.2811, "learning_rate": 4.2218893451814005e-05, "epoch": 1.6450048496605238, "percentage": 55.21, "elapsed_time": "1:14:50", "remaining_time": "1:00:43", "throughput": "12376.02", "total_tokens": 55574528}
+{"current_steps": 214, "total_steps": 384, "loss": 0.2386, "learning_rate": 4.140759581643386e-05, "epoch": 1.6605237633365664, "percentage": 55.73, "elapsed_time": "1:15:32", "remaining_time": "1:00:00", "throughput": "12375.99", "total_tokens": 56098816}
+{"current_steps": 216, "total_steps": 384, "loss": 0.2999, "learning_rate": 4.059862272583755e-05, "epoch": 1.6760426770126091, "percentage": 56.25, "elapsed_time": "1:16:15", "remaining_time": "0:59:18", "throughput": "12375.93", "total_tokens": 56623104}
+{"current_steps": 218, "total_steps": 384, "loss": 0.2857, "learning_rate": 3.979219303543942e-05, "epoch": 1.6915615906886519, "percentage": 56.77, "elapsed_time": "1:16:57", "remaining_time": "0:58:36", "throughput": "12375.82", "total_tokens": 57147392}
+{"current_steps": 220, "total_steps": 384, "loss": 0.2533, "learning_rate": 3.898852491257546e-05, "epoch": 1.7070805043646944, "percentage": 57.29, "elapsed_time": "1:17:40", "remaining_time": "0:57:53", "throughput": "12375.79", "total_tokens": 57671680}
+{"current_steps": 222, "total_steps": 384, "loss": 0.306, "learning_rate": 3.818783577748138e-05, "epoch": 1.7225994180407371, "percentage": 57.81, "elapsed_time": "1:18:22", "remaining_time": "0:57:11", "throughput": "12375.96", "total_tokens": 58195968}
+{"current_steps": 224, "total_steps": 384, "loss": 0.2594, "learning_rate": 3.739034224447289e-05, "epoch": 1.7381183317167799, "percentage": 58.33, "elapsed_time": "1:19:04", "remaining_time": "0:56:29", "throughput": "12376.04", "total_tokens": 58720256}
+{"current_steps": 226, "total_steps": 384, "loss": 0.284, "learning_rate": 3.659626006334395e-05, "epoch": 1.7536372453928224, "percentage": 58.85, "elapsed_time": "1:19:47", "remaining_time": "0:55:46", "throughput": "12376.05", "total_tokens": 59244544}
+{"current_steps": 228, "total_steps": 384, "loss": 0.33, "learning_rate": 3.580580406099893e-05, "epoch": 1.7691561590688651, "percentage": 59.38, "elapsed_time": "1:20:29", "remaining_time": "0:55:04", "throughput": "12376.03", "total_tokens": 59768832}
+{"current_steps": 230, "total_steps": 384, "loss": 0.2968, "learning_rate": 3.501918808333453e-05, "epoch": 1.7846750727449079, "percentage": 59.9, "elapsed_time": "1:21:11", "remaining_time": "0:54:21", "throughput": "12375.98", "total_tokens": 60293120}
+{"current_steps": 232, "total_steps": 384, "loss": 0.2836, "learning_rate": 3.4236624937386876e-05, "epoch": 1.8001939864209504, "percentage": 60.42, "elapsed_time": "1:21:54", "remaining_time": "0:53:39", "throughput": "12376.10", "total_tokens": 60817408}
+{"current_steps": 234, "total_steps": 384, "loss": 0.2452, "learning_rate": 3.3458326333759925e-05, "epoch": 1.8157129000969934, "percentage": 60.94, "elapsed_time": "1:22:36", "remaining_time": "0:52:57", "throughput": "12376.14", "total_tokens": 61341696}
+{"current_steps": 236, "total_steps": 384, "loss": 0.2526, "learning_rate": 3.268450282935026e-05, "epoch": 1.831231813773036, "percentage": 61.46, "elapsed_time": "1:23:18", "remaining_time": "0:52:14", "throughput": "12376.09", "total_tokens": 61865984}
+{"current_steps": 238, "total_steps": 384, "loss": 0.2578, "learning_rate": 3.191536377038422e-05, "epoch": 1.8467507274490784, "percentage": 61.98, "elapsed_time": "1:24:01", "remaining_time": "0:51:32", "throughput": "12376.15", "total_tokens": 62390272}
+{"current_steps": 240, "total_steps": 384, "loss": 0.2895, "learning_rate": 3.115111723578235e-05, "epoch": 1.8622696411251214, "percentage": 62.5, "elapsed_time": "1:24:43", "remaining_time": "0:50:50", "throughput": "12376.22", "total_tokens": 62914560}
+{"current_steps": 242, "total_steps": 384, "loss": 0.3047, "learning_rate": 3.0391969980866875e-05, "epoch": 1.877788554801164, "percentage": 63.02, "elapsed_time": "1:25:25", "remaining_time": "0:50:07", "throughput": "12376.20", "total_tokens": 63438848}
+{"current_steps": 244, "total_steps": 384, "loss": 0.2958, "learning_rate": 2.963812738142713e-05, "epoch": 1.8933074684772064, "percentage": 63.54, "elapsed_time": "1:26:08", "remaining_time": "0:49:25", "throughput": "12376.13", "total_tokens": 63963136}
+{"current_steps": 246, "total_steps": 384, "loss": 0.2598, "learning_rate": 2.888979337815828e-05, "epoch": 1.9088263821532494, "percentage": 64.06, "elapsed_time": "1:26:50", "remaining_time": "0:48:43", "throughput": "12376.10", "total_tokens": 64487424}
+{"current_steps": 248, "total_steps": 384, "loss": 0.2699, "learning_rate": 2.8147170421488272e-05, "epoch": 1.924345295829292, "percentage": 64.58, "elapsed_time": "1:27:33", "remaining_time": "0:48:00", "throughput": "12376.09", "total_tokens": 65011712}
+{"current_steps": 250, "total_steps": 384, "loss": 0.2827, "learning_rate": 2.7410459416807853e-05, "epoch": 1.9398642095053347, "percentage": 65.1, "elapsed_time": "1:28:15", "remaining_time": "0:47:18", "throughput": "12376.20", "total_tokens": 65536000}
+{"current_steps": 252, "total_steps": 384, "loss": 0.3119, "learning_rate": 2.6679859670118783e-05, "epoch": 1.9553831231813774, "percentage": 65.62, "elapsed_time": "1:28:57", "remaining_time": "0:46:35", "throughput": "12376.24", "total_tokens": 66060288}
+{"current_steps": 254, "total_steps": 384, "loss": 0.2837, "learning_rate": 2.5955568834114524e-05, "epoch": 1.97090203685742, "percentage": 66.15, "elapsed_time": "1:29:40", "remaining_time": "0:45:53", "throughput": "12376.19", "total_tokens": 66584576}
+{"current_steps": 256, "total_steps": 384, "loss": 0.2511, "learning_rate": 2.5237782854708348e-05, "epoch": 1.9864209505334627, "percentage": 66.67, "elapsed_time": "1:30:22", "remaining_time": "0:45:11", "throughput": "12376.12", "total_tokens": 67108864}
+{"current_steps": 258, "total_steps": 384, "loss": 0.2501, "learning_rate": 2.452669591802307e-05, "epoch": 2.0019398642095054, "percentage": 67.19, "elapsed_time": "1:31:04", "remaining_time": "0:44:28", "throughput": "12376.06", "total_tokens": 67633152}
+{"current_steps": 260, "total_steps": 384, "loss": 0.2296, "learning_rate": 2.3822500397857018e-05, "epoch": 2.017458777885548, "percentage": 67.71, "elapsed_time": "1:31:47", "remaining_time": "0:43:46", "throughput": "12376.11", "total_tokens": 68157440}
+{"current_steps": 262, "total_steps": 384, "loss": 0.2333, "learning_rate": 2.3125386803640187e-05, "epoch": 2.0329776915615905, "percentage": 68.23, "elapsed_time": "1:32:29", "remaining_time": "0:43:04", "throughput": "12376.14", "total_tokens": 68681728}
+{"current_steps": 264, "total_steps": 384, "loss": 0.2119, "learning_rate": 2.2435543728894792e-05, "epoch": 2.0484966052376334, "percentage": 68.75, "elapsed_time": "1:33:11", "remaining_time": "0:42:21", "throughput": "12376.08", "total_tokens": 69206016}
+{"current_steps": 266, "total_steps": 384, "loss": 0.2676, "learning_rate": 2.175315780021411e-05, "epoch": 2.064015518913676, "percentage": 69.27, "elapsed_time": "1:33:54", "remaining_time": "0:41:39", "throughput": "12376.02", "total_tokens": 69730304}
+{"current_steps": 268, "total_steps": 384, "loss": 0.2285, "learning_rate": 2.1078413626773546e-05, "epoch": 2.079534432589719, "percentage": 69.79, "elapsed_time": "1:34:36", "remaining_time": "0:40:57", "throughput": "12376.08", "total_tokens": 70254592}
+{"current_steps": 270, "total_steps": 384, "loss": 0.2281, "learning_rate": 2.0411493750387423e-05, "epoch": 2.0950533462657615, "percentage": 70.31, "elapsed_time": "1:35:18", "remaining_time": "0:40:14", "throughput": "12376.12", "total_tokens": 70778880}
+{"current_steps": 272, "total_steps": 384, "loss": 0.2701, "learning_rate": 1.9752578596124954e-05, "epoch": 2.110572259941804, "percentage": 70.83, "elapsed_time": "1:36:01", "remaining_time": "0:39:32", "throughput": "12376.07", "total_tokens": 71303168}
+{"current_steps": 274, "total_steps": 384, "loss": 0.2033, "learning_rate": 1.9101846423499116e-05, "epoch": 2.126091173617847, "percentage": 71.35, "elapsed_time": "1:36:43", "remaining_time": "0:38:49", "throughput": "12375.95", "total_tokens": 71827456}
+{"current_steps": 276, "total_steps": 384, "loss": 0.2489, "learning_rate": 1.8459473278241126e-05, "epoch": 2.1416100872938895, "percentage": 71.88, "elapsed_time": "1:37:26", "remaining_time": "0:38:07", "throughput": "12375.99", "total_tokens": 72351744}
+{"current_steps": 278, "total_steps": 384, "loss": 0.2294, "learning_rate": 1.7825632944674015e-05, "epoch": 2.157129000969932, "percentage": 72.4, "elapsed_time": "1:38:08", "remaining_time": "0:37:25", "throughput": "12375.97", "total_tokens": 72876032}
+{"current_steps": 280, "total_steps": 384, "loss": 0.2452, "learning_rate": 1.7200496898697832e-05, "epoch": 2.172647914645975, "percentage": 72.92, "elapsed_time": "1:38:50", "remaining_time": "0:36:42", "throughput": "12375.92", "total_tokens": 73400320}
+{"current_steps": 282, "total_steps": 384, "loss": 0.242, "learning_rate": 1.6584234261399534e-05, "epoch": 2.1881668283220175, "percentage": 73.44, "elapsed_time": "1:39:33", "remaining_time": "0:36:00", "throughput": "12375.92", "total_tokens": 73924608}
+{"current_steps": 284, "total_steps": 384, "loss": 0.2894, "learning_rate": 1.5977011753299725e-05, "epoch": 2.20368574199806, "percentage": 73.96, "elapsed_time": "1:40:15", "remaining_time": "0:35:18", "throughput": "12376.01", "total_tokens": 74448896}
+{"current_steps": 286, "total_steps": 384, "loss": 0.231, "learning_rate": 1.537899364924905e-05, "epoch": 2.219204655674103, "percentage": 74.48, "elapsed_time": "1:40:57", "remaining_time": "0:34:35", "throughput": "12376.10", "total_tokens": 74973184}
+{"current_steps": 288, "total_steps": 384, "loss": 0.2412, "learning_rate": 1.4790341733986085e-05, "epoch": 2.2347235693501455, "percentage": 75.0, "elapsed_time": "1:41:40", "remaining_time": "0:33:53", "throughput": "12376.22", "total_tokens": 75497472}
+{"current_steps": 290, "total_steps": 384, "loss": 0.2464, "learning_rate": 1.4211215258368866e-05, "epoch": 2.250242483026188, "percentage": 75.52, "elapsed_time": "1:42:22", "remaining_time": "0:33:11", "throughput": "12376.23", "total_tokens": 76021760}
+{"current_steps": 292, "total_steps": 384, "loss": 0.2231, "learning_rate": 1.3641770896292084e-05, "epoch": 2.265761396702231, "percentage": 76.04, "elapsed_time": "1:43:04", "remaining_time": "0:32:28", "throughput": "12376.27", "total_tokens": 76546048}
+{"current_steps": 294, "total_steps": 384, "loss": 0.2432, "learning_rate": 1.3082162702301276e-05, "epoch": 2.2812803103782735, "percentage": 76.56, "elapsed_time": "1:43:47", "remaining_time": "0:31:46", "throughput": "12376.31", "total_tokens": 77070336}
+{"current_steps": 296, "total_steps": 384, "loss": 0.2147, "learning_rate": 1.253254206991572e-05, "epoch": 2.296799224054316, "percentage": 77.08, "elapsed_time": "1:44:29", "remaining_time": "0:31:03", "throughput": "12376.31", "total_tokens": 77594624}
+{"current_steps": 298, "total_steps": 384, "loss": 0.249, "learning_rate": 1.1993057690671173e-05, "epoch": 2.312318137730359, "percentage": 77.6, "elapsed_time": "1:45:11", "remaining_time": "0:30:21", "throughput": "12376.43", "total_tokens": 78118912}
+{"current_steps": 300, "total_steps": 384, "loss": 0.2362, "learning_rate": 1.1463855513893695e-05, "epoch": 2.3278370514064015, "percentage": 78.12, "elapsed_time": "1:45:54", "remaining_time": "0:29:39", "throughput": "12376.44", "total_tokens": 78643200}
+{"current_steps": 302, "total_steps": 384, "loss": 0.2232, "learning_rate": 1.0945078707215222e-05, "epoch": 2.343355965082444, "percentage": 78.65, "elapsed_time": "1:46:36", "remaining_time": "0:28:56", "throughput": "12376.47", "total_tokens": 79167488}
+{"current_steps": 304, "total_steps": 384, "loss": 0.2569, "learning_rate": 1.0436867617841768e-05, "epoch": 2.358874878758487, "percentage": 79.17, "elapsed_time": "1:47:18", "remaining_time": "0:28:14", "throughput": "12376.49", "total_tokens": 79691776}
+{"current_steps": 306, "total_steps": 384, "loss": 0.214, "learning_rate": 9.939359734584553e-06, "epoch": 2.3743937924345295, "percentage": 79.69, "elapsed_time": "1:48:01", "remaining_time": "0:27:32", "throughput": "12376.52", "total_tokens": 80216064}
+{"current_steps": 308, "total_steps": 384, "loss": 0.2451, "learning_rate": 9.452689650664515e-06, "epoch": 2.3899127061105725, "percentage": 80.21, "elapsed_time": "1:48:43", "remaining_time": "0:26:49", "throughput": "12376.53", "total_tokens": 80740352}
+{"current_steps": 310, "total_steps": 384, "loss": 0.2288, "learning_rate": 8.976989027300264e-06, "epoch": 2.405431619786615, "percentage": 80.73, "elapsed_time": "1:49:25", "remaining_time": "0:26:07", "throughput": "12376.63", "total_tokens": 81264640}
+{"current_steps": 312, "total_steps": 384, "loss": 0.2332, "learning_rate": 8.51238655808892e-06, "epoch": 2.4209505334626575, "percentage": 81.25, "elapsed_time": "1:50:08", "remaining_time": "0:25:25", "throughput": "12376.58", "total_tokens": 81788928}
+{"current_steps": 314, "total_steps": 384, "loss": 0.202, "learning_rate": 8.059007934190194e-06, "epoch": 2.4364694471387, "percentage": 81.77, "elapsed_time": "1:50:50", "remaining_time": "0:24:42", "throughput": "12376.66", "total_tokens": 82313216}
+{"current_steps": 316, "total_steps": 384, "loss": 0.227, "learning_rate": 7.61697581032243e-06, "epoch": 2.451988360814743, "percentage": 82.29, "elapsed_time": "1:51:33", "remaining_time": "0:24:00", "throughput": "12376.73", "total_tokens": 82837504}
+{"current_steps": 318, "total_steps": 384, "loss": 0.2429, "learning_rate": 7.186409771580354e-06, "epoch": 2.4675072744907856, "percentage": 82.81, "elapsed_time": "1:52:15", "remaining_time": "0:23:17", "throughput": "12376.77", "total_tokens": 83361792}
+{"current_steps": 320, "total_steps": 384, "loss": 0.2147, "learning_rate": 6.76742630108298e-06, "epoch": 2.4830261881668285, "percentage": 83.33, "elapsed_time": "1:52:57", "remaining_time": "0:22:35", "throughput": "12376.72", "total_tokens": 83886080}
+{"current_steps": 322, "total_steps": 384, "loss": 0.2423, "learning_rate": 6.3601387484610145e-06, "epoch": 2.498545101842871, "percentage": 83.85, "elapsed_time": "1:53:40", "remaining_time": "0:21:53", "throughput": "12376.78", "total_tokens": 84410368}
+{"current_steps": 324, "total_steps": 384, "loss": 0.2828, "learning_rate": 5.9646572991917116e-06, "epoch": 2.5140640155189136, "percentage": 84.38, "elapsed_time": "1:54:22", "remaining_time": "0:21:10", "throughput": "12376.78", "total_tokens": 84934656}
+{"current_steps": 326, "total_steps": 384, "loss": 0.2461, "learning_rate": 5.581088944789953e-06, "epoch": 2.529582929194956, "percentage": 84.9, "elapsed_time": "1:55:04", "remaining_time": "0:20:28", "throughput": "12376.78", "total_tokens": 85458944}
+{"current_steps": 328, "total_steps": 384, "loss": 0.296, "learning_rate": 5.209537453863289e-06, "epoch": 2.545101842870999, "percentage": 85.42, "elapsed_time": "1:55:47", "remaining_time": "0:19:46", "throughput": "12376.71", "total_tokens": 85983232}
+{"current_steps": 330, "total_steps": 384, "loss": 0.2061, "learning_rate": 4.850103344038853e-06, "epoch": 2.5606207565470416, "percentage": 85.94, "elapsed_time": "1:56:29", "remaining_time": "0:19:03", "throughput": "12376.82", "total_tokens": 86507520}
+{"current_steps": 332, "total_steps": 384, "loss": 0.2323, "learning_rate": 4.502883854769935e-06, "epoch": 2.5761396702230845, "percentage": 86.46, "elapsed_time": "1:57:11", "remaining_time": "0:18:21", "throughput": "12376.90", "total_tokens": 87031808}
+{"current_steps": 334, "total_steps": 384, "loss": 0.2156, "learning_rate": 4.167972921029262e-06, "epoch": 2.591658583899127, "percentage": 86.98, "elapsed_time": "1:57:54", "remaining_time": "0:17:39", "throughput": "12376.92", "total_tokens": 87556096}
+{"current_steps": 336, "total_steps": 384, "loss": 0.2393, "learning_rate": 3.845461147896323e-06, "epoch": 2.6071774975751696, "percentage": 87.5, "elapsed_time": "1:58:36", "remaining_time": "0:16:56", "throughput": "12376.97", "total_tokens": 88080384}
+{"current_steps": 338, "total_steps": 384, "loss": 0.2165, "learning_rate": 3.535435786045538e-06, "epoch": 2.6226964112512126, "percentage": 88.02, "elapsed_time": "1:59:18", "remaining_time": "0:16:14", "throughput": "12377.00", "total_tokens": 88604672}
+{"current_steps": 340, "total_steps": 384, "loss": 0.2313, "learning_rate": 3.2379807081419187e-06, "epoch": 2.638215324927255, "percentage": 88.54, "elapsed_time": "2:00:01", "remaining_time": "0:15:31", "throughput": "12377.04", "total_tokens": 89128960}
+{"current_steps": 342, "total_steps": 384, "loss": 0.2336, "learning_rate": 2.9531763861505966e-06, "epoch": 2.653734238603298, "percentage": 89.06, "elapsed_time": "2:00:43", "remaining_time": "0:14:49", "throughput": "12377.01", "total_tokens": 89653248}
+{"current_steps": 344, "total_steps": 384, "loss": 0.2311, "learning_rate": 2.6810998695663282e-06, "epoch": 2.6692531522793406, "percentage": 89.58, "elapsed_time": "2:01:25", "remaining_time": "0:14:07", "throughput": "12376.99", "total_tokens": 90177536}
+{"current_steps": 346, "total_steps": 384, "loss": 0.213, "learning_rate": 2.4218247645689307e-06, "epoch": 2.684772065955383, "percentage": 90.1, "elapsed_time": "2:02:08", "remaining_time": "0:13:24", "throughput": "12376.99", "total_tokens": 90701824}
+{"current_steps": 348, "total_steps": 384, "loss": 0.2364, "learning_rate": 2.1754212141102346e-06, "epoch": 2.7002909796314256, "percentage": 90.62, "elapsed_time": "2:02:50", "remaining_time": "0:12:42", "throughput": "12377.02", "total_tokens": 91226112}
+{"current_steps": 350, "total_steps": 384, "loss": 0.2147, "learning_rate": 1.941955878938029e-06, "epoch": 2.7158098933074686, "percentage": 91.15, "elapsed_time": "2:03:32", "remaining_time": "0:12:00", "throughput": "12376.97", "total_tokens": 91750400}
+{"current_steps": 352, "total_steps": 384, "loss": 0.2316, "learning_rate": 1.7214919195619127e-06, "epoch": 2.731328806983511, "percentage": 91.67, "elapsed_time": "2:04:15", "remaining_time": "0:11:17", "throughput": "12377.00", "total_tokens": 92274688}
+{"current_steps": 354, "total_steps": 384, "loss": 0.2263, "learning_rate": 1.514088979166256e-06, "epoch": 2.746847720659554, "percentage": 92.19, "elapsed_time": "2:04:57", "remaining_time": "0:10:35", "throughput": "12376.97", "total_tokens": 92798976}
+{"current_steps": 356, "total_steps": 384, "loss": 0.2323, "learning_rate": 1.3198031674745813e-06, "epoch": 2.7623666343355966, "percentage": 92.71, "elapsed_time": "2:05:40", "remaining_time": "0:09:53", "throughput": "12376.99", "total_tokens": 93323264}
+{"current_steps": 358, "total_steps": 384, "loss": 0.2246, "learning_rate": 1.138687045569975e-06, "epoch": 2.777885548011639, "percentage": 93.23, "elapsed_time": "2:06:22", "remaining_time": "0:09:10", "throughput": "12376.92", "total_tokens": 93847552}
+{"current_steps": 360, "total_steps": 384, "loss": 0.2287, "learning_rate": 9.707896116754488e-07, "epoch": 2.7934044616876816, "percentage": 93.75, "elapsed_time": "2:07:04", "remaining_time": "0:08:28", "throughput": "12376.95", "total_tokens": 94371840}
+{"current_steps": 362, "total_steps": 384, "loss": 0.2081, "learning_rate": 8.161562878982398e-07, "epoch": 2.8089233753637246, "percentage": 94.27, "elapsed_time": "2:07:47", "remaining_time": "0:07:45", "throughput": "12376.94", "total_tokens": 94896128}
+{"current_steps": 364, "total_steps": 384, "loss": 0.226, "learning_rate": 6.74828907941516e-07, "epoch": 2.824442289039767, "percentage": 94.79, "elapsed_time": "2:08:29", "remaining_time": "0:07:03", "throughput": "12377.00", "total_tokens": 95420416}
+{"current_steps": 366, "total_steps": 384, "loss": 0.273, "learning_rate": 5.468457057869358e-07, "epoch": 2.83996120271581, "percentage": 95.31, "elapsed_time": "2:09:11", "remaining_time": "0:06:21", "throughput": "12377.06", "total_tokens": 95944704}
+{"current_steps": 368, "total_steps": 384, "loss": 0.2634, "learning_rate": 4.322413053509944e-07, "epoch": 2.8554801163918526, "percentage": 95.83, "elapsed_time": "2:09:54", "remaining_time": "0:05:38", "throughput": "12377.12", "total_tokens": 96468992}
+{"current_steps": 370, "total_steps": 384, "loss": 0.2592, "learning_rate": 3.3104671111806593e-07, "epoch": 2.870999030067895, "percentage": 96.35, "elapsed_time": "2:10:36", "remaining_time": "0:04:56", "throughput": "12377.13", "total_tokens": 96993280}
+{"current_steps": 372, "total_steps": 384, "loss": 0.2566, "learning_rate": 2.432892997526026e-07, "epoch": 2.8865179437439377, "percentage": 96.88, "elapsed_time": "2:11:18", "remaining_time": "0:04:14", "throughput": "12377.08", "total_tokens": 97517568}
+{"current_steps": 374, "total_steps": 384, "loss": 0.2575, "learning_rate": 1.6899281269279755e-07, "epoch": 2.9020368574199806, "percentage": 97.4, "elapsed_time": "2:12:01", "remaining_time": "0:03:31", "throughput": "12377.14", "total_tokens": 98041856}
+{"current_steps": 376, "total_steps": 384, "loss": 0.2482, "learning_rate": 1.0817734972768944e-07, "epoch": 2.917555771096023, "percentage": 97.92, "elapsed_time": "2:12:43", "remaining_time": "0:02:49", "throughput": "12377.10", "total_tokens": 98566144}
+{"current_steps": 378, "total_steps": 384, "loss": 0.2483, "learning_rate": 6.085936355947897e-08, "epoch": 2.933074684772066, "percentage": 98.44, "elapsed_time": "2:13:25", "remaining_time": "0:02:07", "throughput": "12377.12", "total_tokens": 99090432}
+{"current_steps": 380, "total_steps": 384, "loss": 0.2359, "learning_rate": 2.7051655352494652e-08, "epoch": 2.9485935984481086, "percentage": 98.96, "elapsed_time": "2:14:08", "remaining_time": "0:01:24", "throughput": "12377.19", "total_tokens": 99614720}
+{"current_steps": 382, "total_steps": 384, "loss": 0.2434, "learning_rate": 6.763371270035457e-09, "epoch": 2.964112512124151, "percentage": 99.48, "elapsed_time": "2:14:50", "remaining_time": "0:00:42", "throughput": "12377.19", "total_tokens": 100139008}
+{"current_steps": 384, "total_steps": 384, "loss": 0.2042, "learning_rate": 0.0, "epoch": 2.979631425800194, "percentage": 100.0, "elapsed_time": "2:15:33", "remaining_time": "0:00:00", "throughput": "12377.13", "total_tokens": 100663296}
+{"current_steps": 384, "total_steps": 384, "epoch": 2.979631425800194, "percentage": 100.0, "elapsed_time": "2:15:33", "remaining_time": "0:00:00", "throughput": "12375.80", "total_tokens": 100663296}

trainer_state.json

@@ -0,0 +1,1579 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.979631425800194,
+  "eval_steps": 5000,
+  "global_step": 384,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015518913676042677,
+      "grad_norm": 0.416015625,
+      "learning_rate": 0.0001,
+      "loss": 0.831,
+      "num_input_tokens_seen": 524288,
+      "step": 2
+    },
+    {
+      "epoch": 0.031037827352085354,
+      "grad_norm": 0.49609375,
+      "learning_rate": 9.999323662872997e-05,
+      "loss": 0.7398,
+      "num_input_tokens_seen": 1048576,
+      "step": 4
+    },
+    {
+      "epoch": 0.04655674102812803,
+      "grad_norm": 0.333984375,
+      "learning_rate": 9.99729483446475e-05,
+      "loss": 0.6438,
+      "num_input_tokens_seen": 1572864,
+      "step": 6
+    },
+    {
+      "epoch": 0.06207565470417071,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.993914063644052e-05,
+      "loss": 0.6032,
+      "num_input_tokens_seen": 2097152,
+      "step": 8
+    },
+    {
+      "epoch": 0.07759456838021339,
+      "grad_norm": 0.314453125,
+      "learning_rate": 9.989182265027232e-05,
+      "loss": 0.5433,
+      "num_input_tokens_seen": 2621440,
+      "step": 10
+    },
+    {
+      "epoch": 0.09311348205625607,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 9.98310071873072e-05,
+      "loss": 0.5228,
+      "num_input_tokens_seen": 3145728,
+      "step": 12
+    },
+    {
+      "epoch": 0.10863239573229874,
+      "grad_norm": 0.3359375,
+      "learning_rate": 9.97567107002474e-05,
+      "loss": 0.4702,
+      "num_input_tokens_seen": 3670016,
+      "step": 14
+    },
+    {
+      "epoch": 0.12415130940834142,
+      "grad_norm": 0.2109375,
+      "learning_rate": 9.966895328888194e-05,
+      "loss": 0.4574,
+      "num_input_tokens_seen": 4194304,
+      "step": 16
+    },
+    {
+      "epoch": 0.1396702230843841,
+      "grad_norm": 0.224609375,
+      "learning_rate": 9.956775869464901e-05,
+      "loss": 0.5093,
+      "num_input_tokens_seen": 4718592,
+      "step": 18
+    },
+    {
+      "epoch": 0.15518913676042678,
+      "grad_norm": 0.25390625,
+      "learning_rate": 9.945315429421306e-05,
+      "loss": 0.4771,
+      "num_input_tokens_seen": 5242880,
+      "step": 20
+    },
+    {
+      "epoch": 0.17070805043646944,
+      "grad_norm": 0.201171875,
+      "learning_rate": 9.932517109205849e-05,
+      "loss": 0.4343,
+      "num_input_tokens_seen": 5767168,
+      "step": 22
+    },
+    {
+      "epoch": 0.18622696411251213,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 9.918384371210176e-05,
+      "loss": 0.4455,
+      "num_input_tokens_seen": 6291456,
+      "step": 24
+    },
+    {
+      "epoch": 0.2017458777885548,
+      "grad_norm": 3.265625,
+      "learning_rate": 9.902921038832455e-05,
+      "loss": 0.4669,
+      "num_input_tokens_seen": 6815744,
+      "step": 26
+    },
+    {
+      "epoch": 0.21726479146459748,
+      "grad_norm": 2.421875,
+      "learning_rate": 9.886131295443003e-05,
+      "loss": 0.4723,
+      "num_input_tokens_seen": 7340032,
+      "step": 28
+    },
+    {
+      "epoch": 0.23278370514064015,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 9.868019683252543e-05,
+      "loss": 0.4364,
+      "num_input_tokens_seen": 7864320,
+      "step": 30
+    },
+    {
+      "epoch": 0.24830261881668284,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.848591102083375e-05,
+      "loss": 0.4013,
+      "num_input_tokens_seen": 8388608,
+      "step": 32
+    },
+    {
+      "epoch": 0.2638215324927255,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 9.82785080804381e-05,
+      "loss": 0.3875,
+      "num_input_tokens_seen": 8912896,
+      "step": 34
+    },
+    {
+      "epoch": 0.2793404461687682,
+      "grad_norm": 0.125,
+      "learning_rate": 9.805804412106198e-05,
+      "loss": 0.4187,
+      "num_input_tokens_seen": 9437184,
+      "step": 36
+    },
+    {
+      "epoch": 0.2948593598448109,
+      "grad_norm": 0.12255859375,
+      "learning_rate": 9.782457878588977e-05,
+      "loss": 0.3981,
+      "num_input_tokens_seen": 9961472,
+      "step": 38
+    },
+    {
+      "epoch": 0.31037827352085356,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 9.757817523543109e-05,
+      "loss": 0.4121,
+      "num_input_tokens_seen": 10485760,
+      "step": 40
+    },
+    {
+      "epoch": 0.3258971871968962,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 9.731890013043368e-05,
+      "loss": 0.392,
+      "num_input_tokens_seen": 11010048,
+      "step": 42
+    },
+    {
+      "epoch": 0.3414161008729389,
+      "grad_norm": 0.10546875,
+      "learning_rate": 9.704682361384941e-05,
+      "loss": 0.3845,
+      "num_input_tokens_seen": 11534336,
+      "step": 44
+    },
+    {
+      "epoch": 0.3569350145489816,
+      "grad_norm": 0.0859375,
+      "learning_rate": 9.676201929185809e-05,
+      "loss": 0.397,
+      "num_input_tokens_seen": 12058624,
+      "step": 46
+    },
+    {
+      "epoch": 0.37245392822502427,
+      "grad_norm": 0.083984375,
+      "learning_rate": 9.646456421395446e-05,
+      "loss": 0.3753,
+      "num_input_tokens_seen": 12582912,
+      "step": 48
+    },
+    {
+      "epoch": 0.3879728419010669,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 9.615453885210369e-05,
+      "loss": 0.387,
+      "num_input_tokens_seen": 13107200,
+      "step": 50
+    },
+    {
+      "epoch": 0.4034917555771096,
+      "grad_norm": 0.0703125,
+      "learning_rate": 9.583202707897074e-05,
+      "loss": 0.3724,
+      "num_input_tokens_seen": 13631488,
+      "step": 52
+    },
+    {
+      "epoch": 0.4190106692531523,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 9.549711614523007e-05,
+      "loss": 0.4394,
+      "num_input_tokens_seen": 14155776,
+      "step": 54
+    },
+    {
+      "epoch": 0.43452958292919497,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 9.514989665596114e-05,
+      "loss": 0.4177,
+      "num_input_tokens_seen": 14680064,
+      "step": 56
+    },
+    {
+      "epoch": 0.45004849660523766,
+      "grad_norm": 0.078125,
+      "learning_rate": 9.479046254613673e-05,
+      "loss": 0.3939,
+      "num_input_tokens_seen": 15204352,
+      "step": 58
+    },
+    {
+      "epoch": 0.4655674102812803,
+      "grad_norm": 0.076171875,
+      "learning_rate": 9.441891105521006e-05,
+      "loss": 0.4207,
+      "num_input_tokens_seen": 15728640,
+      "step": 60
+    },
+    {
+      "epoch": 0.481086323957323,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 9.403534270080829e-05,
+      "loss": 0.3653,
+      "num_input_tokens_seen": 16252928,
+      "step": 62
+    },
+    {
+      "epoch": 0.49660523763336567,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 9.3639861251539e-05,
+      "loss": 0.3925,
+      "num_input_tokens_seen": 16777216,
+      "step": 64
+    },
+    {
+      "epoch": 0.5121241513094084,
+      "grad_norm": 0.0859375,
+      "learning_rate": 9.323257369891703e-05,
+      "loss": 0.3982,
+      "num_input_tokens_seen": 17301504,
+      "step": 66
+    },
+    {
+      "epoch": 0.527643064985451,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 9.281359022841965e-05,
+      "loss": 0.3709,
+      "num_input_tokens_seen": 17825792,
+      "step": 68
+    },
+    {
+      "epoch": 0.5431619786614937,
+      "grad_norm": 0.068359375,
+      "learning_rate": 9.238302418967756e-05,
+      "loss": 0.3744,
+      "num_input_tokens_seen": 18350080,
+      "step": 70
+    },
+    {
+      "epoch": 0.5586808923375364,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 9.194099206580982e-05,
+      "loss": 0.3929,
+      "num_input_tokens_seen": 18874368,
+      "step": 72
+    },
+    {
+      "epoch": 0.574199806013579,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 9.148761344191109e-05,
+      "loss": 0.3716,
+      "num_input_tokens_seen": 19398656,
+      "step": 74
+    },
+    {
+      "epoch": 0.5897187196896218,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 9.102301097269974e-05,
+      "loss": 0.3959,
+      "num_input_tokens_seen": 19922944,
+      "step": 76
+    },
+    {
+      "epoch": 0.6052376333656644,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 9.054731034933549e-05,
+      "loss": 0.3514,
+      "num_input_tokens_seen": 20447232,
+      "step": 78
+    },
+    {
+      "epoch": 0.6207565470417071,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 9.006064026541548e-05,
+      "loss": 0.3767,
+      "num_input_tokens_seen": 20971520,
+      "step": 80
+    },
+    {
+      "epoch": 0.6362754607177498,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 8.956313238215824e-05,
+      "loss": 0.371,
+      "num_input_tokens_seen": 21495808,
+      "step": 82
+    },
+    {
+      "epoch": 0.6517943743937924,
+      "grad_norm": 0.1171875,
+      "learning_rate": 8.905492129278478e-05,
+      "loss": 0.3529,
+      "num_input_tokens_seen": 22020096,
+      "step": 84
+    },
+    {
+      "epoch": 0.6673132880698351,
+      "grad_norm": 0.06640625,
+      "learning_rate": 8.853614448610631e-05,
+      "loss": 0.3044,
+      "num_input_tokens_seen": 22544384,
+      "step": 86
+    },
+    {
+      "epoch": 0.6828322017458778,
+      "grad_norm": 0.072265625,
+      "learning_rate": 8.800694230932884e-05,
+      "loss": 0.3532,
+      "num_input_tokens_seen": 23068672,
+      "step": 88
+    },
+    {
+      "epoch": 0.6983511154219205,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 8.74674579300843e-05,
+      "loss": 0.3461,
+      "num_input_tokens_seen": 23592960,
+      "step": 90
+    },
+    {
+      "epoch": 0.7138700290979632,
+      "grad_norm": 0.0693359375,
+      "learning_rate": 8.691783729769874e-05,
+      "loss": 0.3513,
+      "num_input_tokens_seen": 24117248,
+      "step": 92
+    },
+    {
+      "epoch": 0.7293889427740058,
+      "grad_norm": 0.06689453125,
+      "learning_rate": 8.635822910370792e-05,
+      "loss": 0.3842,
+      "num_input_tokens_seen": 24641536,
+      "step": 94
+    },
+    {
+      "epoch": 0.7449078564500485,
+      "grad_norm": 0.11083984375,
+      "learning_rate": 8.578878474163115e-05,
+      "loss": 0.363,
+      "num_input_tokens_seen": 25165824,
+      "step": 96
+    },
+    {
+      "epoch": 0.7604267701260912,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 8.520965826601394e-05,
+      "loss": 0.3079,
+      "num_input_tokens_seen": 25690112,
+      "step": 98
+    },
+    {
+      "epoch": 0.7759456838021338,
+      "grad_norm": 0.08203125,
+      "learning_rate": 8.462100635075097e-05,
+      "loss": 0.3769,
+      "num_input_tokens_seen": 26214400,
+      "step": 100
+    },
+    {
+      "epoch": 0.7914645974781765,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 8.40229882467003e-05,
+      "loss": 0.3907,
+      "num_input_tokens_seen": 26738688,
+      "step": 102
+    },
+    {
+      "epoch": 0.8069835111542192,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 8.341576573860048e-05,
+      "loss": 0.3457,
+      "num_input_tokens_seen": 27262976,
+      "step": 104
+    },
+    {
+      "epoch": 0.8225024248302619,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 8.279950310130217e-05,
+      "loss": 0.3889,
+      "num_input_tokens_seen": 27787264,
+      "step": 106
+    },
+    {
+      "epoch": 0.8380213385063046,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 8.2174367055326e-05,
+      "loss": 0.3142,
+      "num_input_tokens_seen": 28311552,
+      "step": 108
+    },
+    {
+      "epoch": 0.8535402521823472,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 8.154052672175887e-05,
+      "loss": 0.3299,
+      "num_input_tokens_seen": 28835840,
+      "step": 110
+    },
+    {
+      "epoch": 0.8690591658583899,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 8.089815357650089e-05,
+      "loss": 0.3425,
+      "num_input_tokens_seen": 29360128,
+      "step": 112
+    },
+    {
+      "epoch": 0.8845780795344326,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 8.024742140387506e-05,
+      "loss": 0.3363,
+      "num_input_tokens_seen": 29884416,
+      "step": 114
+    },
+    {
+      "epoch": 0.9000969932104753,
+      "grad_norm": 0.083984375,
+      "learning_rate": 7.95885062496126e-05,
+      "loss": 0.3725,
+      "num_input_tokens_seen": 30408704,
+      "step": 116
+    },
+    {
+      "epoch": 0.915615906886518,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 7.892158637322646e-05,
+      "loss": 0.3397,
+      "num_input_tokens_seen": 30932992,
+      "step": 118
+    },
+    {
+      "epoch": 0.9311348205625606,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 7.824684219978591e-05,
+      "loss": 0.2812,
+      "num_input_tokens_seen": 31457280,
+      "step": 120
+    },
+    {
+      "epoch": 0.9466537342386033,
+      "grad_norm": 0.1015625,
+      "learning_rate": 7.756445627110523e-05,
+      "loss": 0.3555,
+      "num_input_tokens_seen": 31981568,
+      "step": 122
+    },
+    {
+      "epoch": 0.962172647914646,
+      "grad_norm": 0.072265625,
+      "learning_rate": 7.687461319635981e-05,
+      "loss": 0.3362,
+      "num_input_tokens_seen": 32505856,
+      "step": 124
+    },
+    {
+      "epoch": 0.9776915615906887,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 7.6177499602143e-05,
+      "loss": 0.3133,
+      "num_input_tokens_seen": 33030144,
+      "step": 126
+    },
+    {
+      "epoch": 0.9932104752667313,
+      "grad_norm": 0.06982421875,
+      "learning_rate": 7.547330408197695e-05,
+      "loss": 0.3119,
+      "num_input_tokens_seen": 33554432,
+      "step": 128
+    },
+    {
+      "epoch": 1.008729388942774,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 7.476221714529167e-05,
+      "loss": 0.3117,
+      "num_input_tokens_seen": 34078720,
+      "step": 130
+    },
+    {
+      "epoch": 1.0242483026188167,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 7.404443116588548e-05,
+      "loss": 0.329,
+      "num_input_tokens_seen": 34603008,
+      "step": 132
+    },
+    {
+      "epoch": 1.0397672162948595,
+      "grad_norm": 0.078125,
+      "learning_rate": 7.332014032988123e-05,
+      "loss": 0.279,
+      "num_input_tokens_seen": 35127296,
+      "step": 134
+    },
+    {
+      "epoch": 1.055286129970902,
+      "grad_norm": 0.0703125,
+      "learning_rate": 7.258954058319216e-05,
+      "loss": 0.2682,
+      "num_input_tokens_seen": 35651584,
+      "step": 136
+    },
+    {
+      "epoch": 1.0708050436469447,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 7.185282957851175e-05,
+      "loss": 0.293,
+      "num_input_tokens_seen": 36175872,
+      "step": 138
+    },
+    {
+      "epoch": 1.0863239573229875,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 7.111020662184174e-05,
+      "loss": 0.315,
+      "num_input_tokens_seen": 36700160,
+      "step": 140
+    },
+    {
+      "epoch": 1.10184287099903,
+      "grad_norm": 0.072265625,
+      "learning_rate": 7.036187261857289e-05,
+      "loss": 0.289,
+      "num_input_tokens_seen": 37224448,
+      "step": 142
+    },
+    {
+      "epoch": 1.1173617846750727,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 6.960803001913314e-05,
+      "loss": 0.2808,
+      "num_input_tokens_seen": 37748736,
+      "step": 144
+    },
+    {
+      "epoch": 1.1328806983511155,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 6.884888276421766e-05,
+      "loss": 0.318,
+      "num_input_tokens_seen": 38273024,
+      "step": 146
+    },
+    {
+      "epoch": 1.148399612027158,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 6.808463622961578e-05,
+      "loss": 0.2685,
+      "num_input_tokens_seen": 38797312,
+      "step": 148
+    },
+    {
+      "epoch": 1.1639185257032008,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 6.731549717064974e-05,
+      "loss": 0.3121,
+      "num_input_tokens_seen": 39321600,
+      "step": 150
+    },
+    {
+      "epoch": 1.1794374393792435,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 6.654167366624009e-05,
+      "loss": 0.2835,
+      "num_input_tokens_seen": 39845888,
+      "step": 152
+    },
+    {
+      "epoch": 1.1949563530552862,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 6.576337506261314e-05,
+      "loss": 0.2905,
+      "num_input_tokens_seen": 40370176,
+      "step": 154
+    },
+    {
+      "epoch": 1.2104752667313288,
+      "grad_norm": 0.08984375,
+      "learning_rate": 6.498081191666548e-05,
+      "loss": 0.3277,
+      "num_input_tokens_seen": 40894464,
+      "step": 156
+    },
+    {
+      "epoch": 1.2259941804073715,
+      "grad_norm": 0.0859375,
+      "learning_rate": 6.419419593900108e-05,
+      "loss": 0.2788,
+      "num_input_tokens_seen": 41418752,
+      "step": 158
+    },
+    {
+      "epoch": 1.2415130940834143,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 6.340373993665607e-05,
+      "loss": 0.2971,
+      "num_input_tokens_seen": 41943040,
+      "step": 160
+    },
+    {
+      "epoch": 1.2570320077594568,
+      "grad_norm": 0.091796875,
+      "learning_rate": 6.260965775552712e-05,
+      "loss": 0.287,
+      "num_input_tokens_seen": 42467328,
+      "step": 162
+    },
+    {
+      "epoch": 1.2725509214354995,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 6.181216422251862e-05,
+      "loss": 0.3196,
+      "num_input_tokens_seen": 42991616,
+      "step": 164
+    },
+    {
+      "epoch": 1.2880698351115423,
+      "grad_norm": 0.083984375,
+      "learning_rate": 6.101147508742455e-05,
+      "loss": 0.3021,
+      "num_input_tokens_seen": 43515904,
+      "step": 166
+    },
+    {
+      "epoch": 1.3035887487875848,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 6.0207806964560584e-05,
+      "loss": 0.2329,
+      "num_input_tokens_seen": 44040192,
+      "step": 168
+    },
+    {
+      "epoch": 1.3191076624636275,
+      "grad_norm": 0.08984375,
+      "learning_rate": 5.940137727416246e-05,
+      "loss": 0.2803,
+      "num_input_tokens_seen": 44564480,
+      "step": 170
+    },
+    {
+      "epoch": 1.3346265761396703,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 5.8592404183566144e-05,
+      "loss": 0.2744,
+      "num_input_tokens_seen": 45088768,
+      "step": 172
+    },
+    {
+      "epoch": 1.3501454898157128,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 5.778110654818601e-05,
+      "loss": 0.3332,
+      "num_input_tokens_seen": 45613056,
+      "step": 174
+    },
+    {
+      "epoch": 1.3656644034917556,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 5.6967703852306786e-05,
+      "loss": 0.3223,
+      "num_input_tokens_seen": 46137344,
+      "step": 176
+    },
+    {
+      "epoch": 1.3811833171677983,
+      "grad_norm": 0.083984375,
+      "learning_rate": 5.6152416149705455e-05,
+      "loss": 0.3127,
+      "num_input_tokens_seen": 46661632,
+      "step": 178
+    },
+    {
+      "epoch": 1.3967022308438408,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 5.5335464004118986e-05,
+      "loss": 0.2908,
+      "num_input_tokens_seen": 47185920,
+      "step": 180
+    },
+    {
+      "epoch": 1.4122211445198836,
+      "grad_norm": 0.08984375,
+      "learning_rate": 5.4517068429574215e-05,
+      "loss": 0.2918,
+      "num_input_tokens_seen": 47710208,
+      "step": 182
+    },
+    {
+      "epoch": 1.4277400581959263,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 5.3697450830595774e-05,
+      "loss": 0.268,
+      "num_input_tokens_seen": 48234496,
+      "step": 184
+    },
+    {
+      "epoch": 1.4432589718719688,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 5.287683294230855e-05,
+      "loss": 0.2862,
+      "num_input_tokens_seen": 48758784,
+      "step": 186
+    },
+    {
+      "epoch": 1.4587778855480116,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 5.205543677045049e-05,
+      "loss": 0.3054,
+      "num_input_tokens_seen": 49283072,
+      "step": 188
+    },
+    {
+      "epoch": 1.4742967992240543,
+      "grad_norm": 0.087890625,
+      "learning_rate": 5.1233484531312414e-05,
+      "loss": 0.2814,
+      "num_input_tokens_seen": 49807360,
+      "step": 190
+    },
+    {
+      "epoch": 1.489815712900097,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 5.0411198591620676e-05,
+      "loss": 0.2703,
+      "num_input_tokens_seen": 50331648,
+      "step": 192
+    },
+    {
+      "epoch": 1.5053346265761398,
+      "grad_norm": 0.11181640625,
+      "learning_rate": 4.958880140837933e-05,
+      "loss": 0.2689,
+      "num_input_tokens_seen": 50855936,
+      "step": 194
+    },
+    {
+      "epoch": 1.5208535402521823,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 4.876651546868759e-05,
+      "loss": 0.3013,
+      "num_input_tokens_seen": 51380224,
+      "step": 196
+    },
+    {
+      "epoch": 1.536372453928225,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 4.794456322954952e-05,
+      "loss": 0.2751,
+      "num_input_tokens_seen": 51904512,
+      "step": 198
+    },
+    {
+      "epoch": 1.5518913676042678,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 4.712316705769145e-05,
+      "loss": 0.3178,
+      "num_input_tokens_seen": 52428800,
+      "step": 200
+    },
+    {
+      "epoch": 1.5674102812803103,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 4.630254916940424e-05,
+      "loss": 0.2742,
+      "num_input_tokens_seen": 52953088,
+      "step": 202
+    },
+    {
+      "epoch": 1.582929194956353,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 4.548293157042581e-05,
+      "loss": 0.2751,
+      "num_input_tokens_seen": 53477376,
+      "step": 204
+    },
+    {
+      "epoch": 1.5984481086323958,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 4.466453599588103e-05,
+      "loss": 0.3256,
+      "num_input_tokens_seen": 54001664,
+      "step": 206
+    },
+    {
+      "epoch": 1.6139670223084384,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 4.384758385029457e-05,
+      "loss": 0.2603,
+      "num_input_tokens_seen": 54525952,
+      "step": 208
+    },
+    {
+      "epoch": 1.629485935984481,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 4.3032296147693225e-05,
+      "loss": 0.2598,
+      "num_input_tokens_seen": 55050240,
+      "step": 210
+    },
+    {
+      "epoch": 1.6450048496605238,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 4.2218893451814005e-05,
+      "loss": 0.2811,
+      "num_input_tokens_seen": 55574528,
+      "step": 212
+    },
+    {
+      "epoch": 1.6605237633365664,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 4.140759581643386e-05,
+      "loss": 0.2386,
+      "num_input_tokens_seen": 56098816,
+      "step": 214
+    },
+    {
+      "epoch": 1.6760426770126091,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 4.059862272583755e-05,
+      "loss": 0.2999,
+      "num_input_tokens_seen": 56623104,
+      "step": 216
+    },
+    {
+      "epoch": 1.6915615906886519,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 3.979219303543942e-05,
+      "loss": 0.2857,
+      "num_input_tokens_seen": 57147392,
+      "step": 218
+    },
+    {
+      "epoch": 1.7070805043646944,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 3.898852491257546e-05,
+      "loss": 0.2533,
+      "num_input_tokens_seen": 57671680,
+      "step": 220
+    },
+    {
+      "epoch": 1.7225994180407371,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 3.818783577748138e-05,
+      "loss": 0.306,
+      "num_input_tokens_seen": 58195968,
+      "step": 222
+    },
+    {
+      "epoch": 1.7381183317167799,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 3.739034224447289e-05,
+      "loss": 0.2594,
+      "num_input_tokens_seen": 58720256,
+      "step": 224
+    },
+    {
+      "epoch": 1.7536372453928224,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 3.659626006334395e-05,
+      "loss": 0.284,
+      "num_input_tokens_seen": 59244544,
+      "step": 226
+    },
+    {
+      "epoch": 1.7691561590688651,
+      "grad_norm": 0.10546875,
+      "learning_rate": 3.580580406099893e-05,
+      "loss": 0.33,
+      "num_input_tokens_seen": 59768832,
+      "step": 228
+    },
+    {
+      "epoch": 1.7846750727449079,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 3.501918808333453e-05,
+      "loss": 0.2968,
+      "num_input_tokens_seen": 60293120,
+      "step": 230
+    },
+    {
+      "epoch": 1.8001939864209504,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 3.4236624937386876e-05,
+      "loss": 0.2836,
+      "num_input_tokens_seen": 60817408,
+      "step": 232
+    },
+    {
+      "epoch": 1.8157129000969934,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 3.3458326333759925e-05,
+      "loss": 0.2452,
+      "num_input_tokens_seen": 61341696,
+      "step": 234
+    },
+    {
+      "epoch": 1.831231813773036,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 3.268450282935026e-05,
+      "loss": 0.2526,
+      "num_input_tokens_seen": 61865984,
+      "step": 236
+    },
+    {
+      "epoch": 1.8467507274490784,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 3.191536377038422e-05,
+      "loss": 0.2578,
+      "num_input_tokens_seen": 62390272,
+      "step": 238
+    },
+    {
+      "epoch": 1.8622696411251214,
+      "grad_norm": 0.09375,
+      "learning_rate": 3.115111723578235e-05,
+      "loss": 0.2895,
+      "num_input_tokens_seen": 62914560,
+      "step": 240
+    },
+    {
+      "epoch": 1.877788554801164,
+      "grad_norm": 0.134765625,
+      "learning_rate": 3.0391969980866875e-05,
+      "loss": 0.3047,
+      "num_input_tokens_seen": 63438848,
+      "step": 242
+    },
+    {
+      "epoch": 1.8933074684772064,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 2.963812738142713e-05,
+      "loss": 0.2958,
+      "num_input_tokens_seen": 63963136,
+      "step": 244
+    },
+    {
+      "epoch": 1.9088263821532494,
+      "grad_norm": 0.1015625,
+      "learning_rate": 2.888979337815828e-05,
+      "loss": 0.2598,
+      "num_input_tokens_seen": 64487424,
+      "step": 246
+    },
+    {
+      "epoch": 1.924345295829292,
+      "grad_norm": 0.09375,
+      "learning_rate": 2.8147170421488272e-05,
+      "loss": 0.2699,
+      "num_input_tokens_seen": 65011712,
+      "step": 248
+    },
+    {
+      "epoch": 1.9398642095053347,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 2.7410459416807853e-05,
+      "loss": 0.2827,
+      "num_input_tokens_seen": 65536000,
+      "step": 250
+    },
+    {
+      "epoch": 1.9553831231813774,
+      "grad_norm": 0.1953125,
+      "learning_rate": 2.6679859670118783e-05,
+      "loss": 0.3119,
+      "num_input_tokens_seen": 66060288,
+      "step": 252
+    },
+    {
+      "epoch": 1.97090203685742,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 2.5955568834114524e-05,
+      "loss": 0.2837,
+      "num_input_tokens_seen": 66584576,
+      "step": 254
+    },
+    {
+      "epoch": 1.9864209505334627,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 2.5237782854708348e-05,
+      "loss": 0.2511,
+      "num_input_tokens_seen": 67108864,
+      "step": 256
+    },
+    {
+      "epoch": 2.0019398642095054,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 2.452669591802307e-05,
+      "loss": 0.2501,
+      "num_input_tokens_seen": 67633152,
+      "step": 258
+    },
+    {
+      "epoch": 2.017458777885548,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 2.3822500397857018e-05,
+      "loss": 0.2296,
+      "num_input_tokens_seen": 68157440,
+      "step": 260
+    },
+    {
+      "epoch": 2.0329776915615905,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 2.3125386803640187e-05,
+      "loss": 0.2333,
+      "num_input_tokens_seen": 68681728,
+      "step": 262
+    },
+    {
+      "epoch": 2.0484966052376334,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 2.2435543728894792e-05,
+      "loss": 0.2119,
+      "num_input_tokens_seen": 69206016,
+      "step": 264
+    },
+    {
+      "epoch": 2.064015518913676,
+      "grad_norm": 0.099609375,
+      "learning_rate": 2.175315780021411e-05,
+      "loss": 0.2676,
+      "num_input_tokens_seen": 69730304,
+      "step": 266
+    },
+    {
+      "epoch": 2.079534432589719,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 2.1078413626773546e-05,
+      "loss": 0.2285,
+      "num_input_tokens_seen": 70254592,
+      "step": 268
+    },
+    {
+      "epoch": 2.0950533462657615,
+      "grad_norm": 0.10546875,
+      "learning_rate": 2.0411493750387423e-05,
+      "loss": 0.2281,
+      "num_input_tokens_seen": 70778880,
+      "step": 270
+    },
+    {
+      "epoch": 2.110572259941804,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 1.9752578596124954e-05,
+      "loss": 0.2701,
+      "num_input_tokens_seen": 71303168,
+      "step": 272
+    },
+    {
+      "epoch": 2.126091173617847,
+      "grad_norm": 0.08984375,
+      "learning_rate": 1.9101846423499116e-05,
+      "loss": 0.2033,
+      "num_input_tokens_seen": 71827456,
+      "step": 274
+    },
+    {
+      "epoch": 2.1416100872938895,
+      "grad_norm": 0.10546875,
+      "learning_rate": 1.8459473278241126e-05,
+      "loss": 0.2489,
+      "num_input_tokens_seen": 72351744,
+      "step": 276
+    },
+    {
+      "epoch": 2.157129000969932,
+      "grad_norm": 0.1015625,
+      "learning_rate": 1.7825632944674015e-05,
+      "loss": 0.2294,
+      "num_input_tokens_seen": 72876032,
+      "step": 278
+    },
+    {
+      "epoch": 2.172647914645975,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 1.7200496898697832e-05,
+      "loss": 0.2452,
+      "num_input_tokens_seen": 73400320,
+      "step": 280
+    },
+    {
+      "epoch": 2.1881668283220175,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.6584234261399534e-05,
+      "loss": 0.242,
+      "num_input_tokens_seen": 73924608,
+      "step": 282
+    },
+    {
+      "epoch": 2.20368574199806,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 1.5977011753299725e-05,
+      "loss": 0.2894,
+      "num_input_tokens_seen": 74448896,
+      "step": 284
+    },
+    {
+      "epoch": 2.219204655674103,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 1.537899364924905e-05,
+      "loss": 0.231,
+      "num_input_tokens_seen": 74973184,
+      "step": 286
+    },
+    {
+      "epoch": 2.2347235693501455,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 1.4790341733986085e-05,
+      "loss": 0.2412,
+      "num_input_tokens_seen": 75497472,
+      "step": 288
+    },
+    {
+      "epoch": 2.250242483026188,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 1.4211215258368866e-05,
+      "loss": 0.2464,
+      "num_input_tokens_seen": 76021760,
+      "step": 290
+    },
+    {
+      "epoch": 2.265761396702231,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 1.3641770896292084e-05,
+      "loss": 0.2231,
+      "num_input_tokens_seen": 76546048,
+      "step": 292
+    },
+    {
+      "epoch": 2.2812803103782735,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 1.3082162702301276e-05,
+      "loss": 0.2432,
+      "num_input_tokens_seen": 77070336,
+      "step": 294
+    },
+    {
+      "epoch": 2.296799224054316,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.253254206991572e-05,
+      "loss": 0.2147,
+      "num_input_tokens_seen": 77594624,
+      "step": 296
+    },
+    {
+      "epoch": 2.312318137730359,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 1.1993057690671173e-05,
+      "loss": 0.249,
+      "num_input_tokens_seen": 78118912,
+      "step": 298
+    },
+    {
+      "epoch": 2.3278370514064015,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 1.1463855513893695e-05,
+      "loss": 0.2362,
+      "num_input_tokens_seen": 78643200,
+      "step": 300
+    },
+    {
+      "epoch": 2.343355965082444,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 1.0945078707215222e-05,
+      "loss": 0.2232,
+      "num_input_tokens_seen": 79167488,
+      "step": 302
+    },
+    {
+      "epoch": 2.358874878758487,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 1.0436867617841768e-05,
+      "loss": 0.2569,
+      "num_input_tokens_seen": 79691776,
+      "step": 304
+    },
+    {
+      "epoch": 2.3743937924345295,
+      "grad_norm": 0.10546875,
+      "learning_rate": 9.939359734584553e-06,
+      "loss": 0.214,
+      "num_input_tokens_seen": 80216064,
+      "step": 306
+    },
+    {
+      "epoch": 2.3899127061105725,
+      "grad_norm": 0.09765625,
+      "learning_rate": 9.452689650664515e-06,
+      "loss": 0.2451,
+      "num_input_tokens_seen": 80740352,
+      "step": 308
+    },
+    {
+      "epoch": 2.405431619786615,
+      "grad_norm": 0.09375,
+      "learning_rate": 8.976989027300264e-06,
+      "loss": 0.2288,
+      "num_input_tokens_seen": 81264640,
+      "step": 310
+    },
+    {
+      "epoch": 2.4209505334626575,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 8.51238655808892e-06,
+      "loss": 0.2332,
+      "num_input_tokens_seen": 81788928,
+      "step": 312
+    },
+    {
+      "epoch": 2.4364694471387,
+      "grad_norm": 0.095703125,
+      "learning_rate": 8.059007934190194e-06,
+      "loss": 0.202,
+      "num_input_tokens_seen": 82313216,
+      "step": 314
+    },
+    {
+      "epoch": 2.451988360814743,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 7.61697581032243e-06,
+      "loss": 0.227,
+      "num_input_tokens_seen": 82837504,
+      "step": 316
+    },
+    {
+      "epoch": 2.4675072744907856,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 7.186409771580354e-06,
+      "loss": 0.2429,
+      "num_input_tokens_seen": 83361792,
+      "step": 318
+    },
+    {
+      "epoch": 2.4830261881668285,
+      "grad_norm": 0.09375,
+      "learning_rate": 6.76742630108298e-06,
+      "loss": 0.2147,
+      "num_input_tokens_seen": 83886080,
+      "step": 320
+    },
+    {
+      "epoch": 2.498545101842871,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 6.3601387484610145e-06,
+      "loss": 0.2423,
+      "num_input_tokens_seen": 84410368,
+      "step": 322
+    },
+    {
+      "epoch": 2.5140640155189136,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 5.9646572991917116e-06,
+      "loss": 0.2828,
+      "num_input_tokens_seen": 84934656,
+      "step": 324
+    },
+    {
+      "epoch": 2.529582929194956,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 5.581088944789953e-06,
+      "loss": 0.2461,
+      "num_input_tokens_seen": 85458944,
+      "step": 326
+    },
+    {
+      "epoch": 2.545101842870999,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 5.209537453863289e-06,
+      "loss": 0.296,
+      "num_input_tokens_seen": 85983232,
+      "step": 328
+    },
+    {
+      "epoch": 2.5606207565470416,
+      "grad_norm": 0.08984375,
+      "learning_rate": 4.850103344038853e-06,
+      "loss": 0.2061,
+      "num_input_tokens_seen": 86507520,
+      "step": 330
+    },
+    {
+      "epoch": 2.5761396702230845,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 4.502883854769935e-06,
+      "loss": 0.2323,
+      "num_input_tokens_seen": 87031808,
+      "step": 332
+    },
+    {
+      "epoch": 2.591658583899127,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 4.167972921029262e-06,
+      "loss": 0.2156,
+      "num_input_tokens_seen": 87556096,
+      "step": 334
+    },
+    {
+      "epoch": 2.6071774975751696,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 3.845461147896323e-06,
+      "loss": 0.2393,
+      "num_input_tokens_seen": 88080384,
+      "step": 336
+    },
+    {
+      "epoch": 2.6226964112512126,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 3.535435786045538e-06,
+      "loss": 0.2165,
+      "num_input_tokens_seen": 88604672,
+      "step": 338
+    },
+    {
+      "epoch": 2.638215324927255,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 3.2379807081419187e-06,
+      "loss": 0.2313,
+      "num_input_tokens_seen": 89128960,
+      "step": 340
+    },
+    {
+      "epoch": 2.653734238603298,
+      "grad_norm": 0.099609375,
+      "learning_rate": 2.9531763861505966e-06,
+      "loss": 0.2336,
+      "num_input_tokens_seen": 89653248,
+      "step": 342
+    },
+    {
+      "epoch": 2.6692531522793406,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 2.6810998695663282e-06,
+      "loss": 0.2311,
+      "num_input_tokens_seen": 90177536,
+      "step": 344
+    },
+    {
+      "epoch": 2.684772065955383,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 2.4218247645689307e-06,
+      "loss": 0.213,
+      "num_input_tokens_seen": 90701824,
+      "step": 346
+    },
+    {
+      "epoch": 2.7002909796314256,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 2.1754212141102346e-06,
+      "loss": 0.2364,
+      "num_input_tokens_seen": 91226112,
+      "step": 348
+    },
+    {
+      "epoch": 2.7158098933074686,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 1.941955878938029e-06,
+      "loss": 0.2147,
+      "num_input_tokens_seen": 91750400,
+      "step": 350
+    },
+    {
+      "epoch": 2.731328806983511,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 1.7214919195619127e-06,
+      "loss": 0.2316,
+      "num_input_tokens_seen": 92274688,
+      "step": 352
+    },
+    {
+      "epoch": 2.746847720659554,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 1.514088979166256e-06,
+      "loss": 0.2263,
+      "num_input_tokens_seen": 92798976,
+      "step": 354
+    },
+    {
+      "epoch": 2.7623666343355966,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.3198031674745813e-06,
+      "loss": 0.2323,
+      "num_input_tokens_seen": 93323264,
+      "step": 356
+    },
+    {
+      "epoch": 2.777885548011639,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 1.138687045569975e-06,
+      "loss": 0.2246,
+      "num_input_tokens_seen": 93847552,
+      "step": 358
+    },
+    {
+      "epoch": 2.7934044616876816,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 9.707896116754488e-07,
+      "loss": 0.2287,
+      "num_input_tokens_seen": 94371840,
+      "step": 360
+    },
+    {
+      "epoch": 2.8089233753637246,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 8.161562878982398e-07,
+      "loss": 0.2081,
+      "num_input_tokens_seen": 94896128,
+      "step": 362
+    },
+    {
+      "epoch": 2.824442289039767,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 6.74828907941516e-07,
+      "loss": 0.226,
+      "num_input_tokens_seen": 95420416,
+      "step": 364
+    },
+    {
+      "epoch": 2.83996120271581,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 5.468457057869358e-07,
+      "loss": 0.273,
+      "num_input_tokens_seen": 95944704,
+      "step": 366
+    },
+    {
+      "epoch": 2.8554801163918526,
+      "grad_norm": 0.107421875,
+      "learning_rate": 4.322413053509944e-07,
+      "loss": 0.2634,
+      "num_input_tokens_seen": 96468992,
+      "step": 368
+    },
+    {
+      "epoch": 2.870999030067895,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 3.3104671111806593e-07,
+      "loss": 0.2592,
+      "num_input_tokens_seen": 96993280,
+      "step": 370
+    },
+    {
+      "epoch": 2.8865179437439377,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 2.432892997526026e-07,
+      "loss": 0.2566,
+      "num_input_tokens_seen": 97517568,
+      "step": 372
+    },
+    {
+      "epoch": 2.9020368574199806,
+      "grad_norm": 0.099609375,
+      "learning_rate": 1.6899281269279755e-07,
+      "loss": 0.2575,
+      "num_input_tokens_seen": 98041856,
+      "step": 374
+    },
+    {
+      "epoch": 2.917555771096023,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 1.0817734972768944e-07,
+      "loss": 0.2482,
+      "num_input_tokens_seen": 98566144,
+      "step": 376
+    },
+    {
+      "epoch": 2.933074684772066,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 6.085936355947897e-08,
+      "loss": 0.2483,
+      "num_input_tokens_seen": 99090432,
+      "step": 378
+    },
+    {
+      "epoch": 2.9485935984481086,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 2.7051655352494652e-08,
+      "loss": 0.2359,
+      "num_input_tokens_seen": 99614720,
+      "step": 380
+    },
+    {
+      "epoch": 2.964112512124151,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 6.763371270035457e-09,
+      "loss": 0.2434,
+      "num_input_tokens_seen": 100139008,
+      "step": 382
+    },
+    {
+      "epoch": 2.979631425800194,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 0.0,
+      "loss": 0.2042,
+      "num_input_tokens_seen": 100663296,
+      "step": 384
+    },
+    {
+      "epoch": 2.979631425800194,
+      "num_input_tokens_seen": 100663296,
+      "step": 384,
+      "total_flos": 4.2827022437921587e+18,
+      "train_loss": 0.3106601850595325,
+      "train_runtime": 8133.8849,
+      "train_samples_per_second": 12.157,
+      "train_steps_per_second": 0.047
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 384,
+  "num_input_tokens_seen": 100663296,
+  "num_train_epochs": 3,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.2827022437921587e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641fd8445c27c8de50beaa5c1f0c27c0a3d158ba94db539f56dbd8c858546757
+size 5368

training_args.yaml

@@ -0,0 +1,37 @@
+bf16: true
+cutoff_len: 1024
+dataset: cangjie
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+eval_steps: 5000
+eval_strategy: steps
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 0.0001
+logging_steps: 2
+lora_alpha: 32
+lora_dropout: 0.1
+lora_rank: 8
+lora_target: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
+loraplus_lr_ratio: 16
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen2-7B-Instruct
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2-7B-Chat/lora/train_08-16-2
+packing: true
+per_device_eval_batch_size: 4
+per_device_train_batch_size: 4
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 5000
+stage: pt
+template: qwen
+val_size: 0.05
+warmup_steps: 2