Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca3777dc11dfa9bf88d8cc6d00ba6310cb5d9fe808e281c945e383848b6e8ca
+oid sha256:7d41ac3b38b1f25f83b42f2b8106140a3fc805b15ea339bf95982f70326459e2
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25da41f8396bcb2e1bcf53e9d8725c15ff2bbc31ebf343f000dea35d8994c7b5
+oid sha256:f65194c80a8d3f9c4a8422d3d17d4bbba3b442cfde91b0722c9ee846756e9d8c
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997b37e8e4d4313266e5aafe8f4d418b086633a9c94b4c13db86ae839aa09b15
+oid sha256:9246553064bea11894d1cdc342a12358c62b3d7caceee2321170ee68aed86db4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06603565925599823,
+  "epoch": 0.08804754567466432,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 4.041,
       "eval_steps_per_second": 2.025,
       "step": 75
+    },
+    {
+      "epoch": 0.06691613471274488,
+      "grad_norm": 1.0145089626312256,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.4273,
+      "step": 76
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 1.8886373043060303,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 0.4417,
+      "step": 77
+    },
+    {
+      "epoch": 0.06867708562623817,
+      "grad_norm": 1.1678515672683716,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 0.4121,
+      "step": 78
+    },
+    {
+      "epoch": 0.06955756108298482,
+      "grad_norm": 3.4151155948638916,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.5006,
+      "step": 79
+    },
+    {
+      "epoch": 0.07043803653973145,
+      "grad_norm": 1.1192302703857422,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.3849,
+      "step": 80
+    },
+    {
+      "epoch": 0.0713185119964781,
+      "grad_norm": 1.1415249109268188,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 0.39,
+      "step": 81
+    },
+    {
+      "epoch": 0.07219898745322474,
+      "grad_norm": 1.7569003105163574,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6394,
+      "step": 82
+    },
+    {
+      "epoch": 0.07307946290997139,
+      "grad_norm": 3.5374794006347656,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 1.0147,
+      "step": 83
+    },
+    {
+      "epoch": 0.07395993836671803,
+      "grad_norm": 0.9409904479980469,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 0.3722,
+      "step": 84
+    },
+    {
+      "epoch": 0.07484041382346467,
+      "grad_norm": 1.6608474254608154,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.4311,
+      "step": 85
+    },
+    {
+      "epoch": 0.07572088928021131,
+      "grad_norm": 2.132925271987915,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 0.6121,
+      "step": 86
+    },
+    {
+      "epoch": 0.07660136473695796,
+      "grad_norm": 1.2028199434280396,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 0.33,
+      "step": 87
+    },
+    {
+      "epoch": 0.0774818401937046,
+      "grad_norm": 1.059144139289856,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.458,
+      "step": 88
+    },
+    {
+      "epoch": 0.07836231565045125,
+      "grad_norm": 1.6935112476348877,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 0.5158,
+      "step": 89
+    },
+    {
+      "epoch": 0.07924279110719788,
+      "grad_norm": 1.4320807456970215,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.4924,
+      "step": 90
+    },
+    {
+      "epoch": 0.08012326656394453,
+      "grad_norm": 2.2760002613067627,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.4067,
+      "step": 91
+    },
+    {
+      "epoch": 0.08100374202069117,
+      "grad_norm": 2.197097063064575,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 0.6285,
+      "step": 92
+    },
+    {
+      "epoch": 0.08188421747743782,
+      "grad_norm": 1.5171617269515991,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 0.5067,
+      "step": 93
+    },
+    {
+      "epoch": 0.08276469293418445,
+      "grad_norm": 1.208709478378296,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.419,
+      "step": 94
+    },
+    {
+      "epoch": 0.0836451683909311,
+      "grad_norm": 1.862436056137085,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.567,
+      "step": 95
+    },
+    {
+      "epoch": 0.08452564384767774,
+      "grad_norm": 1.5693188905715942,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 0.6098,
+      "step": 96
+    },
+    {
+      "epoch": 0.08540611930442439,
+      "grad_norm": 2.0004355907440186,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.5554,
+      "step": 97
+    },
+    {
+      "epoch": 0.08628659476117104,
+      "grad_norm": 1.4339842796325684,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 0.3237,
+      "step": 98
+    },
+    {
+      "epoch": 0.08716707021791767,
+      "grad_norm": 2.115415573120117,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 0.5879,
+      "step": 99
+    },
+    {
+      "epoch": 0.08804754567466432,
+      "grad_norm": 15.940089225769043,
+      "learning_rate": 0.0,
+      "loss": 0.7996,
+      "step": 100
+    },
+    {
+      "epoch": 0.08804754567466432,
+      "eval_loss": 0.4441887140274048,
+      "eval_runtime": 118.611,
+      "eval_samples_per_second": 4.038,
+      "eval_steps_per_second": 2.023,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.88845956923392e+16,
+  "total_flos": 1.318461275897856e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null