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:ba10fcc8359141bdc76749bfe804bf1854c7c35161cb682341218e2174e7389e
+oid sha256:f9a23a94a34924b90b0f549089d98b2f3164a23353e3399ca0c5ed395e1eeeff
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1b73c40de3df8179743b16e333529d91bc1cbc4d729d0b6a0dbb0a2743c526a
+oid sha256:c182c74ba77845faabaa3f3b99b0f619fcfdfe21766f798f66ce984147476534
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c7f44ec6860003f13de57bd2ad679abc76372e696f0ba64dcb096ad8c2d194
+oid sha256:c6a3bdea21e6ba079ccbba624ec1dfb599a55306a888996d433b7da6e98cbcc2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6efc3cf2283ba2318df09b4fccd81fc2c7c92f336f9b8fbed31252acffe51a
+oid sha256:9a0972cadd551b6d9210f90d9b2e3421a9d27b4b199b21668663b7517dda9ca7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec5a5fa365a025d7b72e73ba5ae61435c717d5192c0a548efd67efffa7d01f8
+oid sha256:052d2643f94d39de729385018900f6560552f49ed10facb0a7531f28b31aadc0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef8374d5b4a7b565c654f01afc3676c24946d4955ee4d27506c6d5576f109d2
+oid sha256:efb31cd55af594dd5a265c5dff7191e1e4857df34d419a4bf8db7fd4e3cef497
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4098360655737705,
+  "epoch": 0.546448087431694,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 10.3736,
       "step": 75
+    },
+    {
+      "epoch": 0.41530054644808745,
+      "grad_norm": 0.05782744288444519,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3741,
+      "step": 76
+    },
+    {
+      "epoch": 0.4207650273224044,
+      "grad_norm": 0.06212912127375603,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3724,
+      "step": 77
+    },
+    {
+      "epoch": 0.4262295081967213,
+      "grad_norm": 0.05933624878525734,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3718,
+      "step": 78
+    },
+    {
+      "epoch": 0.43169398907103823,
+      "grad_norm": 0.06697092950344086,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3723,
+      "step": 79
+    },
+    {
+      "epoch": 0.4371584699453552,
+      "grad_norm": 0.07022427767515182,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3724,
+      "step": 80
+    },
+    {
+      "epoch": 0.4426229508196721,
+      "grad_norm": 0.0685114711523056,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3733,
+      "step": 81
+    },
+    {
+      "epoch": 0.4426229508196721,
+      "eval_loss": 10.37241268157959,
+      "eval_runtime": 0.8287,
+      "eval_samples_per_second": 743.363,
+      "eval_steps_per_second": 24.135,
+      "step": 81
+    },
+    {
+      "epoch": 0.44808743169398907,
+      "grad_norm": 0.06889978051185608,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3733,
+      "step": 82
+    },
+    {
+      "epoch": 0.453551912568306,
+      "grad_norm": 0.06139597296714783,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3727,
+      "step": 83
+    },
+    {
+      "epoch": 0.45901639344262296,
+      "grad_norm": 0.06276782602071762,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3731,
+      "step": 84
+    },
+    {
+      "epoch": 0.4644808743169399,
+      "grad_norm": 0.06612912565469742,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3714,
+      "step": 85
+    },
+    {
+      "epoch": 0.46994535519125685,
+      "grad_norm": 0.07081400603055954,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3717,
+      "step": 86
+    },
+    {
+      "epoch": 0.47540983606557374,
+      "grad_norm": 0.0591704323887825,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3735,
+      "step": 87
+    },
+    {
+      "epoch": 0.4808743169398907,
+      "grad_norm": 0.06865952908992767,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3724,
+      "step": 88
+    },
+    {
+      "epoch": 0.48633879781420764,
+      "grad_norm": 0.06752797216176987,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3725,
+      "step": 89
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 0.06979833543300629,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3714,
+      "step": 90
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "eval_loss": 10.372178077697754,
+      "eval_runtime": 0.8396,
+      "eval_samples_per_second": 733.682,
+      "eval_steps_per_second": 23.821,
+      "step": 90
+    },
+    {
+      "epoch": 0.4972677595628415,
+      "grad_norm": 0.06850720196962357,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3721,
+      "step": 91
+    },
+    {
+      "epoch": 0.5027322404371585,
+      "grad_norm": 0.06722009181976318,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3729,
+      "step": 92
+    },
+    {
+      "epoch": 0.5081967213114754,
+      "grad_norm": 0.06894061714410782,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3715,
+      "step": 93
+    },
+    {
+      "epoch": 0.5136612021857924,
+      "grad_norm": 0.06594067066907883,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3724,
+      "step": 94
+    },
+    {
+      "epoch": 0.5191256830601093,
+      "grad_norm": 0.0674702599644661,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3722,
+      "step": 95
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 0.06486930698156357,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3736,
+      "step": 96
+    },
+    {
+      "epoch": 0.5300546448087432,
+      "grad_norm": 0.06004992127418518,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3725,
+      "step": 97
+    },
+    {
+      "epoch": 0.5355191256830601,
+      "grad_norm": 0.07898783683776855,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3715,
+      "step": 98
+    },
+    {
+      "epoch": 0.5409836065573771,
+      "grad_norm": 0.06925985962152481,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3717,
+      "step": 99
+    },
+    {
+      "epoch": 0.5409836065573771,
+      "eval_loss": 10.372146606445312,
+      "eval_runtime": 0.8336,
+      "eval_samples_per_second": 738.92,
+      "eval_steps_per_second": 23.991,
+      "step": 99
+    },
+    {
+      "epoch": 0.546448087431694,
+      "grad_norm": 0.06981387734413147,
+      "learning_rate": 0.0,
+      "loss": 10.3721,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 31381467955200.0,
+  "total_flos": 41841957273600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null