Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d2f7e4f1c095ec0e4631cd524d2e283a06849f337e3dadd87db0a9f6043405
+oid sha256:ea967581f4108a7af7953cf3e2a561347d65864a71387ae0e84b75eb22647c33
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cda95b964ed8777b8a66181e3e64d8af3591aa05a65f4a9be75bbb7a5c1d3fc
+oid sha256:fddcf0e9feb3131642b633df161b69801800f8df2a8f41ac2fb02a6bff17fead
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 size 14244

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": 0.08944543828264759,
+  "epoch": 0.11926058437686345,
   "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": 10.3686,
       "step": 75
+    },
+    {
+      "epoch": 0.09063804412641623,
+      "grad_norm": 0.0732855573296547,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3666,
+      "step": 76
+    },
+    {
+      "epoch": 0.09183064997018485,
+      "grad_norm": 0.05297171697020531,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3696,
+      "step": 77
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 0.05004735663533211,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3691,
+      "step": 78
+    },
+    {
+      "epoch": 0.09421586165772212,
+      "grad_norm": 0.056061867624521255,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3688,
+      "step": 79
+    },
+    {
+      "epoch": 0.09540846750149076,
+      "grad_norm": 0.06218897923827171,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3682,
+      "step": 80
+    },
+    {
+      "epoch": 0.09660107334525939,
+      "grad_norm": 0.05653758719563484,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3744,
+      "step": 81
+    },
+    {
+      "epoch": 0.09660107334525939,
+      "eval_loss": 10.369139671325684,
+      "eval_runtime": 1.4083,
+      "eval_samples_per_second": 501.311,
+      "eval_steps_per_second": 63.196,
+      "step": 81
+    },
+    {
+      "epoch": 0.09779367918902802,
+      "grad_norm": 0.0647573173046112,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.371,
+      "step": 82
+    },
+    {
+      "epoch": 0.09898628503279666,
+      "grad_norm": 0.0794467180967331,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3652,
+      "step": 83
+    },
+    {
+      "epoch": 0.1001788908765653,
+      "grad_norm": 0.06957988440990448,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3704,
+      "step": 84
+    },
+    {
+      "epoch": 0.10137149672033392,
+      "grad_norm": 0.050267431885004044,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3687,
+      "step": 85
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 0.05273786932229996,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3704,
+      "step": 86
+    },
+    {
+      "epoch": 0.1037567084078712,
+      "grad_norm": 0.050435155630111694,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3724,
+      "step": 87
+    },
+    {
+      "epoch": 0.10494931425163984,
+      "grad_norm": 0.05046040192246437,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3641,
+      "step": 88
+    },
+    {
+      "epoch": 0.10614192009540847,
+      "grad_norm": 0.08423416316509247,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3732,
+      "step": 89
+    },
+    {
+      "epoch": 0.1073345259391771,
+      "grad_norm": 0.0676737129688263,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3709,
+      "step": 90
+    },
+    {
+      "epoch": 0.1073345259391771,
+      "eval_loss": 10.369009971618652,
+      "eval_runtime": 1.4423,
+      "eval_samples_per_second": 489.493,
+      "eval_steps_per_second": 61.707,
+      "step": 90
+    },
+    {
+      "epoch": 0.10852713178294573,
+      "grad_norm": 0.061363909393548965,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.371,
+      "step": 91
+    },
+    {
+      "epoch": 0.10971973762671437,
+      "grad_norm": 0.05670735239982605,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3729,
+      "step": 92
+    },
+    {
+      "epoch": 0.11091234347048301,
+      "grad_norm": 0.04956693947315216,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3691,
+      "step": 93
+    },
+    {
+      "epoch": 0.11210494931425163,
+      "grad_norm": 0.06154552474617958,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.369,
+      "step": 94
+    },
+    {
+      "epoch": 0.11329755515802027,
+      "grad_norm": 0.07234995067119598,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3676,
+      "step": 95
+    },
+    {
+      "epoch": 0.11449016100178891,
+      "grad_norm": 0.07232902944087982,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3691,
+      "step": 96
+    },
+    {
+      "epoch": 0.11568276684555755,
+      "grad_norm": 0.05388721078634262,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3661,
+      "step": 97
+    },
+    {
+      "epoch": 0.11687537268932618,
+      "grad_norm": 0.04916412755846977,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3708,
+      "step": 98
+    },
+    {
+      "epoch": 0.11806797853309481,
+      "grad_norm": 0.06878488510847092,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3664,
+      "step": 99
+    },
+    {
+      "epoch": 0.11806797853309481,
+      "eval_loss": 10.368987083435059,
+      "eval_runtime": 1.3332,
+      "eval_samples_per_second": 529.551,
+      "eval_steps_per_second": 66.756,
+      "step": 99
+    },
+    {
+      "epoch": 0.11926058437686345,
+      "grad_norm": 0.05977727845311165,
+      "learning_rate": 0.0,
+      "loss": 10.3683,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null