Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770f34d2af360ce37368d45351fd502f4f1882d96b301f9e1648c7e2070f4423
+oid sha256:f72b180fb42731238524b2c01c21984a6b474cdec4cffe82f5cb958e37bf5345
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d796e429f833b812d7a91107794f7e577f20ee6d95e8f5163c4b23ac17a577ba
+oid sha256:4e658bf5db720c761e1a6b7e2b7bff20d9f107228d76c75fdde0869f2fcb3a56
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c86b8cb9cf7d4aa12029d2c56f7ad5767a9d9029213bbbd55c9ff2f0cad5bf
+oid sha256:ee835b1b5466b4de2c4ddef4b908a309d122dcf6a40bd09f1f262cba8937c427
 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": 0.023302780798508622,
+  "epoch": 0.031070374398011497,
   "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": 0.0713,
       "step": 75
+    },
+    {
+      "epoch": 0.02361348454248874,
+      "grad_norm": 0.38487324118614197,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1164,
+      "step": 76
+    },
+    {
+      "epoch": 0.02392418828646885,
+      "grad_norm": 0.5476064682006836,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0682,
+      "step": 77
+    },
+    {
+      "epoch": 0.024234892030448967,
+      "grad_norm": 0.5468012690544128,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0986,
+      "step": 78
+    },
+    {
+      "epoch": 0.024545595774429083,
+      "grad_norm": 0.18167272210121155,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0497,
+      "step": 79
+    },
+    {
+      "epoch": 0.024856299518409196,
+      "grad_norm": 0.2906138300895691,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0629,
+      "step": 80
+    },
+    {
+      "epoch": 0.025167003262389312,
+      "grad_norm": 0.4465659260749817,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0762,
+      "step": 81
+    },
+    {
+      "epoch": 0.025167003262389312,
+      "eval_loss": 0.09172177314758301,
+      "eval_runtime": 478.5611,
+      "eval_samples_per_second": 5.665,
+      "eval_steps_per_second": 0.708,
+      "step": 81
+    },
+    {
+      "epoch": 0.025477707006369428,
+      "grad_norm": 0.26898109912872314,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0526,
+      "step": 82
+    },
+    {
+      "epoch": 0.02578841075034954,
+      "grad_norm": 0.5038782954216003,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1666,
+      "step": 83
+    },
+    {
+      "epoch": 0.026099114494329657,
+      "grad_norm": 0.2767373025417328,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0521,
+      "step": 84
+    },
+    {
+      "epoch": 0.026409818238309773,
+      "grad_norm": 0.5038904547691345,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0702,
+      "step": 85
+    },
+    {
+      "epoch": 0.026720521982289885,
+      "grad_norm": 0.263021856546402,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0777,
+      "step": 86
+    },
+    {
+      "epoch": 0.02703122572627,
+      "grad_norm": 0.5625424385070801,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0838,
+      "step": 87
+    },
+    {
+      "epoch": 0.027341929470250118,
+      "grad_norm": 0.4216459095478058,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0653,
+      "step": 88
+    },
+    {
+      "epoch": 0.02765263321423023,
+      "grad_norm": 0.3736090660095215,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0643,
+      "step": 89
+    },
+    {
+      "epoch": 0.027963336958210346,
+      "grad_norm": 0.5854941606521606,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1054,
+      "step": 90
+    },
+    {
+      "epoch": 0.027963336958210346,
+      "eval_loss": 0.09043664485216141,
+      "eval_runtime": 478.5777,
+      "eval_samples_per_second": 5.665,
+      "eval_steps_per_second": 0.708,
+      "step": 90
+    },
+    {
+      "epoch": 0.028274040702190462,
+      "grad_norm": 0.2925987243652344,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0793,
+      "step": 91
+    },
+    {
+      "epoch": 0.028584744446170575,
+      "grad_norm": 0.5664364099502563,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0755,
+      "step": 92
+    },
+    {
+      "epoch": 0.02889544819015069,
+      "grad_norm": 0.29245734214782715,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1267,
+      "step": 93
+    },
+    {
+      "epoch": 0.029206151934130807,
+      "grad_norm": 0.45084962248802185,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0548,
+      "step": 94
+    },
+    {
+      "epoch": 0.02951685567811092,
+      "grad_norm": 0.39742884039878845,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0825,
+      "step": 95
+    },
+    {
+      "epoch": 0.029827559422091036,
+      "grad_norm": 0.4094812273979187,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1132,
+      "step": 96
+    },
+    {
+      "epoch": 0.030138263166071152,
+      "grad_norm": 0.5582484006881714,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3011,
+      "step": 97
+    },
+    {
+      "epoch": 0.030448966910051264,
+      "grad_norm": 0.26959139108657837,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0663,
+      "step": 98
+    },
+    {
+      "epoch": 0.03075967065403138,
+      "grad_norm": 0.22900760173797607,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0863,
+      "step": 99
+    },
+    {
+      "epoch": 0.03075967065403138,
+      "eval_loss": 0.09016219526529312,
+      "eval_runtime": 478.5425,
+      "eval_samples_per_second": 5.665,
+      "eval_steps_per_second": 0.708,
+      "step": 99
+    },
+    {
+      "epoch": 0.031070374398011497,
+      "grad_norm": 0.30340513586997986,
+      "learning_rate": 0.0,
+      "loss": 0.0709,
+      "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": 3.407936228425728e+16,
+  "total_flos": 4.5274515111936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null