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:e1ef62a913535130932f6eb519b62110a3a2609c249a2361068617998278f660
+oid sha256:f1a4265fd00bba5dafbf308ed544d9483b9ac47681c6684c67e954ac4e36e44f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb56c82326936c55f3af0a585088361eeee9743b511b290730b8856949793e90
+oid sha256:20de830373fd0486e66cefec6d6533b9703efcb6aef507d4af340ee49e435525
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97a2e5fdfed828bd2d46f4226a454975be6bbdf4f2d04b3297b8b7dd2d460e6
+oid sha256:82d17984ee8acef4a95ea3c29a0c962322abd10996c9459ecad748ba428de5f5
 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": 0.44776119402985076,
+  "epoch": 0.5970149253731343,
   "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": 6.0745,
       "step": 75
+    },
+    {
+      "epoch": 0.4537313432835821,
+      "grad_norm": 0.2998201847076416,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 6.0431,
+      "step": 76
+    },
+    {
+      "epoch": 0.4597014925373134,
+      "grad_norm": 0.3127894997596741,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 6.0226,
+      "step": 77
+    },
+    {
+      "epoch": 0.46567164179104475,
+      "grad_norm": 0.43001511693000793,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 5.978,
+      "step": 78
+    },
+    {
+      "epoch": 0.4716417910447761,
+      "grad_norm": 0.33651402592658997,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 6.1142,
+      "step": 79
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 0.21707896888256073,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 6.0496,
+      "step": 80
+    },
+    {
+      "epoch": 0.4835820895522388,
+      "grad_norm": 0.35698696970939636,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 6.0289,
+      "step": 81
+    },
+    {
+      "epoch": 0.4835820895522388,
+      "eval_loss": 3.0151987075805664,
+      "eval_runtime": 43.8317,
+      "eval_samples_per_second": 3.217,
+      "eval_steps_per_second": 0.411,
+      "step": 81
+    },
+    {
+      "epoch": 0.48955223880597015,
+      "grad_norm": 0.5543007254600525,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.0474,
+      "step": 82
+    },
+    {
+      "epoch": 0.4955223880597015,
+      "grad_norm": 0.4010198712348938,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 5.8782,
+      "step": 83
+    },
+    {
+      "epoch": 0.5014925373134328,
+      "grad_norm": 0.32788336277008057,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 6.0287,
+      "step": 84
+    },
+    {
+      "epoch": 0.5074626865671642,
+      "grad_norm": 0.5506189465522766,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.9883,
+      "step": 85
+    },
+    {
+      "epoch": 0.5134328358208955,
+      "grad_norm": 0.2949792444705963,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 6.0173,
+      "step": 86
+    },
+    {
+      "epoch": 0.5194029850746269,
+      "grad_norm": 0.4571002423763275,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 6.1268,
+      "step": 87
+    },
+    {
+      "epoch": 0.5253731343283582,
+      "grad_norm": 0.3164324462413788,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 6.09,
+      "step": 88
+    },
+    {
+      "epoch": 0.5313432835820896,
+      "grad_norm": 0.3322482705116272,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 6.1152,
+      "step": 89
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "grad_norm": 0.24083533883094788,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 5.9978,
+      "step": 90
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "eval_loss": 3.0151336193084717,
+      "eval_runtime": 43.8495,
+      "eval_samples_per_second": 3.216,
+      "eval_steps_per_second": 0.41,
+      "step": 90
+    },
+    {
+      "epoch": 0.5432835820895522,
+      "grad_norm": 0.18689143657684326,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 5.9407,
+      "step": 91
+    },
+    {
+      "epoch": 0.5492537313432836,
+      "grad_norm": 0.46981728076934814,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 6.0932,
+      "step": 92
+    },
+    {
+      "epoch": 0.5552238805970149,
+      "grad_norm": 0.6365844011306763,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 6.0243,
+      "step": 93
+    },
+    {
+      "epoch": 0.5611940298507463,
+      "grad_norm": 0.3402203917503357,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 6.0505,
+      "step": 94
+    },
+    {
+      "epoch": 0.5671641791044776,
+      "grad_norm": 0.36457496881484985,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 5.9351,
+      "step": 95
+    },
+    {
+      "epoch": 0.573134328358209,
+      "grad_norm": 0.19878581166267395,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 5.9019,
+      "step": 96
+    },
+    {
+      "epoch": 0.5791044776119403,
+      "grad_norm": 0.3363381028175354,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 6.0841,
+      "step": 97
+    },
+    {
+      "epoch": 0.5850746268656717,
+      "grad_norm": 0.2318965047597885,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 6.0409,
+      "step": 98
+    },
+    {
+      "epoch": 0.591044776119403,
+      "grad_norm": 0.4164699912071228,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 5.9838,
+      "step": 99
+    },
+    {
+      "epoch": 0.591044776119403,
+      "eval_loss": 3.0150856971740723,
+      "eval_runtime": 43.8489,
+      "eval_samples_per_second": 3.216,
+      "eval_steps_per_second": 0.411,
+      "step": 99
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.3236719071865082,
+      "learning_rate": 0.0,
+      "loss": 6.0534,
+      "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": 1.897989119410176e+17,
+  "total_flos": 2.532768089112576e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null