Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0844fd14e4606b7dc1b8ea679b4b7a63d63588748f22d31f748b3b39e9140e0b
+oid sha256:16cc438bf39dba2c4b7fc6083ccc1a6ce30481dc3acc6d87d99ce1298b5bf467
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f54b3b38477bb452dc3bbe3278736486e816fbb05b324bb5abd5521e55a30c
+oid sha256:e6bc0e7f49a7d59b8ae4a7c0358087a3c90fd0ccfad5e9d2823b3052a953b5e2
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.012664640324214792,
+  "epoch": 0.016886187098953058,
   "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": 0.2374,
       "step": 75
+    },
+    {
+      "epoch": 0.012833502195204323,
+      "grad_norm": 6.92727518081665,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0763,
+      "step": 76
+    },
+    {
+      "epoch": 0.013002364066193853,
+      "grad_norm": 2.045363187789917,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0438,
+      "step": 77
+    },
+    {
+      "epoch": 0.013171225937183385,
+      "grad_norm": 0.5398113131523132,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0111,
+      "step": 78
+    },
+    {
+      "epoch": 0.013340087808172914,
+      "grad_norm": 0.021576276049017906,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0005,
+      "step": 79
+    },
+    {
+      "epoch": 0.013508949679162444,
+      "grad_norm": 2.4949581623077393,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0727,
+      "step": 80
+    },
+    {
+      "epoch": 0.013677811550151976,
+      "grad_norm": 3.859738349914551,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1469,
+      "step": 81
+    },
+    {
+      "epoch": 0.013677811550151976,
+      "eval_loss": 0.055368997156620026,
+      "eval_runtime": 549.2203,
+      "eval_samples_per_second": 9.08,
+      "eval_steps_per_second": 1.136,
+      "step": 81
+    },
+    {
+      "epoch": 0.013846673421141506,
+      "grad_norm": 2.325451135635376,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0345,
+      "step": 82
+    },
+    {
+      "epoch": 0.014015535292131037,
+      "grad_norm": 0.9638977646827698,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0166,
+      "step": 83
+    },
+    {
+      "epoch": 0.014184397163120567,
+      "grad_norm": 0.6836529970169067,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0114,
+      "step": 84
+    },
+    {
+      "epoch": 0.014353259034110099,
+      "grad_norm": 2.1207351684570312,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0357,
+      "step": 85
+    },
+    {
+      "epoch": 0.014522120905099628,
+      "grad_norm": 0.31320345401763916,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.004,
+      "step": 86
+    },
+    {
+      "epoch": 0.014690982776089158,
+      "grad_norm": 2.221935272216797,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.1703,
+      "step": 87
+    },
+    {
+      "epoch": 0.01485984464707869,
+      "grad_norm": 0.486160010099411,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0152,
+      "step": 88
+    },
+    {
+      "epoch": 0.01502870651806822,
+      "grad_norm": 0.8668288588523865,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0133,
+      "step": 89
+    },
+    {
+      "epoch": 0.015197568389057751,
+      "grad_norm": 2.698561429977417,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1563,
+      "step": 90
+    },
+    {
+      "epoch": 0.015197568389057751,
+      "eval_loss": 0.05165484547615051,
+      "eval_runtime": 549.0935,
+      "eval_samples_per_second": 9.082,
+      "eval_steps_per_second": 1.136,
+      "step": 90
+    },
+    {
+      "epoch": 0.015366430260047281,
+      "grad_norm": 1.8739296197891235,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0499,
+      "step": 91
+    },
+    {
+      "epoch": 0.015535292131036813,
+      "grad_norm": 1.749314546585083,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1767,
+      "step": 92
+    },
+    {
+      "epoch": 0.015704154002026342,
+      "grad_norm": 2.652275800704956,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1609,
+      "step": 93
+    },
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 2.8473572731018066,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.348,
+      "step": 94
+    },
+    {
+      "epoch": 0.016041877744005402,
+      "grad_norm": 1.411710500717163,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0292,
+      "step": 95
+    },
+    {
+      "epoch": 0.016210739614994935,
+      "grad_norm": 3.422239065170288,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0503,
+      "step": 96
+    },
+    {
+      "epoch": 0.016379601485984465,
+      "grad_norm": 0.6517059803009033,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0131,
+      "step": 97
+    },
+    {
+      "epoch": 0.016548463356973995,
+      "grad_norm": 1.2050694227218628,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0304,
+      "step": 98
+    },
+    {
+      "epoch": 0.016717325227963525,
+      "grad_norm": 2.157958984375,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0815,
+      "step": 99
+    },
+    {
+      "epoch": 0.016717325227963525,
+      "eval_loss": 0.05151946842670441,
+      "eval_runtime": 549.1548,
+      "eval_samples_per_second": 9.081,
+      "eval_steps_per_second": 1.136,
+      "step": 99
+    },
+    {
+      "epoch": 0.016886187098953058,
+      "grad_norm": 0.8211965560913086,
+      "learning_rate": 0.0,
+      "loss": 0.0152,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null