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:a9b07f2c636b17d2202a117ae11fbb9aaf81f44078df965b607860c275ac5155
+oid sha256:9cb6866ebe0be5c51624c9384f1dd132b5029a83168bad55cab218246ba0af6c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c54816ea7f2c2a0b630c67c291a7441e44f92d0679eb963f3a3c4fbeacd1de
+oid sha256:102640f87036caca3670b52c1d1f733071ad98ffc61cc975f3e51ff19326dd3f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06e459b7c667b4a6e7f8a6a5a204523d051f7ba92ae0b9c5a6c9461a833ce6b
+oid sha256:12d5e215f21fbf0d0fadcba9d9404c63f2d389e7deeb200582435d8a294f7182
 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": 0.02346316283435007,
+  "epoch": 0.03128421711246676,
   "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": 0.4185,
       "step": 75
+    },
+    {
+      "epoch": 0.023776005005474738,
+      "grad_norm": 1.5238317251205444,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4236,
+      "step": 76
+    },
+    {
+      "epoch": 0.024088847176599405,
+      "grad_norm": 1.646121621131897,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.4858,
+      "step": 77
+    },
+    {
+      "epoch": 0.024401689347724072,
+      "grad_norm": 1.8075958490371704,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4913,
+      "step": 78
+    },
+    {
+      "epoch": 0.02471453151884874,
+      "grad_norm": 1.2012605667114258,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3215,
+      "step": 79
+    },
+    {
+      "epoch": 0.025027373689973407,
+      "grad_norm": 1.520753026008606,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3818,
+      "step": 80
+    },
+    {
+      "epoch": 0.025340215861098078,
+      "grad_norm": 1.7736116647720337,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.62,
+      "step": 81
+    },
+    {
+      "epoch": 0.025340215861098078,
+      "eval_loss": 0.41683319211006165,
+      "eval_runtime": 295.3198,
+      "eval_samples_per_second": 9.116,
+      "eval_steps_per_second": 1.141,
+      "step": 81
+    },
+    {
+      "epoch": 0.025653058032222745,
+      "grad_norm": 1.5321831703186035,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3879,
+      "step": 82
+    },
+    {
+      "epoch": 0.025965900203347412,
+      "grad_norm": 1.1673277616500854,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.4108,
+      "step": 83
+    },
+    {
+      "epoch": 0.02627874237447208,
+      "grad_norm": 1.4989150762557983,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5533,
+      "step": 84
+    },
+    {
+      "epoch": 0.026591584545596746,
+      "grad_norm": 1.5603235960006714,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6211,
+      "step": 85
+    },
+    {
+      "epoch": 0.026904426716721414,
+      "grad_norm": 1.4086264371871948,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2919,
+      "step": 86
+    },
+    {
+      "epoch": 0.02721726888784608,
+      "grad_norm": 1.7630650997161865,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.7224,
+      "step": 87
+    },
+    {
+      "epoch": 0.027530111058970748,
+      "grad_norm": 1.5985987186431885,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5151,
+      "step": 88
+    },
+    {
+      "epoch": 0.02784295323009542,
+      "grad_norm": 1.4477020502090454,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.3901,
+      "step": 89
+    },
+    {
+      "epoch": 0.028155795401220086,
+      "grad_norm": 1.2764562368392944,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3503,
+      "step": 90
+    },
+    {
+      "epoch": 0.028155795401220086,
+      "eval_loss": 0.4124401807785034,
+      "eval_runtime": 295.306,
+      "eval_samples_per_second": 9.116,
+      "eval_steps_per_second": 1.141,
+      "step": 90
+    },
+    {
+      "epoch": 0.028468637572344753,
+      "grad_norm": 1.822226643562317,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7625,
+      "step": 91
+    },
+    {
+      "epoch": 0.02878147974346942,
+      "grad_norm": 1.6981431245803833,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.4653,
+      "step": 92
+    },
+    {
+      "epoch": 0.029094321914594087,
+      "grad_norm": 1.470794916152954,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.4396,
+      "step": 93
+    },
+    {
+      "epoch": 0.029407164085718755,
+      "grad_norm": 1.1165651082992554,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2726,
+      "step": 94
+    },
+    {
+      "epoch": 0.02972000625684342,
+      "grad_norm": 1.0978894233703613,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3345,
+      "step": 95
+    },
+    {
+      "epoch": 0.03003284842796809,
+      "grad_norm": 0.906370222568512,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.21,
+      "step": 96
+    },
+    {
+      "epoch": 0.030345690599092756,
+      "grad_norm": 1.5754798650741577,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5051,
+      "step": 97
+    },
+    {
+      "epoch": 0.030658532770217427,
+      "grad_norm": 1.6001464128494263,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4832,
+      "step": 98
+    },
+    {
+      "epoch": 0.030971374941342094,
+      "grad_norm": 1.4036067724227905,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.3839,
+      "step": 99
+    },
+    {
+      "epoch": 0.030971374941342094,
+      "eval_loss": 0.41170284152030945,
+      "eval_runtime": 295.3304,
+      "eval_samples_per_second": 9.115,
+      "eval_steps_per_second": 1.141,
+      "step": 99
+    },
+    {
+      "epoch": 0.03128421711246676,
+      "grad_norm": 1.121339201927185,
+      "learning_rate": 0.0,
+      "loss": 0.3074,
+      "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