Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58069f8589c361930b02556060f33f8ae7a4eb1d96fafa5d1bd3fa49683c5e2f
+oid sha256:c96e32b039f32c63ecedd4e4254822f50a9a2344ff2aae636216425712ce36ac
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdc04e0a027a5fd1de712f0b8d61671eafe2eaa2dc48a8c5d25276b552cd4c9
+oid sha256:e3cbb26bd13617c3cbc7c7cd82ae290f43209cf4ca66202a5c5cc3e3da0977c9
 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": 0.14395393474088292,
+  "epoch": 0.19193857965451055,
   "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": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.14587332053742802,
+      "grad_norm": NaN,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.14779270633397312,
+      "grad_norm": NaN,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.14971209213051823,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.15163147792706333,
+      "grad_norm": NaN,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.15355086372360843,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.15547024952015356,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.15547024952015356,
+      "eval_loss": NaN,
+      "eval_runtime": 14.3157,
+      "eval_samples_per_second": 30.666,
+      "eval_steps_per_second": 3.842,
+      "step": 81
+    },
+    {
+      "epoch": 0.15738963531669867,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.15930902111324377,
+      "grad_norm": NaN,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.16122840690978887,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.16314779270633398,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.16506717850287908,
+      "grad_norm": NaN,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.16698656429942418,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.1689059500959693,
+      "grad_norm": NaN,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.1708253358925144,
+      "grad_norm": NaN,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.1727447216890595,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1727447216890595,
+      "eval_loss": NaN,
+      "eval_runtime": 14.3057,
+      "eval_samples_per_second": 30.687,
+      "eval_steps_per_second": 3.845,
+      "step": 90
+    },
+    {
+      "epoch": 0.1746641074856046,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.1765834932821497,
+      "grad_norm": NaN,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.1785028790786948,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.18042226487523993,
+      "grad_norm": NaN,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.18234165067178504,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.18426103646833014,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.18618042226487524,
+      "grad_norm": NaN,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.18809980806142035,
+      "grad_norm": NaN,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.19001919385796545,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.19001919385796545,
+      "eval_loss": NaN,
+      "eval_runtime": 14.3187,
+      "eval_samples_per_second": 30.659,
+      "eval_steps_per_second": 3.841,
+      "step": 99
+    },
+    {
+      "epoch": 0.19193857965451055,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "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": 1.45158385434624e+16,
+  "total_flos": 1.93544513912832e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null