Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8785178ab67973d156e1bf32e0bd7e58b58ed5bbeb60e7d49dea8c6e1fb8bc6b
+oid sha256:d1844fe9ac875a081a307a0a7e1376806e4ef627526fdbb03219a0277cfa11ec
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06befea34ff2bfd28b299135677677cb8125609004f72f75f1e909cf7c3d734a
+oid sha256:4d62592433bc9e3fe59f299eb039b2ed2191a4af8307e04ee9616c8ba5752e35
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21942857142857142,
+  "epoch": 0.22857142857142856,
   "eval_steps": 4,
-  "global_step": 48,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -447,6 +447,20 @@
       "eval_samples_per_second": 22.932,
       "eval_steps_per_second": 11.589,
       "step": 48
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -461,12 +475,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6270090416750592.0,
+  "total_flos": 6531344184115200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null