Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17ce74019d38f2454569f135d5d3b2391350f53b9cf5393cd3945b7879f8faa
+oid sha256:8c91f1fc6f5c82d81486a31017c92e0a577b24d305e0af1b80a3f824d8bf18d7
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ac73ebffc361a29eb6c365a9dad8a79521fe6bef765881cf9ab491bab804d9
+oid sha256:1e718a7530d4a43c65f6a32c4ec06806234526b2416ad18edaa4e2a72b6d99ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04828226555246054,
+  "epoch": 0.07242339832869081,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 18.389,
       "eval_steps_per_second": 9.195,
       "step": 26
+    },
+    {
+      "epoch": 0.055710306406685235,
+      "grad_norm": NaN,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07242339832869081,
+      "eval_loss": NaN,
+      "eval_runtime": 6.209,
+      "eval_samples_per_second": 18.36,
+      "eval_steps_per_second": 9.18,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4273022630363136.0,
+  "total_flos": 6368447189483520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null