Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f368ba2352a06857cd39027a96bcea367b2803e1e886e5302990562b45ff047
+oid sha256:a9722890d0ddbdcbe005ffafefd2aeb4afcc8a35c50083151e33736bf5446794
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b262526425799fb98e2d61312eaae75bdff8a353c8cfff3c328c80589e185b08
+oid sha256:ebf9cae03cc7e63e39c14786cae61472b5c071e76b7d2529c091bfdd68817926
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
+oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0029193801931282283,
+  "epoch": 0.004379070289692342,
   "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": 18.612,
       "eval_steps_per_second": 9.306,
       "step": 26
+    },
+    {
+      "epoch": 0.0033685156074556477,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.004379070289692342,
+      "eval_loss": NaN,
+      "eval_runtime": 201.4479,
+      "eval_samples_per_second": 18.615,
+      "eval_steps_per_second": 9.308,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7817923884220416.0,
+  "total_flos": 1.1767604179894272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null