Training in progress, step 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dbc3cbb7648f34047d2fbb6fc1eb0094781c51c08275e075ce0ca03052ed4b1
+oid sha256:dd9aaa2b36f73ed02b8fb9ed8679602aa8e102b880942e3d6b6c6c0429d74487
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:f05c00ecbc39ad6d3b8acd20ff5f742532a970f1a2dc6f9d82c9bff99ab0d533
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6274509803921569,
+  "epoch": 0.9411764705882353,
   "eval_steps": 1,
-  "global_step": 2,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,21 @@
       "eval_samples_per_second": 28.409,
       "eval_steps_per_second": 14.204,
       "step": 2
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "eval_loss": NaN,
+      "eval_runtime": 0.2321,
+      "eval_samples_per_second": 25.856,
+      "eval_steps_per_second": 12.928,
+      "step": 3
     }
   ],
   "logging_steps": 1,
@@ -56,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 734826558652416.0,
+  "total_flos": 1102239837978624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null