Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a40c39d880cd8741119832272ac9c076eedfd9b1f7f298c1493ba953ca1ebc7
+oid sha256:294fde63636bc3a4eb39062dbc54100433381cbd9cd582167811199794e0fd7f
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2217bddafdf3b6e8eaedd27506a6ce00af88645969bc815dfff9f073da8be14d
+oid sha256:68d0ab2b507d487fe3cdf107a26d6222d2fd30b493db39cc1012490685af18ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42105263157894735,
+  "epoch": 0.8421052631578947,
   "eval_steps": 1,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,22 @@
       "eval_samples_per_second": 7.277,
       "eval_steps_per_second": 3.638,
       "step": 2
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": NaN,
+      "eval_runtime": 0.272,
+      "eval_samples_per_second": 7.353,
+      "eval_steps_per_second": 3.676,
+      "step": 3
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": NaN,
+      "eval_runtime": 0.266,
+      "eval_samples_per_second": 7.519,
+      "eval_steps_per_second": 3.759,
+      "step": 4
     }
   ],
   "logging_steps": 5,
@@ -42,7 +58,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 183706639663104.0,
+  "total_flos": 367413279326208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null