Training in progress, step 2, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcee44b622f8870061561ee7ee58abaf75d1705ac8327344d0854fa7563d749f
+oid sha256:9f6a6ff573525e891f9464bbebe5dcb556bca666f701470d51de91a8f119e247
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363face5e0c4345ae14e796278c5a666be90641fcc445bb7e7b0b6a955dfe136
+oid sha256:5de509cb1d4b95149355ed16ecf55a2f490753b62719a62b1429bd7b3dc36680
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc0702f850359504b0c41d5f4d7d6f89f03a8d466c8e18705ace84bfa7bb075
+oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3076923076923077,
+  "epoch": 0.6153846153846154,
   "eval_steps": 1,
-  "global_step": 1,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15,6 +15,14 @@
       "eval_samples_per_second": 8.446,
       "eval_steps_per_second": 1.408,
       "step": 1
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "eval_loss": NaN,
+      "eval_runtime": 0.1686,
+      "eval_samples_per_second": 35.585,
+      "eval_steps_per_second": 5.931,
+      "step": 2
     }
   ],
   "logging_steps": 3,
@@ -34,7 +42,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 272144730685440.0,
+  "total_flos": 544289461370880.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null