Training in progress, step 2, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7c8950c683b27f3b887af369f118f82c791ca70953d0de3c84aaa679b22104
+oid sha256:bae5e8cd45156eba2dbde0e43590603e7f7fe71c69bc5a43ee32cdd68efd6618
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79aaf543e8010ccb504e3285a056c1ee9d3a90b68d20a3510c65a2bfb9b54860
+oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
 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": 0.32,
+  "epoch": 0.64,
   "eval_steps": 1,
-  "global_step": 1,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,21 @@
       "eval_samples_per_second": 0.128,
       "eval_steps_per_second": 0.064,
       "step": 1
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": NaN,
+      "eval_runtime": 0.1924,
+      "eval_samples_per_second": 31.193,
+      "eval_steps_per_second": 15.597,
+      "step": 2
     }
   ],
   "logging_steps": 1,
@@ -41,7 +56,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 697054418436096.0,
+  "total_flos": 1394108836872192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null