Training in progress, step 2, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59554ef6300c6ccc6c65b9fa29da5194ac132d93d368b0e9cb58d57eb8fb60e
+oid sha256:cd736e39e28b1a6481ced19ff1d42ebf42f6e2dd6e7bf4c563abe20214b1f681
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79aaf543e8010ccb504e3285a056c1ee9d3a90b68d20a3510c65a2bfb9b54860
+oid sha256:3a80f2d20a53db546ca755939d12958dca589836d7c8f350c13f668337d6d24e
 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": 0.7619047619047619,
+  "epoch": 1.5238095238095237,
   "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": 0.04,
       "eval_steps_per_second": 0.027,
       "step": 1
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "eval_loss": NaN,
+      "eval_runtime": 0.0488,
+      "eval_samples_per_second": 61.484,
+      "eval_steps_per_second": 40.989,
+      "step": 2
     }
   ],
   "logging_steps": 1,
@@ -36,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 129719303405568.0,
+  "total_flos": 275653519736832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null