Training in progress, step 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd736e39e28b1a6481ced19ff1d42ebf42f6e2dd6e7bf4c563abe20214b1f681
+oid sha256:658071d9b2033379dd51189a5f206d13de7dcb53561f16c26873bd709822158a
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bbba064701c6c5641a803b1cc6ad3663ec5a37b46a361f1a3f2ad360548d26
+oid sha256:e481b51734b403b82efa9748869e4b6472a688b83d6d8f6e46fff1ac08014aed
 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": 0.7441860465116279,
+  "epoch": 1.255813953488372,
   "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": 70.831,
       "eval_steps_per_second": 42.498,
       "step": 2
+    },
+    {
+      "epoch": 1.255813953488372,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 1.255813953488372,
+      "eval_loss": NaN,
+      "eval_runtime": 0.0676,
+      "eval_samples_per_second": 73.988,
+      "eval_steps_per_second": 44.393,
+      "step": 3
     }
   ],
   "logging_steps": 1,
@@ -51,12 +66,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 259438606811136.0,
+  "total_flos": 389157910216704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null