Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5714c165fdb2d6f6d088918875c58f2936d78f0e34147c54b936a4908291e999
+oid sha256:da960b47b20c222e51835cb1d263885a19a25592edab5a659dd8b6fa724fb066
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5e3d3394f67bbd9143f5e7e099cb750cf5ca42b6126b8e1d7d155d82d549ca
+oid sha256:171da188d8ff036fed8601d089ec6b39009a363e407a262b4674e6e87c2b3278
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.96,
+  "epoch": 1.28,
   "eval_steps": 1,
-  "global_step": 3,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,21 @@
       "eval_samples_per_second": 19.321,
       "eval_steps_per_second": 9.66,
       "step": 3
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": NaN,
+      "eval_runtime": 0.3107,
+      "eval_samples_per_second": 19.31,
+      "eval_steps_per_second": 9.655,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -66,12 +81,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 2936183243931648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null