Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f095c7046f286c6f814382f3bac7e029c9fd3ddfeefe3dad128a317eb5d8a7
+oid sha256:b73c53f82c0ee93afc08c341341c8a5a55b4199164c31f828c4c05286fbd204c
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d309c82430719548cd6c375388a5d51ff0105a8118dd1385043c7625a3e340ab
+oid sha256:a9d15f531f56b380ac66e59d49af6e2ec8f06d12d2c05295527e0c18d6113075
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be43866b7a112efbf8125d7bbc11610819a4fb8c7f205bdfffb33dc32734ab8
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02330733513398683,
+  "epoch": 0.024278474097902947,
   "eval_steps": 2,
-  "global_step": 24,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -279,6 +279,13 @@
       "eval_samples_per_second": 8.457,
       "eval_steps_per_second": 8.457,
       "step": 24
+    },
+    {
+      "epoch": 0.024278474097902947,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0457,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -293,12 +300,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5670142822318080.0,
+  "total_flos": 5913645888307200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null