Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73e54014ac1fbb8349236bcf98e0fc0d5b402d1214e58acf4d6174107aeb019
+oid sha256:fe6761db302d71b032c9f7d45329ea3f0288ae940e638bcaaf42d7ee0af58561
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449a2143d9fc3f32f546c0dbe0dbea4c0eb0c51c32b15e4c50238f6def3034e8
+oid sha256:b953f866251e427e44ebe6e7ea847b5fd232ef47dc17bde3f2df9f1ccd4c636b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4615384615384617,
+  "epoch": 2.769230769230769,
   "eval_steps": 1,
-  "global_step": 8,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,21 @@
       "eval_samples_per_second": 34.694,
       "eval_steps_per_second": 5.782,
       "step": 8
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 2.769230769230769,
+      "eval_loss": NaN,
+      "eval_runtime": 0.1715,
+      "eval_samples_per_second": 34.979,
+      "eval_steps_per_second": 5.83,
+      "step": 9
     }
   ],
   "logging_steps": 3,
@@ -104,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2092112617144320.0,
+  "total_flos": 2364257347829760.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null