Training in progress, step 28, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c1d6bdd755319f1f434c95c22ec7ff65d2136a02928e38d507f58dc50ed300
+oid sha256:a2195117d41b17e4fe58cca08787f019143407a6dab60695c3c4ba2233a5692f
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7e627a0f75e8e1695b923aa7f2e71fc850c47eaa8c8adc15535761677b7864
+oid sha256:7d476b0b3563b1fa3d4de8be22a666cbc835905a62f1f401aa3aa58a55379251
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
+oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026030368763557483,
+  "epoch": 0.03036876355748373,
   "eval_steps": 4,
-  "global_step": 24,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,42 @@
       "eval_samples_per_second": 7.65,
       "eval_steps_per_second": 3.835,
       "step": 24
+    },
+    {
+      "epoch": 0.027114967462039046,
+      "grad_norm": NaN,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.028199566160520606,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.02928416485900217,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.03036876355748373,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.03036876355748373,
+      "eval_loss": NaN,
+      "eval_runtime": 107.1539,
+      "eval_samples_per_second": 3.63,
+      "eval_steps_per_second": 1.82,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -250,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6707623030161408.0,
+  "total_flos": 7825560201854976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null