Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2de700abee18cc74db321ece69444250660040db4c9d2d79dba989035f4c8d
+oid sha256:d51c8aac43a16ae0e18194fd87627e582896a0c12c93331bf810c77a8ba881ff
 size 458278

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0aaedb551c4ed6d1a681a74f25d0e7f09df1298892466b2d9d6f1f8889fb30
+oid sha256:3b6aa6d92613d8ec55613881281a6c881897813d14e7c601a64ba4f3be3d2a35
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04134762633996937,
+  "epoch": 0.045941807044410414,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 428.825,
       "eval_steps_per_second": 53.668,
       "step": 81
+    },
+    {
+      "epoch": 0.042879019908116385,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.0444104134762634,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.045941807044410414,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.045941807044410414,
+      "eval_loss": NaN,
+      "eval_runtime": 7.7362,
+      "eval_samples_per_second": 426.566,
+      "eval_steps_per_second": 53.385,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 23038284791808.0,
+  "total_flos": 25669697273856.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null