Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821d2ce339b19d97ea8628afe64a5d4514be9fc28ad41de38585a5369b8b5e09
+oid sha256:fbd0b9ec022541f07ff1009a810146baa197aed747187e27d7269255c27f657f
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0f9037f48f7cf42040857e4a42197433a0487867c3ffe08f41429048719150
+oid sha256:ce43c1c6a1d57b3b200cbf8caf65e2a35eac403d7147012b79984e463c83e316
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0405616224648986,
+  "epoch": 0.0811232449297972,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 9.44,
       "eval_steps_per_second": 4.755,
       "step": 10
+    },
+    {
+      "epoch": 0.046801872074883,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.062402496099843996,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.062402496099843996,
+      "eval_loss": NaN,
+      "eval_runtime": 14.3506,
+      "eval_samples_per_second": 9.407,
+      "eval_steps_per_second": 4.738,
+      "step": 20
+    },
+    {
+      "epoch": 0.078003120124805,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4481097916219392.0,
+  "total_flos": 8962195832438784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null