Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
+oid sha256:d3198af97fd8cfcdad00f14309da038efe5e49694545c548255fddfa9f700511
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354a52bb626af282d7a6ea9338281c3aa9a16fb2e8df97f3200a6858413cf01c
+oid sha256:7af70b7c60c0a548c7f73ac4df9931e509c909f7d83fd36720f72548deb597a0
 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": 0.054910242872228086,
+  "epoch": 0.10982048574445617,
   "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": 24.376,
       "eval_steps_per_second": 12.188,
       "step": 10
+    },
+    {
+      "epoch": 0.06335797254487856,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.08447729672650475,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.08447729672650475,
+      "eval_loss": NaN,
+      "eval_runtime": 4.2138,
+      "eval_samples_per_second": 23.732,
+      "eval_steps_per_second": 11.866,
+      "step": 20
+    },
+    {
+      "epoch": 0.10559662090813093,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 478339931308032.0,
+  "total_flos": 964787319078912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null