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 sha256:4ba0a0a9a491cfd6a4fcbfc4291dfd213ae2188f2559dea22d095989a4c7a7be
+oid sha256:9bde1fd16616f9afdbede8aed8bda89c45bbed4733e92ba2f0699b31107c7ae6
 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": 0.00011005733563889342,
+  "epoch": 0.00022011467127778684,
   "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": 22.652,
       "eval_steps_per_second": 11.326,
       "step": 10
+    },
+    {
+      "epoch": 0.0001269892334294924,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.00016931897790598986,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.00016931897790598986,
+      "eval_loss": NaN,
+      "eval_runtime": 2275.7667,
+      "eval_samples_per_second": 21.854,
+      "eval_steps_per_second": 10.927,
+      "step": 20
+    },
+    {
+      "epoch": 0.00021164872238248734,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 462125018382336.0,
+  "total_flos": 891820210913280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null