Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aed911d9b32a5591a67e2df93476ac4cc4b1c27d8a9c7f22ee4317c10579b75
+oid sha256:3768217573c1658afad5ef321418ab100ca3cf01f01ab905b4c09440048bddc9
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b91eba2ecb8c11f2ba05eeffb946ce79b2d6c10e39a409918596295758d1e604
+oid sha256:663e3c3f170d4fcfce6ba3deb4ce9cfef2f3ad793eddb4ad0bda5ead8da908ac
 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": 0.0018897408874513936,
+  "epoch": 0.0037794817749027872,
   "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": 45.07,
       "eval_steps_per_second": 22.543,
       "step": 10
+    },
+    {
+      "epoch": 0.002180470254751608,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.2943,
+      "step": 15
+    },
+    {
+      "epoch": 0.002907293673002144,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.8638,
+      "step": 20
+    },
+    {
+      "epoch": 0.002907293673002144,
+      "eval_loss": NaN,
+      "eval_runtime": 59.2667,
+      "eval_samples_per_second": 48.881,
+      "eval_steps_per_second": 24.449,
+      "step": 20
+    },
+    {
+      "epoch": 0.00363411709125268,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14510831173632.0,
+  "total_flos": 28484224155648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null