Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290f1d689f9a2aeeaf83c0d12c42534ae1e3953d2beff34eb7c9cd64074a4e9e
+oid sha256:4c08cb21cb8cfb1c88563137b9043e7aae7c4502fa94f039ffa090d050b71951
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29accfb5adac83d5b9df422d9bb143810bbb3a15382228817b7ba29703dee92
+oid sha256:8b0e6a792a0b5f599b8363ed7c7bf5f49ee21b84ae03dbb82ab991dd4ef75de6
 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": 0.01117078410311493,
+  "epoch": 0.02234156820622986,
   "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": 5.053,
       "eval_steps_per_second": 2.526,
       "step": 10
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": NaN,
+      "eval_runtime": 97.0305,
+      "eval_samples_per_second": 5.05,
+      "eval_steps_per_second": 2.525,
+      "step": 20
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3707722751016960.0,
+  "total_flos": 7415445502033920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null