Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77565fb688e625a82712b1757a1187e13ad45dd76171a2b31fafe37eaf3d05d4
+oid sha256:9b54a48a97aae933e2faf1a3c1e75742dc4a9529c75e875ccfda78efc9a4a11f
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00fb6c6886659deb5bb37c3ff91f94b4bebef32a5b5659f8ccec56b94dc6d7a1
+oid sha256:fe811a66d30687e509246a270e8c6f37d3a7b430b53a76fe7519c6dca6d5e76e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08528085280852808,
+  "epoch": 0.17056170561705616,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 46.654,
       "eval_steps_per_second": 5.86,
       "step": 10
+    },
+    {
+      "epoch": 0.13120131201312013,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.13120131201312013,
+      "eval_loss": NaN,
+      "eval_runtime": 22.0176,
+      "eval_samples_per_second": 46.644,
+      "eval_steps_per_second": 5.859,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3703987614253056.0,
+  "total_flos": 7407975228506112.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null