Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c4b1b1022476a667133913254b988ff83885ee227e03c4f7dc228d6177ea10
+oid sha256:59d717237662ebe0e3eb1443064fadff6463b9604761d84bf438962c3ddf5958
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9013a79d67ddcb6d9d32a487da5e5f304f6d20307ca065e25b775a6da9df05
+oid sha256:0b8655a5a9160ec43d953c1802967f30ec2e3cb247ed234027cc1d2b343c4362
 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": 0.17869415807560138,
+  "epoch": 0.35738831615120276,
   "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": 29.828,
       "eval_steps_per_second": 3.774,
       "step": 10
+    },
+    {
+      "epoch": 0.27491408934707906,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.27491408934707906,
+      "eval_loss": NaN,
+      "eval_runtime": 16.3568,
+      "eval_samples_per_second": 29.957,
+      "eval_steps_per_second": 3.79,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1545018003095552e+16,
+  "total_flos": 2.347919391640781e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null