Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ca6eb77df6de7a2c08d25f9e16f833e29c3197229f1676e81a6dd80455f6ae
+oid sha256:8b3506f4d8f60ee79343b7e4058edde035f2877849a8d7b1623a3e5077ee983f
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff2db54f3ee1b8fdd9e984bc137cd286e9bf3dae129dcacfac4d71a7c830716
+oid sha256:4efcd12f7fbe33ea22657b65729cf5b73b1738702516516fe01622226329590d
 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": 0.11409764125068568,
+  "epoch": 0.22819528250137136,
   "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": 28.675,
       "eval_steps_per_second": 3.584,
       "step": 10
+    },
+    {
+      "epoch": 0.1755348326933626,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.1755348326933626,
+      "eval_loss": NaN,
+      "eval_runtime": 26.5791,
+      "eval_samples_per_second": 28.895,
+      "eval_steps_per_second": 3.612,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9105490524962816e+16,
+  "total_flos": 3.821098104992563e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null