Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04542a8a8f4997877cf19de2f2f40075d162e9d03e558b378e1174e5c6d72b24
+oid sha256:2285f370b0e0cd30dd9db68212de9a552891be53c2c13b1e1b5abddeaebe9571
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434330aa91d3168fb439501decd09101b4d4a95add94876d0a7a56280ac3a8af
+oid sha256:2faf290601c46972054a0e77b165b301024ba9b8f17fe3670cab00793296f083
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06757634827810266,
+  "epoch": 0.10136452241715399,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 55.049,
       "eval_steps_per_second": 27.694,
       "step": 26
+    },
+    {
+      "epoch": 0.07797270955165692,
+      "grad_norm": NaN,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.10136452241715399,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8858,
+      "eval_samples_per_second": 56.483,
+      "eval_steps_per_second": 28.415,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1328826474823680.0,
+  "total_flos": 2009059075031040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null