Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b22d48537f692165a83091e9e8f8e36aeab4aa034b4900c718abec5454ef14b
+oid sha256:3ef6446a670d938f654c662fd31f2dc6b5b99fd959c47bd3130eb7be372fb3da
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee5fc14cb90882735f660cbc4348a9a2576d8224004ff2af3c2e1182bca7483
+oid sha256:58ed156a7fd848f1f7fc3cd09fe962a41e3fcfc536d855dffc5cb2d42590de4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0a9ae08a837d696210720a364c40061c9c8b036f36570a99f11fe3b8d70f51
+oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006645537266128208,
+  "epoch": 0.0013291074532256416,
   "eval_steps": 13,
-  "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": 21.116,
       "eval_steps_per_second": 10.56,
       "step": 13
+    },
+    {
+      "epoch": 0.0010223903486351088,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0013291074532256416,
+      "eval_loss": NaN,
+      "eval_runtime": 195.0362,
+      "eval_samples_per_second": 21.119,
+      "eval_steps_per_second": 10.562,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2067638003957760.0,
+  "total_flos": 4135276007915520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null