Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef6446a670d938f654c662fd31f2dc6b5b99fd959c47bd3130eb7be372fb3da
+oid sha256:1d1d00962b34e17a50f93dcb472397e3f035895271a4c90999415b1e14287aaa
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ed156a7fd848f1f7fc3cd09fe962a41e3fcfc536d855dffc5cb2d42590de4c
+oid sha256:b8f464a425f07706e30bf8638dd8ea141b3dee643ecebb4338bcd7a3756a09f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
+oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013291074532256416,
+  "epoch": 0.001993661179838462,
   "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": 21.119,
       "eval_steps_per_second": 10.562,
       "step": 26
+    },
+    {
+      "epoch": 0.0015335855229526632,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.001993661179838462,
+      "eval_loss": NaN,
+      "eval_runtime": 195.0267,
+      "eval_samples_per_second": 21.12,
+      "eval_steps_per_second": 10.563,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4135276007915520.0,
+  "total_flos": 6202914011873280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null