Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ff0c88641ada116e9a595261fe0625c4ba13e3bf59cc99ce8f1acc7045d352
+oid sha256:90fa08a5f51c831bf29bcc64ea88f6a98f463ad4c0b4c5c8020e7c21e1ceb051
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5ce39f0bb47059afaf65dec7caddeaabb42171c266b73bffab23578e2fe346
+oid sha256:0ebbaa00a6627a9b6f31f07794cc82c3cdd664f03072179d8e24446779fa4794
 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": 0.11052072263549416,
+  "epoch": 0.16578108395324123,
   "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": 227.221,
       "eval_steps_per_second": 113.61,
       "step": 26
+    },
+    {
+      "epoch": 0.1275239107332625,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.16578108395324123,
+      "eval_loss": NaN,
+      "eval_runtime": 0.4429,
+      "eval_samples_per_second": 225.76,
+      "eval_steps_per_second": 112.88,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 138073532792832.0,
+  "total_flos": 207110299189248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null