Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143c28c5deae3fb4128f47506e470c142f96fb77b21e23e121b782bd15e36446
+oid sha256:932932e12b863d4ae6e21f82dc859ebc60a5b7d06df8ca1bdf0cfe63b76fa6ea
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1327cda913b67e19dd1ccf297cd431bd3e0275207422954ff3e554aa8bd74d85
+oid sha256:25f332b86c0ab33d6e324c8c3eefc646f5485b415d2350334c80ab3c90e59680
 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": 0.012938541925852202,
+  "epoch": 0.019407812888778304,
   "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": 28.186,
       "eval_steps_per_second": 14.126,
       "step": 26
+    },
+    {
+      "epoch": 0.014929086837521772,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.019407812888778304,
+      "eval_loss": NaN,
+      "eval_runtime": 14.9775,
+      "eval_samples_per_second": 28.242,
+      "eval_steps_per_second": 14.155,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2828445268574208.0,
+  "total_flos": 4219483925250048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null