Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da4ba0b3b0a0060abe31bc5c6fead762f82d90149cf6eecd0b4216b50b9ca27
+oid sha256:7c810e4b0e90c8871150c0ae3ee438ac54f85426a030804b5d63ab2ce887491a
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ebefa66f685e689769adaafd457264ae6777a954ae0a77f34d7684be2682c30
+oid sha256:a6a629bcc4d1cf05d0ed241ade838414811cac61f7bea2bcdb22033b753ca109
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007097038351303399,
+  "epoch": 0.010645557526955098,
   "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": 62.057,
       "eval_steps_per_second": 31.049,
       "step": 26
+    },
+    {
+      "epoch": 0.008188890405350075,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.010645557526955098,
+      "eval_loss": NaN,
+      "eval_runtime": 24.5021,
+      "eval_samples_per_second": 62.974,
+      "eval_steps_per_second": 31.508,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1034985884614656.0,
+  "total_flos": 1552478826921984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null