Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5917e9802c6409080f300fce33a5edc706c8ca1bf6e4f53e530ac0e346f9fdf2
+oid sha256:e6592512f3b66d0be05591525897ff53f54682a02dc7a391352a80ae3eb928e8
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02cfb08abee12b17337b98567ba9f28dd70ea9e907b1536d2d444555c87a1e6f
+oid sha256:354fcbfab35beb320321fc72abe28e2ba17d63b820a2c10b34cfe337af85be52
 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": 0.00046272196194111864,
+  "epoch": 0.0006940829429116779,
   "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": 21.336,
       "eval_steps_per_second": 10.668,
       "step": 26
+    },
+    {
+      "epoch": 0.0005339099560859061,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0006940829429116779,
+      "eval_loss": NaN,
+      "eval_runtime": 1107.2845,
+      "eval_samples_per_second": 21.367,
+      "eval_steps_per_second": 10.684,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8250556258713600.0,
+  "total_flos": 1.23758343880704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null