Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d83b3a81042c5a11605afb23f5d896b06df81fa62c421d0021eb32c266bed9
+oid sha256:269771c4ea644209ab53b0582aa151d3e997c80a60624ee287c6e3761e09c62c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7144b0dce529bd6ff66b9941983b581e0ea1f47f188e811ff4fa48d3921f957f
+oid sha256:c5a4d40f9c4bf65078886d54e1cfc54df5ccabb01b6dd112966b8979e806e106
 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": 0.009670820159940488,
+  "epoch": 0.01450623023991073,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,28 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.011158638646085177,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.011158638646085177,
+      "eval_loss": NaN,
+      "eval_runtime": 124.8955,
+      "eval_samples_per_second": 9.064,
+      "eval_steps_per_second": 4.532,
+      "step": 30
+    },
+    {
+      "epoch": 0.01301841175376604,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4855106151383040.0,
+  "total_flos": 7305778780176384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null