Training in progress, step 81, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b364129139d8e6902584af483c8a6742af34470beb4619207a854c02cb50de
+oid sha256:59587431aa0755f4eeae607a90ff6f85242a5296d66e6f36e71e31abdeda445e
 size 1279641042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5087e6b9e926b05ecc9b87a4d75f8422e9b3841b8250b18515e99b88368e50
+oid sha256:bbd9014e306facc51ff6aa9e745c7ecb4955c0471ad648ba8c7f9b78a1828521
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.061068702290076333,
+  "epoch": 0.06870229007633588,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 13.616,
       "eval_steps_per_second": 3.414,
       "step": 72
+    },
+    {
+      "epoch": 0.06361323155216285,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.06615776081424936,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.06870229007633588,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.06870229007633588,
+      "eval_loss": NaN,
+      "eval_runtime": 72.9323,
+      "eval_samples_per_second": 13.615,
+      "eval_steps_per_second": 3.414,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.789787686443418e+16,
+  "total_flos": 5.388511147248845e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null