Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5611d10b1dc80593a4bdac7adf240fe7ec3afb8b0341077ac9b221743431d240
+oid sha256:1defbca4043484cb392603e118480c2260be0a971572b683cb4bc0aab7c0d9cc
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c8b900649e3a89c1fce9528aed431e4557d641a9f9d733e5c5a569fff76173
+oid sha256:877d81a96b676d84ec02e1a014cb419a88765bda6712204625f964784cbbe247
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00025046767010277,
+  "epoch": 0.00031308458762846253,
   "eval_steps": 2,
-  "global_step": 8,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 4.116,
       "eval_steps_per_second": 4.116,
       "step": 8
+    },
+    {
+      "epoch": 0.0002817761288656163,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.00031308458762846253,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00031308458762846253,
+      "eval_loss": NaN,
+      "eval_runtime": 3420.2031,
+      "eval_samples_per_second": 3.932,
+      "eval_steps_per_second": 3.932,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -122,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5625035989450752.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null