Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5c9c0a64ab8fdbae53dac1dd1f9e56b81ae97f263cf783b5a88524601126b2
+oid sha256:d0f8ed3236c52996a01c25847ddcc1aa015645c3e401b336cf7425a733c6684b
 size 69844690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d873e5981a74ca193df96e36ccebe68055d4a9941f3ec8ce17e5615941b9a7
+oid sha256:9a9ab7db431e6cea4f6f67f645378c70ef004171a9209f8ce85124ff5172a3ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021119324181626188,
+  "epoch": 0.042238648363252376,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 27.728,
       "eval_steps_per_second": 13.864,
       "step": 10
+    },
+    {
+      "epoch": 0.025343189017951427,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.03167898627243928,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.03167898627243928,
+      "eval_loss": NaN,
+      "eval_runtime": 7.2445,
+      "eval_samples_per_second": 27.607,
+      "eval_steps_per_second": 13.804,
+      "step": 15
+    },
+    {
+      "epoch": 0.03801478352692714,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.042238648363252376,
+      "eval_loss": NaN,
+      "eval_runtime": 7.248,
+      "eval_samples_per_second": 27.594,
+      "eval_steps_per_second": 13.797,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 158917617254400.0,
+  "total_flos": 317835234508800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null