Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c631f23bb5860cf4eef17638b11e53ba36660a462ffc2bd582233024b2983071
+oid sha256:61ef777d3cf5653eab13fc05ebe02815da4b6a32d0500f707858f99ba52c0fe4
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1be5635e7fe5aed02620b4be3bcb48bec5ddb23cc4a2d0ee067ac7be2b6d243
+oid sha256:0f460a79034f1e3c3842d20a3765feb14ab6e7319ab4dac56475879db4a3c877
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
+oid sha256:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0302679978980557,
+  "epoch": 0.040357330530740934,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 8.266,
       "eval_steps_per_second": 4.135,
       "step": 27
+    },
+    {
+      "epoch": 0.033631108775617445,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001442909649383465,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03699421965317919,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001404372005304598,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.040357330530740934,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.040357330530740934,
+      "eval_loss": NaN,
+      "eval_runtime": 363.2495,
+      "eval_samples_per_second": 8.273,
+      "eval_steps_per_second": 4.138,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.732609275152302e+17,
+  "total_flos": 2.335012715275223e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null