Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c205648a743e8c8f6b786638db954bd7b378add5d722af4608f009a0cf0b44dc
+oid sha256:f5983c67fe0fd2352ec8abd0638dfcf09fda574085aabc876819c05463c58fc7
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c47a6bd81caa0a4968692909a347e7c346b9901310c601090825fe9eac93a78
+oid sha256:09ddddfd4db7bc7498164de4d7122ad4755db606e33abfe8f6e66c7f2fc4ef12
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007853814335829101,
+  "epoch": 0.0010471752447772135,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,35 @@
       "eval_samples_per_second": 10.236,
       "eval_steps_per_second": 5.12,
       "step": 30
+    },
+    {
+      "epoch": 0.0008639195769412011,
+      "grad_norm": NaN,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0009424577202994921,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0010209958636577831,
+      "grad_norm": NaN,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0010471752447772135,
+      "eval_loss": NaN,
+      "eval_runtime": 637.7476,
+      "eval_samples_per_second": 6.305,
+      "eval_steps_per_second": 3.153,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -123,12 +152,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3103926459039744.0,
+  "total_flos": 4329160587608064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null