Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff33993c83db654924ab85ac1155bf79ecd4ba80222ed0113f3865437c2cd23d
+oid sha256:433ae90ff6972fc8205043e2806796c20fbadd4c29cf520220fed9c4f4ffd4f0
 size 147781268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ded0f3db3370155cf83e972d92995dd98a90bf7b3580e316ce3a6a5e6d81cf
+oid sha256:de9b088334b26e89cbef5f99763bb7bf2ac020cca89428619c13971255ae0713
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02109426499670402,
+  "epoch": 0.026367831245880026,
   "eval_steps": 1,
-  "global_step": 8,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,36 @@
       "eval_samples_per_second": 7.603,
       "eval_steps_per_second": 3.802,
       "step": 8
+    },
+    {
+      "epoch": 0.023731048121292023,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.023731048121292023,
+      "eval_loss": NaN,
+      "eval_runtime": 21.0418,
+      "eval_samples_per_second": 7.604,
+      "eval_steps_per_second": 3.802,
+      "step": 9
+    },
+    {
+      "epoch": 0.026367831245880026,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.026367831245880026,
+      "eval_loss": NaN,
+      "eval_runtime": 21.0573,
+      "eval_samples_per_second": 7.598,
+      "eval_steps_per_second": 3.799,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -141,12 +171,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5196225246658560.0,
+  "total_flos": 6495281558323200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null