Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb2cf7c036915940b401cd24109a6ea9213269d31f7c88380bb9bb3c11604b1
+oid sha256:839a78f3d56eb96d522de1c032ba268e4cb75061d40e97b43079a3e6bcd42087
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb72697e985b48c26880ec71c5e9554f59988c6ec9d4fc8510f3dca1c8ea3d9
+oid sha256:b5161d8bab6f5dbfdd2caca5425e5ada9a3a4a44a2d50ce2336ccf7bde2962e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009052924791086351,
+  "epoch": 0.01160631383472609,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,20 @@
       "eval_samples_per_second": 84.47,
       "eval_steps_per_second": 42.281,
       "step": 39
+    },
+    {
+      "epoch": 0.009285051067780872,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.01160631383472609,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 3.4753,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 469063755104256.0,
+  "total_flos": 601363788595200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null