Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2285f370b0e0cd30dd9db68212de9a552891be53c2c13b1e1b5abddeaebe9571
+oid sha256:3c0ab04f554c4ffc66075fe987829590185a059d8408702fbfdb2cbc2c5aac59
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2faf290601c46972054a0e77b165b301024ba9b8f17fe3670cab00793296f083
+oid sha256:75c4819a563d6b113ee27811b29d01695e64cb8b5f8dedc522dc0ab4142a4307
 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": 0.10136452241715399,
+  "epoch": 0.1299545159194282,
   "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": 56.483,
       "eval_steps_per_second": 28.415,
       "step": 39
+    },
+    {
+      "epoch": 0.10396361273554255,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.1299545159194282,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.1452,
+      "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": 2009059075031040.0,
+  "total_flos": 2570646454272000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null