Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9cbb0d2f004fe5975a67decf7fc53a11e3766500be5d1095e98e9dfa85fd633
+oid sha256:8534e1ea95a57845a3a49b3d88f91ad50d6673f5641fd2e3d8994dc41604c55d
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e46ed7f51c2a3a3ae3be0a5ed2fae9fb201c81bbc92c8a554135c02f50f5ab9
+oid sha256:5d26e19e9574f263efe695a1a8fce1cdc23c4a87c6721298cac04bec1afdc167
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.052060737527114966,
+  "epoch": 0.05422993492407809,
   "eval_steps": 4,
-  "global_step": 48,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -447,6 +447,20 @@
       "eval_samples_per_second": 7.641,
       "eval_steps_per_second": 3.83,
       "step": 48
+    },
+    {
+      "epoch": 0.05314533622559653,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05422993492407809,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -461,12 +475,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3415246060322816e+16,
+  "total_flos": 1.39742146461696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null