Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57799aaf1aab16b8eb569779e7dcc5cd1abdc466429f48ad317bbe8f288947db
+oid sha256:5dd013ada97965cbbcadd886f28eab1cfffa60c7b5f9813a303231c7aa904985
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200d8a86ef41acdf01eea96fef00c6f1766f4a479628e82d083c05b86f6ea4b9
+oid sha256:5fd94707a68b93aa762467c38fb2d78c5beeedb7aaa44c317ab4d6648e7860ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180fb2930efffe03d2da3c10543b777c65c99574dc1268b92ac9f51b0f1b7030
+oid sha256:c173f1ea09c6827195593a20783569fe174cf07527de359de93783bfea48b980
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002866698518872432,
+  "epoch": 0.0031852205765249245,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 6.253,
       "eval_steps_per_second": 3.131,
       "step": 9
+    },
+    {
+      "epoch": 0.0031852205765249245,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0005,
+      "loss": 1.3865,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 926431894831104.0,
+  "total_flos": 1029368772034560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null