Training in progress, step 11, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298134d4c8dffddc6bd0ca2789f713703e093aba625780c0df959e434b690184
+oid sha256:5eae9b60084574f9331adbe4747545ca28607ee03a912dabed33af0ef030912a
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b138580fd1455e247dfc8e822f1b487e5eb2e008976b6c875eb6f11c4c9bc8e
+oid sha256:5bcc4d2409840b1b127474e2ae7677766647f6c0542890047c33ededad636de4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:4968f693466c40cb971e90a0117e2a9be84fd1e9f8d5d00ed1cc54675e5c78ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8372093023255814,
+  "epoch": 1.069767441860465,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 11,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,13 @@
       "eval_samples_per_second": 16.838,
       "eval_steps_per_second": 10.103,
       "step": 9
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 5,
@@ -60,12 +67,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1568372441481216.0,
+  "total_flos": 1916899650699264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null