Training in progress, step 250, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98819538b1e96734af7cdde014f4b9cdb48d90e2a06f1ad31ef8c5e29df34cb4
+oid sha256:467cd00a7dabe6b04105edf2985167f7e3095273281695bddf39762f3e778bf6
 size 128584660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fcce9de0cc1f71342c751f72457aac3b43dcfc73ff0bfc403ea380246d9d7b3
+oid sha256:aafc92b6894a569ec483aa68ec2123c627b5a8b5e36deb2feacd058bf0591342
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4421052631578947,
+  "epoch": 0.5847953216374269,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 22.659,
       "eval_steps_per_second": 11.329,
       "step": 189
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": NaN,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.4678362573099415,
+      "grad_norm": NaN,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": NaN,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.5146198830409356,
+      "grad_norm": NaN,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.5380116959064327,
+      "grad_norm": NaN,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": NaN,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.5847953216374269,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.4764962974990336e+16,
+  "total_flos": 3.2757887533056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null