Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e71c850cf62da549bc70f46dca63363921700a216a2d89b84791552cefd07a6
+oid sha256:a1fded5f36ea11a7246109519aaecea8e4bda7ffcb30126d1b6503634d7d00f4
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed8c0843a4beca848b9d019f77125d5963e6b5d28890bbd48313e270584ab1c
+oid sha256:a51a564a9acaa6f52f6d5c610defc3027f9872eda07a196dcfa4d35a3357966d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00011492519088355923,
+  "epoch": 0.00014365648860444904,
   "eval_steps": 2,
-  "global_step": 8,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 8.477,
       "eval_steps_per_second": 4.239,
       "step": 8
+    },
+    {
+      "epoch": 0.00012929083974400413,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.00014365648860444904,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00014365648860444904,
+      "eval_loss": NaN,
+      "eval_runtime": 3456.2017,
+      "eval_samples_per_second": 8.48,
+      "eval_steps_per_second": 4.24,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -117,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2967549134241792.0,
+  "total_flos": 3709436417802240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null