Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6667ce0c575c8e876d70533fd3d44fa002d0923d53924c86e6cb19dfdb2e8cc9
+oid sha256:ba5b54feb9e2cadbc373f013e31cfa852e99c9767c489ae56e54e1fddbabadc8
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4024304f7a0346e1ea2dd1d3e14e932816a39584bd6329811f3108a9687b47f
+oid sha256:a316d0bcb1453bf971180513b89b4690923738c9ed2088d98d69be86637ed6d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011673151750972763,
+  "epoch": 0.01556420233463035,
   "eval_steps": 2,
-  "global_step": 6,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 28.519,
       "eval_steps_per_second": 14.325,
       "step": 6
+    },
+    {
+      "epoch": 0.013618677042801557,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.01556420233463035,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.01556420233463035,
+      "eval_loss": NaN,
+      "eval_runtime": 7.6002,
+      "eval_samples_per_second": 28.552,
+      "eval_steps_per_second": 14.342,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 308810631610368.0,
+  "total_flos": 411747508813824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null