Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c58066ebd736de7ffaeec97b826c389c9c1b460c83ab9df2b691f05c06561a
+oid sha256:f73e54014ac1fbb8349236bcf98e0fc0d5b402d1214e58acf4d6174107aeb019
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5472f98c2ad9bd4abfb8c409ce5738521e3910aae76db97f4e69ffc71a546bc5
+oid sha256:449a2143d9fc3f32f546c0dbe0dbea4c0eb0c51c32b15e4c50238f6def3034e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d44c0ecfb16f05885a8478afdaa40e988069bb6891bbc6c82185a9b1533b4c7
+oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1538461538461537,
+  "epoch": 2.4615384615384617,
   "eval_steps": 1,
-  "global_step": 7,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,14 @@
       "eval_samples_per_second": 35.549,
       "eval_steps_per_second": 5.925,
       "step": 7
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "eval_loss": NaN,
+      "eval_runtime": 0.1729,
+      "eval_samples_per_second": 34.694,
+      "eval_steps_per_second": 5.782,
+      "step": 8
     }
   ],
   "logging_steps": 3,
@@ -96,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1819967886458880.0,
+  "total_flos": 2092112617144320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null