Training in progress, step 56500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeb786eb0371dac8116a7c39711597af2ea96f5c356a75a35aabb900ea86e004
+oid sha256:d531d21039250fcca88be6784ba5854c358ac1da74ed24180548bcb969a31db9
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54720773072468bfe6b1b175bb4a94503147088acd010c5df088ca6e512d33f1
+oid sha256:56995fafbb4f8eaa743d86d29f85c2f8acf8ae107f748232a0cc26dad98abf90
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c37864a57f69aff6c21a01aeca96a6c7791b2f6e8eaab3ec45738bea7cf2aa09
+oid sha256:2df41033224e75d7b43473d5191695ba6bc8d55f9a9fe70d63b4403b6a33e45f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7596516454597249,
-  "global_step": 56000,
+  "epoch": 0.7664342494370439,
+  "global_step": 56500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -678,11 +678,17 @@
       "learning_rate": 0.0,
       "loss": 0.0406,
       "step": 56000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0,
+      "loss": 0.0405,
+      "step": 56500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 5.851247946183475e+16,
+  "total_flos": 5.903489365652275e+16,
   "trial_name": null,
   "trial_params": null
 }

runs/Oct10_09-11-38_e244ff9c7972/events.out.tfevents.1665393287.e244ff9c7972.24.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054ba9421841b363a48d15d9eab11202068273044a9b4441bb4b86234187dc64
-size 26472
+oid sha256:2220987cc1b65880278fd830a1a641866ccf62553cd7348560f3724867774a84
+size 26632