Training in progress, step 10500

last-checkpoint/mlm/pytorch_adapter.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad877319c971a84d0eeec69e3512b4ca3024675ab04ad3dcb8133926540001a
+oid sha256:ab31d3c1e44d96d6aa7dc385bb2a374bb3650411b1f2bbf3a5632cf6d8a364dd
 size 4782029

last-checkpoint/mlm/pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5d50db03d217d34221e09d4b0ca0e7a21ce5c2c24f42346ae1628b69d5bb848
+oid sha256:c5a68f21c96d1017414c75ab9cb39667b15070c234626b171849d4374c8815f2
 size 771377007

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721920b7457ba86cd65256c179e475d2feca931b40c364c76876ce7770b78837
+oid sha256:c879fb2ff43e64a5330a90d7721d2020e0ba4b2bfa608256284bd1443f844131
 size 16297733

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f605e9c95813b0903543e3c40538435b7b08a66dc9897feee50408cb6b0ac2
+oid sha256:b9699ad8a13d39e0088b256bc19bede304b6e109e99940bf7c075c82acfc186a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df137fab96c45f6507c5eb745baef5cab212ab8ddbfb3e5ab618a4a18dc5dee3
+oid sha256:13f27483992a93e2d0e00be6d9edd9ab2fa3162b3b09ab3826e3fa33ba45c5fe
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
- "best_metric": 1.978848934173584,
- "best_model_checkpoint": "./test-mlm/checkpoint-9000",
- "epoch": 7.396449704142012,
- "global_step": 10000,
+ "best_metric": 1.9753360748291016,
+ "best_model_checkpoint": "./test-mlm/checkpoint-10500",
+ "epoch": 7.766272189349112,
+ "global_step": 10500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -306,11 +306,26 @@
  "eval_samples_per_second": 10.62,
  "eval_steps_per_second": 2.127,
  "step": 10000
+ },
+ {
+ "epoch": 7.77,
+ "learning_rate": 2.2337278106508877e-05,
+ "loss": 2.0887,
+ "step": 10500
+ },
+ {
+ "epoch": 7.77,
+ "eval_accuracy": 0.5924927994053703,
+ "eval_loss": 1.9753360748291016,
+ "eval_runtime": 81.7861,
+ "eval_samples_per_second": 10.625,
+ "eval_steps_per_second": 2.128,
+ "step": 10500
  }
  ],
  "max_steps": 13520,
  "num_train_epochs": 10,
- "total_flos": 1.3369336675688448e+16,
+ "total_flos": 1.4038178060648448e+16,
  "trial_name": null,
  "trial_params": null
 }

runs/Mar03_09-29-00_375a4f73e1b6/events.out.tfevents.1677835778.375a4f73e1b6.4551.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6546cc9c2aad4e11e8ab2df7ddede7cf03903f350a89f6c22c8f75467f9c5e3f
-size 14615
+oid sha256:b869a8447d8ff33826cbddda19026ca1771b64cc0c9fba4809c94e5c091d71e3
+size 15095