Training in progress, step 4800, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df2e208838caa0a6289675c9590358044e0e119c1ed9f3d1b37bd90679b10249
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09a6a2133adfd57ae6e9d5b505287ef4df9fe32c067ee56b438f532cb8890bec
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:206c7ae40501025094ff9fb1a6e6708863e797e75b45c8e1f41c515f17ee9c79
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 36.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -8630,6 +8630,24 @@
|
|
| 8630 |
"mean_token_accuracy": 0.6497946470975876,
|
| 8631 |
"num_tokens": 17466677.0,
|
| 8632 |
"step": 4790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8633 |
}
|
| 8634 |
],
|
| 8635 |
"logging_steps": 5,
|
|
@@ -8649,7 +8667,7 @@
|
|
| 8649 |
"attributes": {}
|
| 8650 |
}
|
| 8651 |
},
|
| 8652 |
-
"total_flos": 8.
|
| 8653 |
"train_batch_size": 4,
|
| 8654 |
"trial_name": null,
|
| 8655 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8630 |
"mean_token_accuracy": 0.6497946470975876,
|
| 8631 |
"num_tokens": 17466677.0,
|
| 8632 |
"step": 4790
|
| 8633 |
+
},
|
| 8634 |
+
{
|
| 8635 |
+
"epoch": 36.88461538461539,
|
| 8636 |
+
"grad_norm": 0.0,
|
| 8637 |
+
"learning_rate": 2.603e-05,
|
| 8638 |
+
"loss": 1.7532,
|
| 8639 |
+
"mean_token_accuracy": 0.6486219108104706,
|
| 8640 |
+
"num_tokens": 17485904.0,
|
| 8641 |
+
"step": 4795
|
| 8642 |
+
},
|
| 8643 |
+
{
|
| 8644 |
+
"epoch": 36.92307692307692,
|
| 8645 |
+
"grad_norm": 0.0,
|
| 8646 |
+
"learning_rate": 2.6005000000000003e-05,
|
| 8647 |
+
"loss": 1.7336,
|
| 8648 |
+
"mean_token_accuracy": 0.6513243049383164,
|
| 8649 |
+
"num_tokens": 17503928.0,
|
| 8650 |
+
"step": 4800
|
| 8651 |
}
|
| 8652 |
],
|
| 8653 |
"logging_steps": 5,
|
|
|
|
| 8667 |
"attributes": {}
|
| 8668 |
}
|
| 8669 |
},
|
| 8670 |
+
"total_flos": 8.870252577398784e+17,
|
| 8671 |
"train_batch_size": 4,
|
| 8672 |
"trial_name": null,
|
| 8673 |
"trial_params": null
|