Training in progress, step 4110, 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:a71538980f66b7ec1a5638c38eaa575b40ea7d0dc4f01bb3dec8d76046c38342
|
| 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 sha256:56d049bce2fbb09b16bd5fe568366b4ec69bf2554127bd4c6266fc475d1a3128
|
| 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 sha256:54bb4839b81cd6228f73a4a8e1fcba5976485414762f1cec5806655f27c191f5
|
| 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": 31.
|
| 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,
|
|
@@ -7388,6 +7388,24 @@
|
|
| 7388 |
"mean_token_accuracy": 0.6539542943239212,
|
| 7389 |
"num_tokens": 14952726.0,
|
| 7390 |
"step": 4100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7391 |
}
|
| 7392 |
],
|
| 7393 |
"logging_steps": 5,
|
|
@@ -7407,7 +7425,7 @@
|
|
| 7407 |
"attributes": {}
|
| 7408 |
}
|
| 7409 |
},
|
| 7410 |
-
"total_flos": 7.
|
| 7411 |
"train_batch_size": 4,
|
| 7412 |
"trial_name": null,
|
| 7413 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7388 |
"mean_token_accuracy": 0.6539542943239212,
|
| 7389 |
"num_tokens": 14952726.0,
|
| 7390 |
"step": 4100
|
| 7391 |
+
},
|
| 7392 |
+
{
|
| 7393 |
+
"epoch": 31.576923076923077,
|
| 7394 |
+
"grad_norm": 0.0,
|
| 7395 |
+
"learning_rate": 2.9480000000000002e-05,
|
| 7396 |
+
"loss": 1.7294,
|
| 7397 |
+
"mean_token_accuracy": 0.6499251574277878,
|
| 7398 |
+
"num_tokens": 14971349.0,
|
| 7399 |
+
"step": 4105
|
| 7400 |
+
},
|
| 7401 |
+
{
|
| 7402 |
+
"epoch": 31.615384615384617,
|
| 7403 |
+
"grad_norm": 0.0,
|
| 7404 |
+
"learning_rate": 2.9455e-05,
|
| 7405 |
+
"loss": 1.7617,
|
| 7406 |
+
"mean_token_accuracy": 0.6461383640766144,
|
| 7407 |
+
"num_tokens": 14989504.0,
|
| 7408 |
+
"step": 4110
|
| 7409 |
}
|
| 7410 |
],
|
| 7411 |
"logging_steps": 5,
|
|
|
|
| 7425 |
"attributes": {}
|
| 7426 |
}
|
| 7427 |
},
|
| 7428 |
+
"total_flos": 7.597150268306227e+17,
|
| 7429 |
"train_batch_size": 4,
|
| 7430 |
"trial_name": null,
|
| 7431 |
"trial_params": null
|