Training in progress, step 4270, 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 sha256:6e2eec3216a61270c64ce1c49be5add6649fa12bc9543de3424d923bd8a035f6
|
| 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 sha256:8839eebf179e8eac6e5900e21f12d8d9f1d1238be65091ce1e5372df1a57ba2c
|
| 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 sha256:8d8cd8fe8052f86fdb71fbca670e68b2ccd2cb0475a9d640f4c7e2f117a1dd05
|
| 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": 32.
|
| 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,
|
|
@@ -7676,6 +7676,24 @@
|
|
| 7676 |
"mean_token_accuracy": 0.641147717833519,
|
| 7677 |
"num_tokens": 15538006.0,
|
| 7678 |
"step": 4260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7679 |
}
|
| 7680 |
],
|
| 7681 |
"logging_steps": 5,
|
|
@@ -7695,7 +7713,7 @@
|
|
| 7695 |
"attributes": {}
|
| 7696 |
}
|
| 7697 |
},
|
| 7698 |
-
"total_flos": 7.
|
| 7699 |
"train_batch_size": 4,
|
| 7700 |
"trial_name": null,
|
| 7701 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7676 |
"mean_token_accuracy": 0.641147717833519,
|
| 7677 |
"num_tokens": 15538006.0,
|
| 7678 |
"step": 4260
|
| 7679 |
+
},
|
| 7680 |
+
{
|
| 7681 |
+
"epoch": 32.80769230769231,
|
| 7682 |
+
"grad_norm": 0.0,
|
| 7683 |
+
"learning_rate": 2.868e-05,
|
| 7684 |
+
"loss": 1.6918,
|
| 7685 |
+
"mean_token_accuracy": 0.662942835688591,
|
| 7686 |
+
"num_tokens": 15555826.0,
|
| 7687 |
+
"step": 4265
|
| 7688 |
+
},
|
| 7689 |
+
{
|
| 7690 |
+
"epoch": 32.84615384615385,
|
| 7691 |
+
"grad_norm": 0.0,
|
| 7692 |
+
"learning_rate": 2.8655000000000003e-05,
|
| 7693 |
+
"loss": 1.7834,
|
| 7694 |
+
"mean_token_accuracy": 0.6468859910964966,
|
| 7695 |
+
"num_tokens": 15573396.0,
|
| 7696 |
+
"step": 4270
|
| 7697 |
}
|
| 7698 |
],
|
| 7699 |
"logging_steps": 5,
|
|
|
|
| 7713 |
"attributes": {}
|
| 7714 |
}
|
| 7715 |
},
|
| 7716 |
+
"total_flos": 7.893292429541376e+17,
|
| 7717 |
"train_batch_size": 4,
|
| 7718 |
"trial_name": null,
|
| 7719 |
"trial_params": null
|