Training in progress, step 7050, 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 sha256:3aad40d093380a5e6af7d963a755cfb5f893ce589c461a3dc2c84da52f102b63
|
| 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:efa763a325906e02c1eef1cbe8527e299609baef2deb6cbdf57074ee89d802a9
|
| 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 sha256:14bb8ce1ebbd768068af13e5644eb9e0fbb4c53ab6e058b49b28ab9a4d01405d
|
| 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": 54.
|
| 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,
|
|
@@ -12680,6 +12680,24 @@
|
|
| 12680 |
"mean_token_accuracy": 0.6411665648221969,
|
| 12681 |
"num_tokens": 25675005.0,
|
| 12682 |
"step": 7040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12683 |
}
|
| 12684 |
],
|
| 12685 |
"logging_steps": 5,
|
|
@@ -12699,7 +12717,7 @@
|
|
| 12699 |
"attributes": {}
|
| 12700 |
}
|
| 12701 |
},
|
| 12702 |
-
"total_flos": 1.
|
| 12703 |
"train_batch_size": 4,
|
| 12704 |
"trial_name": null,
|
| 12705 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7050,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12680 |
"mean_token_accuracy": 0.6411665648221969,
|
| 12681 |
"num_tokens": 25675005.0,
|
| 12682 |
"step": 7040
|
| 12683 |
+
},
|
| 12684 |
+
{
|
| 12685 |
+
"epoch": 54.19230769230769,
|
| 12686 |
+
"grad_norm": 0.0,
|
| 12687 |
+
"learning_rate": 1.4779999999999999e-05,
|
| 12688 |
+
"loss": 1.6956,
|
| 12689 |
+
"mean_token_accuracy": 0.6606644123792649,
|
| 12690 |
+
"num_tokens": 25694037.0,
|
| 12691 |
+
"step": 7045
|
| 12692 |
+
},
|
| 12693 |
+
{
|
| 12694 |
+
"epoch": 54.23076923076923,
|
| 12695 |
+
"grad_norm": 0.0,
|
| 12696 |
+
"learning_rate": 1.4755e-05,
|
| 12697 |
+
"loss": 1.7537,
|
| 12698 |
+
"mean_token_accuracy": 0.6480139315128326,
|
| 12699 |
+
"num_tokens": 25712064.0,
|
| 12700 |
+
"step": 7050
|
| 12701 |
}
|
| 12702 |
],
|
| 12703 |
"logging_steps": 5,
|
|
|
|
| 12717 |
"attributes": {}
|
| 12718 |
}
|
| 12719 |
},
|
| 12720 |
+
"total_flos": 1.3036514168291328e+18,
|
| 12721 |
"train_batch_size": 4,
|
| 12722 |
"trial_name": null,
|
| 12723 |
"trial_params": null
|