Training in progress, step 7530, 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:cea78a0bf613da5eff7a00da685da5afb90e6343859863456e7184af21eaf6c3
|
| 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 sha256:2abf62f332066a796df731d45408c00673c8dd06efef6312284fc8749fe497eb
|
| 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:c0a13f2b28a400546665078c7a8a3b24d3f22b284d3033c755ffb6577e88c745
|
| 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": 57.
|
| 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,
|
|
@@ -13544,6 +13544,24 @@
|
|
| 13544 |
"mean_token_accuracy": 0.6471449792385101,
|
| 13545 |
"num_tokens": 27427046.0,
|
| 13546 |
"step": 7520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13547 |
}
|
| 13548 |
],
|
| 13549 |
"logging_steps": 5,
|
|
@@ -13563,7 +13581,7 @@
|
|
| 13563 |
"attributes": {}
|
| 13564 |
}
|
| 13565 |
},
|
| 13566 |
-
"total_flos": 1.
|
| 13567 |
"train_batch_size": 4,
|
| 13568 |
"trial_name": null,
|
| 13569 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13544 |
"mean_token_accuracy": 0.6471449792385101,
|
| 13545 |
"num_tokens": 27427046.0,
|
| 13546 |
"step": 7520
|
| 13547 |
+
},
|
| 13548 |
+
{
|
| 13549 |
+
"epoch": 57.88461538461539,
|
| 13550 |
+
"grad_norm": 0.0,
|
| 13551 |
+
"learning_rate": 1.238e-05,
|
| 13552 |
+
"loss": 1.7179,
|
| 13553 |
+
"mean_token_accuracy": 0.6572539776563644,
|
| 13554 |
+
"num_tokens": 27445469.0,
|
| 13555 |
+
"step": 7525
|
| 13556 |
+
},
|
| 13557 |
+
{
|
| 13558 |
+
"epoch": 57.92307692307692,
|
| 13559 |
+
"grad_norm": 0.0,
|
| 13560 |
+
"learning_rate": 1.2355e-05,
|
| 13561 |
+
"loss": 1.7317,
|
| 13562 |
+
"mean_token_accuracy": 0.653878676891327,
|
| 13563 |
+
"num_tokens": 27463877.0,
|
| 13564 |
+
"step": 7530
|
| 13565 |
}
|
| 13566 |
],
|
| 13567 |
"logging_steps": 5,
|
|
|
|
| 13581 |
"attributes": {}
|
| 13582 |
}
|
| 13583 |
},
|
| 13584 |
+
"total_flos": 1.392435475694715e+18,
|
| 13585 |
"train_batch_size": 4,
|
| 13586 |
"trial_name": null,
|
| 13587 |
"trial_params": null
|