Training in progress, step 7500, 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:bafb20d16b66ccc9addfcfcff0a0d29a789c2e7e92a73081f82c38ae6d455caa
|
| 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:a8c51969b0c705b58945e56ea72f66ba837037687a9a947866b644811e17e694
|
| 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:b44b6a96eeb922776f1702595738066693161592c968666cb5aa9912a6b33e49
|
| 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,
|
|
@@ -13490,6 +13490,24 @@
|
|
| 13490 |
"mean_token_accuracy": 0.6624167144298554,
|
| 13491 |
"num_tokens": 27316540.0,
|
| 13492 |
"step": 7490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13493 |
}
|
| 13494 |
],
|
| 13495 |
"logging_steps": 5,
|
|
@@ -13509,7 +13527,7 @@
|
|
| 13509 |
"attributes": {}
|
| 13510 |
}
|
| 13511 |
},
|
| 13512 |
-
"total_flos": 1.
|
| 13513 |
"train_batch_size": 4,
|
| 13514 |
"trial_name": null,
|
| 13515 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13490 |
"mean_token_accuracy": 0.6624167144298554,
|
| 13491 |
"num_tokens": 27316540.0,
|
| 13492 |
"step": 7490
|
| 13493 |
+
},
|
| 13494 |
+
{
|
| 13495 |
+
"epoch": 57.65384615384615,
|
| 13496 |
+
"grad_norm": 0.0,
|
| 13497 |
+
"learning_rate": 1.253e-05,
|
| 13498 |
+
"loss": 1.6621,
|
| 13499 |
+
"mean_token_accuracy": 0.6645474463701249,
|
| 13500 |
+
"num_tokens": 27336007.0,
|
| 13501 |
+
"step": 7495
|
| 13502 |
+
},
|
| 13503 |
+
{
|
| 13504 |
+
"epoch": 57.69230769230769,
|
| 13505 |
+
"grad_norm": 0.0,
|
| 13506 |
+
"learning_rate": 1.2505e-05,
|
| 13507 |
+
"loss": 1.7167,
|
| 13508 |
+
"mean_token_accuracy": 0.6529757559299469,
|
| 13509 |
+
"num_tokens": 27354439.0,
|
| 13510 |
+
"step": 7500
|
| 13511 |
}
|
| 13512 |
],
|
| 13513 |
"logging_steps": 5,
|
|
|
|
| 13527 |
"attributes": {}
|
| 13528 |
}
|
| 13529 |
},
|
| 13530 |
+
"total_flos": 1.3869429874679808e+18,
|
| 13531 |
"train_batch_size": 4,
|
| 13532 |
"trial_name": null,
|
| 13533 |
"trial_params": null
|