Training in progress, step 400, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b773ce2de6d7cc50ab369fe688147a42e0e791a508e666bce07706c4b35f10c
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db050a8e740f735f809fc576df4e37f292ec6a5314c77554aae6e4cf4e25267e
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b560efadabac5e38946943c60a5a9026b112488df1175e8c4d33d1ede001047c
|
| 3 |
size 14645
|
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:ca62f923b6bedfedee2b94878f48259e4a79dad81665ba7ca91e99e993ab4fc9
|
| 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": 0.
|
| 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,
|
|
@@ -408,6 +408,16 @@
|
|
| 408 |
"mean_token_accuracy": 0.76050655990839,
|
| 409 |
"num_tokens": 1805002.0,
|
| 410 |
"step": 390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 411 |
}
|
| 412 |
],
|
| 413 |
"logging_steps": 10,
|
|
@@ -427,7 +437,7 @@
|
|
| 427 |
"attributes": {}
|
| 428 |
}
|
| 429 |
},
|
| 430 |
-
"total_flos":
|
| 431 |
"train_batch_size": 4,
|
| 432 |
"trial_name": null,
|
| 433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.08533333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 408 |
"mean_token_accuracy": 0.76050655990839,
|
| 409 |
"num_tokens": 1805002.0,
|
| 410 |
"step": 390
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"entropy": 0.8763241834938527,
|
| 414 |
+
"epoch": 0.08533333333333333,
|
| 415 |
+
"grad_norm": 0.24879010021686554,
|
| 416 |
+
"learning_rate": 9.997064523088384e-05,
|
| 417 |
+
"loss": 0.9313676834106446,
|
| 418 |
+
"mean_token_accuracy": 0.7820899412035942,
|
| 419 |
+
"num_tokens": 1844640.0,
|
| 420 |
+
"step": 400
|
| 421 |
}
|
| 422 |
],
|
| 423 |
"logging_steps": 10,
|
|
|
|
| 437 |
"attributes": {}
|
| 438 |
}
|
| 439 |
},
|
| 440 |
+
"total_flos": 8772071858506752.0,
|
| 441 |
"train_batch_size": 4,
|
| 442 |
"trial_name": null,
|
| 443 |
"trial_params": null
|