Training in progress, step 9120, 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 sha256:17333d38cda4976d525ea115bfe93f780af889988c5f26f0441936e654ef0425
|
| 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 sha256:67b8820954d7630005f868abeaabd668ae58068bbd6f98e0c0df08e3abf217af
|
| 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 sha256:53c06b925abc7a89c6cf1893682bf81ebc30d0d3a28e8cf131e0ad8b7b7547f4
|
| 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": 70.
|
| 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,
|
|
@@ -16406,6 +16406,24 @@
|
|
| 16406 |
"mean_token_accuracy": 0.6699670910835266,
|
| 16407 |
"num_tokens": 33224500.0,
|
| 16408 |
"step": 9110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16409 |
}
|
| 16410 |
],
|
| 16411 |
"logging_steps": 5,
|
|
@@ -16425,7 +16443,7 @@
|
|
| 16425 |
"attributes": {}
|
| 16426 |
}
|
| 16427 |
},
|
| 16428 |
-
"total_flos": 1.
|
| 16429 |
"train_batch_size": 4,
|
| 16430 |
"trial_name": null,
|
| 16431 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16406 |
"mean_token_accuracy": 0.6699670910835266,
|
| 16407 |
"num_tokens": 33224500.0,
|
| 16408 |
"step": 9110
|
| 16409 |
+
},
|
| 16410 |
+
{
|
| 16411 |
+
"epoch": 70.11538461538461,
|
| 16412 |
+
"grad_norm": 0.0,
|
| 16413 |
+
"learning_rate": 4.43e-06,
|
| 16414 |
+
"loss": 1.7034,
|
| 16415 |
+
"mean_token_accuracy": 0.6562402963638305,
|
| 16416 |
+
"num_tokens": 33243151.0,
|
| 16417 |
+
"step": 9115
|
| 16418 |
+
},
|
| 16419 |
+
{
|
| 16420 |
+
"epoch": 70.15384615384616,
|
| 16421 |
+
"grad_norm": 0.0,
|
| 16422 |
+
"learning_rate": 4.405e-06,
|
| 16423 |
+
"loss": 1.7118,
|
| 16424 |
+
"mean_token_accuracy": 0.6556406348943711,
|
| 16425 |
+
"num_tokens": 33261667.0,
|
| 16426 |
+
"step": 9120
|
| 16427 |
}
|
| 16428 |
],
|
| 16429 |
"logging_steps": 5,
|
|
|
|
| 16443 |
"attributes": {}
|
| 16444 |
}
|
| 16445 |
},
|
| 16446 |
+
"total_flos": 1.6866159205780685e+18,
|
| 16447 |
"train_batch_size": 4,
|
| 16448 |
"trial_name": null,
|
| 16449 |
"trial_params": null
|