Training in progress, step 8050, 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:bf5f982b527df6a7d59bc87b7ae321a9e1fd19baf8c1dfd17ac1153dc29ee63c
|
| 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 sha256:62f2648967c20be035190134359e1d2e985d1db7834dbc5c55013a1d5e7ca4ce
|
| 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:b31059b28cb8d5a2f007977a9765b556a59063deb1803aa1203c286652446acf
|
| 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": 61.
|
| 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,
|
|
@@ -14480,6 +14480,24 @@
|
|
| 14480 |
"mean_token_accuracy": 0.6459253072738648,
|
| 14481 |
"num_tokens": 29320675.0,
|
| 14482 |
"step": 8040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14483 |
}
|
| 14484 |
],
|
| 14485 |
"logging_steps": 5,
|
|
@@ -14499,7 +14517,7 @@
|
|
| 14499 |
"attributes": {}
|
| 14500 |
}
|
| 14501 |
},
|
| 14502 |
-
"total_flos": 1.
|
| 14503 |
"train_batch_size": 4,
|
| 14504 |
"trial_name": null,
|
| 14505 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8050,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14480 |
"mean_token_accuracy": 0.6459253072738648,
|
| 14481 |
"num_tokens": 29320675.0,
|
| 14482 |
"step": 8040
|
| 14483 |
+
},
|
| 14484 |
+
{
|
| 14485 |
+
"epoch": 61.88461538461539,
|
| 14486 |
+
"grad_norm": 0.0,
|
| 14487 |
+
"learning_rate": 9.78e-06,
|
| 14488 |
+
"loss": 1.7512,
|
| 14489 |
+
"mean_token_accuracy": 0.6454969674348832,
|
| 14490 |
+
"num_tokens": 29339644.0,
|
| 14491 |
+
"step": 8045
|
| 14492 |
+
},
|
| 14493 |
+
{
|
| 14494 |
+
"epoch": 61.92307692307692,
|
| 14495 |
+
"grad_norm": 0.0,
|
| 14496 |
+
"learning_rate": 9.755e-06,
|
| 14497 |
+
"loss": 1.7042,
|
| 14498 |
+
"mean_token_accuracy": 0.6602411061525345,
|
| 14499 |
+
"num_tokens": 29357996.0,
|
| 14500 |
+
"step": 8050
|
| 14501 |
}
|
| 14502 |
],
|
| 14503 |
"logging_steps": 5,
|
|
|
|
| 14517 |
"attributes": {}
|
| 14518 |
}
|
| 14519 |
},
|
| 14520 |
+
"total_flos": 1.4884260436706918e+18,
|
| 14521 |
"train_batch_size": 4,
|
| 14522 |
"trial_name": null,
|
| 14523 |
"trial_params": null
|