Training in progress, step 4090, 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 sha256:930c1ea14bfc2947c3caa63c873578e9aaf201792ce74192b089853653c08c58
|
| 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:ca466bdbd43f4674b8b3728172189757317aa95159436e658d73f25d17d6fee1
|
| 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:a9536753d6a23643c42cfcb5bce879d264c498ff5bea71dac2aa7142044959a3
|
| 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": 31.
|
| 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,
|
|
@@ -7352,6 +7352,24 @@
|
|
| 7352 |
"mean_token_accuracy": 0.6624060094356536,
|
| 7353 |
"num_tokens": 14879361.0,
|
| 7354 |
"step": 4080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7355 |
}
|
| 7356 |
],
|
| 7357 |
"logging_steps": 5,
|
|
@@ -7371,7 +7389,7 @@
|
|
| 7371 |
"attributes": {}
|
| 7372 |
}
|
| 7373 |
},
|
| 7374 |
-
"total_flos": 7.
|
| 7375 |
"train_batch_size": 4,
|
| 7376 |
"trial_name": null,
|
| 7377 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7352 |
"mean_token_accuracy": 0.6624060094356536,
|
| 7353 |
"num_tokens": 14879361.0,
|
| 7354 |
"step": 4080
|
| 7355 |
+
},
|
| 7356 |
+
{
|
| 7357 |
+
"epoch": 31.423076923076923,
|
| 7358 |
+
"grad_norm": 0.0,
|
| 7359 |
+
"learning_rate": 2.958e-05,
|
| 7360 |
+
"loss": 1.735,
|
| 7361 |
+
"mean_token_accuracy": 0.6479102671146393,
|
| 7362 |
+
"num_tokens": 14897412.0,
|
| 7363 |
+
"step": 4085
|
| 7364 |
+
},
|
| 7365 |
+
{
|
| 7366 |
+
"epoch": 31.46153846153846,
|
| 7367 |
+
"grad_norm": 0.0,
|
| 7368 |
+
"learning_rate": 2.9555e-05,
|
| 7369 |
+
"loss": 1.7283,
|
| 7370 |
+
"mean_token_accuracy": 0.6495876848697663,
|
| 7371 |
+
"num_tokens": 14915712.0,
|
| 7372 |
+
"step": 4090
|
| 7373 |
}
|
| 7374 |
],
|
| 7375 |
"logging_steps": 5,
|
|
|
|
| 7389 |
"attributes": {}
|
| 7390 |
}
|
| 7391 |
},
|
| 7392 |
+
"total_flos": 7.55958788568023e+17,
|
| 7393 |
"train_batch_size": 4,
|
| 7394 |
"trial_name": null,
|
| 7395 |
"trial_params": null
|