Training in progress, step 5780, 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:c4c1c5638b68129fd46c34d650d5a099c8143f1d20a2d5fc5588f09bf7548b2c
|
| 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 sha256:848d8ef4a4e293d309bd11aed8dff800f05666a851b28d24a6751a5d24e7f304
|
| 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:be74f5315b43319b24876dc96a50baca1a3f81fdb72177ffe23829658c900b4d
|
| 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": 44.
|
| 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,
|
|
@@ -10394,6 +10394,24 @@
|
|
| 10394 |
"mean_token_accuracy": 0.6409606844186783,
|
| 10395 |
"num_tokens": 21041662.0,
|
| 10396 |
"step": 5770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10397 |
}
|
| 10398 |
],
|
| 10399 |
"logging_steps": 5,
|
|
@@ -10413,7 +10431,7 @@
|
|
| 10413 |
"attributes": {}
|
| 10414 |
}
|
| 10415 |
},
|
| 10416 |
-
"total_flos": 1.
|
| 10417 |
"train_batch_size": 4,
|
| 10418 |
"trial_name": null,
|
| 10419 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10394 |
"mean_token_accuracy": 0.6409606844186783,
|
| 10395 |
"num_tokens": 21041662.0,
|
| 10396 |
"step": 5770
|
| 10397 |
+
},
|
| 10398 |
+
{
|
| 10399 |
+
"epoch": 44.42307692307692,
|
| 10400 |
+
"grad_norm": 0.0,
|
| 10401 |
+
"learning_rate": 2.113e-05,
|
| 10402 |
+
"loss": 1.7182,
|
| 10403 |
+
"mean_token_accuracy": 0.6524233877658844,
|
| 10404 |
+
"num_tokens": 21060206.0,
|
| 10405 |
+
"step": 5775
|
| 10406 |
+
},
|
| 10407 |
+
{
|
| 10408 |
+
"epoch": 44.46153846153846,
|
| 10409 |
+
"grad_norm": 0.0,
|
| 10410 |
+
"learning_rate": 2.1105e-05,
|
| 10411 |
+
"loss": 1.7231,
|
| 10412 |
+
"mean_token_accuracy": 0.655006617307663,
|
| 10413 |
+
"num_tokens": 21078736.0,
|
| 10414 |
+
"step": 5780
|
| 10415 |
}
|
| 10416 |
],
|
| 10417 |
"logging_steps": 5,
|
|
|
|
| 10431 |
"attributes": {}
|
| 10432 |
}
|
| 10433 |
},
|
| 10434 |
+
"total_flos": 1.0681412954937754e+18,
|
| 10435 |
"train_batch_size": 4,
|
| 10436 |
"trial_name": null,
|
| 10437 |
"trial_params": null
|