Training in progress, step 4080, 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:f9cd9972b8e95a449dd54958ea0393faa9a6d8a91b32f94fc1e21e9bbd9ab026
|
| 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 sha256:67b8e22bb348ac7b9fb20cfdeaa735973e403ee22810dc8ba45fe80fa25ec998
|
| 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 sha256:36631c532a36686fe443b9fdc0327b371df176c5cc539fc0afbc34f12980a165
|
| 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,
|
|
@@ -7334,6 +7334,24 @@
|
|
| 7334 |
"mean_token_accuracy": 0.6469120174646378,
|
| 7335 |
"num_tokens": 14842766.0,
|
| 7336 |
"step": 4070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7337 |
}
|
| 7338 |
],
|
| 7339 |
"logging_steps": 5,
|
|
@@ -7353,7 +7371,7 @@
|
|
| 7353 |
"attributes": {}
|
| 7354 |
}
|
| 7355 |
},
|
| 7356 |
-
"total_flos": 7.
|
| 7357 |
"train_batch_size": 4,
|
| 7358 |
"trial_name": null,
|
| 7359 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7334 |
"mean_token_accuracy": 0.6469120174646378,
|
| 7335 |
"num_tokens": 14842766.0,
|
| 7336 |
"step": 4070
|
| 7337 |
+
},
|
| 7338 |
+
{
|
| 7339 |
+
"epoch": 31.346153846153847,
|
| 7340 |
+
"grad_norm": 0.0,
|
| 7341 |
+
"learning_rate": 2.9630000000000003e-05,
|
| 7342 |
+
"loss": 1.7272,
|
| 7343 |
+
"mean_token_accuracy": 0.6515872448682785,
|
| 7344 |
+
"num_tokens": 14861282.0,
|
| 7345 |
+
"step": 4075
|
| 7346 |
+
},
|
| 7347 |
+
{
|
| 7348 |
+
"epoch": 31.384615384615383,
|
| 7349 |
+
"grad_norm": 0.0,
|
| 7350 |
+
"learning_rate": 2.9605e-05,
|
| 7351 |
+
"loss": 1.6966,
|
| 7352 |
+
"mean_token_accuracy": 0.6624060094356536,
|
| 7353 |
+
"num_tokens": 14879361.0,
|
| 7354 |
+
"step": 4080
|
| 7355 |
}
|
| 7356 |
],
|
| 7357 |
"logging_steps": 5,
|
|
|
|
| 7371 |
"attributes": {}
|
| 7372 |
}
|
| 7373 |
},
|
| 7374 |
+
"total_flos": 7.541342573985792e+17,
|
| 7375 |
"train_batch_size": 4,
|
| 7376 |
"trial_name": null,
|
| 7377 |
"trial_params": null
|