Training in progress, step 3630, 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:f23193bf545cc35fac9feb847233cc962552ec6d23c1cfe6227dcef357a424b2
|
| 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 sha256:5f0937a0e75044ff035381f4830933f6522edc78fb4000b7e4f05c71d02ec832
|
| 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 sha256:734b968b397a0b955a904805c5414a56f6a72043b725a3686284d8f8156e94f0
|
| 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": 27.
|
| 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,
|
|
@@ -6524,6 +6524,24 @@
|
|
| 6524 |
"mean_token_accuracy": 0.6301412254571914,
|
| 6525 |
"num_tokens": 13200878.0,
|
| 6526 |
"step": 3620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6527 |
}
|
| 6528 |
],
|
| 6529 |
"logging_steps": 5,
|
|
@@ -6543,7 +6561,7 @@
|
|
| 6543 |
"attributes": {}
|
| 6544 |
}
|
| 6545 |
},
|
| 6546 |
-
"total_flos": 6.
|
| 6547 |
"train_batch_size": 4,
|
| 6548 |
"trial_name": null,
|
| 6549 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6524 |
"mean_token_accuracy": 0.6301412254571914,
|
| 6525 |
"num_tokens": 13200878.0,
|
| 6526 |
"step": 3620
|
| 6527 |
+
},
|
| 6528 |
+
{
|
| 6529 |
+
"epoch": 27.884615384615383,
|
| 6530 |
+
"grad_norm": 0.0,
|
| 6531 |
+
"learning_rate": 3.188e-05,
|
| 6532 |
+
"loss": 1.7052,
|
| 6533 |
+
"mean_token_accuracy": 0.6592441231012345,
|
| 6534 |
+
"num_tokens": 13219674.0,
|
| 6535 |
+
"step": 3625
|
| 6536 |
+
},
|
| 6537 |
+
{
|
| 6538 |
+
"epoch": 27.923076923076923,
|
| 6539 |
+
"grad_norm": 0.0,
|
| 6540 |
+
"learning_rate": 3.1855e-05,
|
| 6541 |
+
"loss": 1.7817,
|
| 6542 |
+
"mean_token_accuracy": 0.6449559360742569,
|
| 6543 |
+
"num_tokens": 13238217.0,
|
| 6544 |
+
"step": 3630
|
| 6545 |
}
|
| 6546 |
],
|
| 6547 |
"logging_steps": 5,
|
|
|
|
| 6561 |
"attributes": {}
|
| 6562 |
}
|
| 6563 |
},
|
| 6564 |
+
"total_flos": 6.708255386119373e+17,
|
| 6565 |
"train_batch_size": 4,
|
| 6566 |
"trial_name": null,
|
| 6567 |
"trial_params": null
|