Training in progress, step 3600, 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:b281feb72ef3e658e7d34c51bec992e994e76057744451e2af897e920eb570b4
|
| 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 sha256:7fecb97158d4e8976dc69588c0bc4b6b2d332eaf575eb3f1b1ee89ef3aaf38b2
|
| 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 sha256:1395f2d8c184ea27dac5a3e732eba1f1627a53a0cd0d8c449ac6f6e2798a86df
|
| 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,
|
|
@@ -6470,6 +6470,24 @@
|
|
| 6470 |
"mean_token_accuracy": 0.6677554935216904,
|
| 6471 |
"num_tokens": 13092135.0,
|
| 6472 |
"step": 3590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6473 |
}
|
| 6474 |
],
|
| 6475 |
"logging_steps": 5,
|
|
@@ -6489,7 +6507,7 @@
|
|
| 6489 |
"attributes": {}
|
| 6490 |
}
|
| 6491 |
},
|
| 6492 |
-
"total_flos": 6.
|
| 6493 |
"train_batch_size": 4,
|
| 6494 |
"trial_name": null,
|
| 6495 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6470 |
"mean_token_accuracy": 0.6677554935216904,
|
| 6471 |
"num_tokens": 13092135.0,
|
| 6472 |
"step": 3590
|
| 6473 |
+
},
|
| 6474 |
+
{
|
| 6475 |
+
"epoch": 27.653846153846153,
|
| 6476 |
+
"grad_norm": 0.0,
|
| 6477 |
+
"learning_rate": 3.2029999999999997e-05,
|
| 6478 |
+
"loss": 1.7139,
|
| 6479 |
+
"mean_token_accuracy": 0.6528209656476974,
|
| 6480 |
+
"num_tokens": 13110720.0,
|
| 6481 |
+
"step": 3595
|
| 6482 |
+
},
|
| 6483 |
+
{
|
| 6484 |
+
"epoch": 27.692307692307693,
|
| 6485 |
+
"grad_norm": 0.0,
|
| 6486 |
+
"learning_rate": 3.2005e-05,
|
| 6487 |
+
"loss": 1.6911,
|
| 6488 |
+
"mean_token_accuracy": 0.6594361692667008,
|
| 6489 |
+
"num_tokens": 13128968.0,
|
| 6490 |
+
"step": 3600
|
| 6491 |
}
|
| 6492 |
],
|
| 6493 |
"logging_steps": 5,
|
|
|
|
| 6507 |
"attributes": {}
|
| 6508 |
}
|
| 6509 |
},
|
| 6510 |
+
"total_flos": 6.652134896880845e+17,
|
| 6511 |
"train_batch_size": 4,
|
| 6512 |
"trial_name": null,
|
| 6513 |
"trial_params": null
|