Training in progress, step 490, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b20e3dc241ba7e61559848a4782261510aeb595780c8b6ba37d2e8cd071e73
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d11fc1e3f068586a108c35f0e84046ed075886913c14e8aab2062ed522abebb
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22618160cbfa09502376be3800a7692462b312dee3f727003804d83614555a3d
|
| 3 |
size 14645
|
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 sha256:791bd3b5bf2fe8605f5fb8b3e81e0b70c8390e444ae91052abb3ee7a092dd572
|
| 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": 0.
|
| 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,
|
|
@@ -498,6 +498,16 @@
|
|
| 498 |
"mean_token_accuracy": 0.773382380604744,
|
| 499 |
"num_tokens": 2216186.0,
|
| 500 |
"step": 480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 501 |
}
|
| 502 |
],
|
| 503 |
"logging_steps": 10,
|
|
@@ -517,7 +527,7 @@
|
|
| 517 |
"attributes": {}
|
| 518 |
}
|
| 519 |
},
|
| 520 |
-
"total_flos": 1.
|
| 521 |
"train_batch_size": 4,
|
| 522 |
"trial_name": null,
|
| 523 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.10453333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 498 |
"mean_token_accuracy": 0.773382380604744,
|
| 499 |
"num_tokens": 2216186.0,
|
| 500 |
"step": 480
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"entropy": 0.9513905093073844,
|
| 504 |
+
"epoch": 0.10453333333333334,
|
| 505 |
+
"grad_norm": 0.27456656098365784,
|
| 506 |
+
"learning_rate": 9.989304046961772e-05,
|
| 507 |
+
"loss": 1.0514169692993165,
|
| 508 |
+
"mean_token_accuracy": 0.7602177545428276,
|
| 509 |
+
"num_tokens": 2263172.0,
|
| 510 |
+
"step": 490
|
| 511 |
}
|
| 512 |
],
|
| 513 |
"logging_steps": 10,
|
|
|
|
| 527 |
"attributes": {}
|
| 528 |
}
|
| 529 |
},
|
| 530 |
+
"total_flos": 1.0758801390329856e+16,
|
| 531 |
"train_batch_size": 4,
|
| 532 |
"trial_name": null,
|
| 533 |
"trial_params": null
|