Training in progress, step 270, 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 sha256:58e302b8fb6a075eb20f7b9083232a17402df3ff65ecc1702a0bec5090adaeb0
|
| 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 sha256:9c0a2ffc3d4c3fa38a7308c059b113e7b60dc4e7f693a222b81785af7d8924e7
|
| 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 sha256:3932e9ddf5c061466628c07b6f6fceab5bb9d954dac79e17f54bb3b3e564b499
|
| 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": 2.
|
| 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,
|
|
@@ -476,6 +476,24 @@
|
|
| 476 |
"mean_token_accuracy": 0.6733784437179565,
|
| 477 |
"num_tokens": 948210.0,
|
| 478 |
"step": 260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 479 |
}
|
| 480 |
],
|
| 481 |
"logging_steps": 5,
|
|
@@ -495,7 +513,7 @@
|
|
| 495 |
"attributes": {}
|
| 496 |
}
|
| 497 |
},
|
| 498 |
-
"total_flos":
|
| 499 |
"train_batch_size": 4,
|
| 500 |
"trial_name": null,
|
| 501 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 476 |
"mean_token_accuracy": 0.6733784437179565,
|
| 477 |
"num_tokens": 948210.0,
|
| 478 |
"step": 260
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.0384615384615383,
|
| 482 |
+
"grad_norm": 0.0,
|
| 483 |
+
"learning_rate": 4.868e-05,
|
| 484 |
+
"loss": 1.74,
|
| 485 |
+
"mean_token_accuracy": 0.6532588005065918,
|
| 486 |
+
"num_tokens": 966435.0,
|
| 487 |
+
"step": 265
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.076923076923077,
|
| 491 |
+
"grad_norm": 0.0,
|
| 492 |
+
"learning_rate": 4.8655e-05,
|
| 493 |
+
"loss": 1.6645,
|
| 494 |
+
"mean_token_accuracy": 0.6623793184757233,
|
| 495 |
+
"num_tokens": 985701.0,
|
| 496 |
+
"step": 270
|
| 497 |
}
|
| 498 |
],
|
| 499 |
"logging_steps": 5,
|
|
|
|
| 513 |
"attributes": {}
|
| 514 |
}
|
| 515 |
},
|
| 516 |
+
"total_flos": 5.003353188827136e+16,
|
| 517 |
"train_batch_size": 4,
|
| 518 |
"trial_name": null,
|
| 519 |
"trial_params": null
|