Training in progress, step 280, 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 sha256:5598eaf711e1be213d404d0dc9f8634a9620b0da33fcd0de7beddc8fc8ae475c
|
| 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:aaa66e36052996c1ab96f973fe1a57569323e5bf9bf029a78908acc754c93082
|
| 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:d4a30c5fe2c89022a89e2968eeb7bb0db86488fccc9757cf0fd90869d3d9581f
|
| 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,
|
|
@@ -494,6 +494,24 @@
|
|
| 494 |
"mean_token_accuracy": 0.6623793184757233,
|
| 495 |
"num_tokens": 985701.0,
|
| 496 |
"step": 270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 497 |
}
|
| 498 |
],
|
| 499 |
"logging_steps": 5,
|
|
@@ -513,7 +531,7 @@
|
|
| 513 |
"attributes": {}
|
| 514 |
}
|
| 515 |
},
|
| 516 |
-
"total_flos": 5.
|
| 517 |
"train_batch_size": 4,
|
| 518 |
"trial_name": null,
|
| 519 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.1538461538461537,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 494 |
"mean_token_accuracy": 0.6623793184757233,
|
| 495 |
"num_tokens": 985701.0,
|
| 496 |
"step": 270
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.1153846153846154,
|
| 500 |
+
"grad_norm": 0.0,
|
| 501 |
+
"learning_rate": 4.863e-05,
|
| 502 |
+
"loss": 1.7274,
|
| 503 |
+
"mean_token_accuracy": 0.6545837461948395,
|
| 504 |
+
"num_tokens": 1004078.0,
|
| 505 |
+
"step": 275
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.1538461538461537,
|
| 509 |
+
"grad_norm": 0.0,
|
| 510 |
+
"learning_rate": 4.8605e-05,
|
| 511 |
+
"loss": 1.7044,
|
| 512 |
+
"mean_token_accuracy": 0.6571849673986435,
|
| 513 |
+
"num_tokens": 1023219.0,
|
| 514 |
+
"step": 280
|
| 515 |
}
|
| 516 |
],
|
| 517 |
"logging_steps": 5,
|
|
|
|
| 531 |
"attributes": {}
|
| 532 |
}
|
| 533 |
},
|
| 534 |
+
"total_flos": 5.19176052375552e+16,
|
| 535 |
"train_batch_size": 4,
|
| 536 |
"trial_name": null,
|
| 537 |
"trial_params": null
|