TachyHealthResearch
commited on
Commit
·
b7c9c2e
1
Parent(s):
bfa628b
Training in progress, step 90, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37eb76d094dcc7632701d52847f17cebaf3c2d1f89e929bc33829731f32bfcdc
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42545748
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1477bdabaa3322f3b0890056340000fc6c5b3118b05197e45b4be40ddeb5d92
|
3 |
size 42545748
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a547a76271f1c64e2d7367c4322cb2512e489925ea0a7e0f9d1cd2d7ba6973b
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b296677280182a88e75c28cc855364d568a9149408830a5cd922e45719e62ac
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -487,13 +487,73 @@
|
|
487 |
"learning_rate": 4.210526315789474e-05,
|
488 |
"loss": 1.7028,
|
489 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
490 |
}
|
491 |
],
|
492 |
"logging_steps": 1,
|
493 |
"max_steps": 100,
|
494 |
"num_train_epochs": 1,
|
495 |
"save_steps": 10,
|
496 |
-
"total_flos":
|
497 |
"trial_name": null,
|
498 |
"trial_params": null
|
499 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.036,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 90,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
487 |
"learning_rate": 4.210526315789474e-05,
|
488 |
"loss": 1.7028,
|
489 |
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.03,
|
493 |
+
"learning_rate": 4e-05,
|
494 |
+
"loss": 1.5573,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.03,
|
499 |
+
"learning_rate": 3.789473684210527e-05,
|
500 |
+
"loss": 1.7494,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.03,
|
505 |
+
"learning_rate": 3.578947368421053e-05,
|
506 |
+
"loss": 1.4485,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.03,
|
511 |
+
"learning_rate": 3.368421052631579e-05,
|
512 |
+
"loss": 2.087,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.03,
|
517 |
+
"learning_rate": 3.157894736842105e-05,
|
518 |
+
"loss": 1.7953,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.03,
|
523 |
+
"learning_rate": 2.9473684210526314e-05,
|
524 |
+
"loss": 1.6708,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.03,
|
529 |
+
"learning_rate": 2.7368421052631583e-05,
|
530 |
+
"loss": 1.5081,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.04,
|
535 |
+
"learning_rate": 2.5263157894736845e-05,
|
536 |
+
"loss": 1.9174,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.04,
|
541 |
+
"learning_rate": 2.3157894736842107e-05,
|
542 |
+
"loss": 1.8299,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.04,
|
547 |
+
"learning_rate": 2.105263157894737e-05,
|
548 |
+
"loss": 1.9316,
|
549 |
+
"step": 90
|
550 |
}
|
551 |
],
|
552 |
"logging_steps": 1,
|
553 |
"max_steps": 100,
|
554 |
"num_train_epochs": 1,
|
555 |
"save_steps": 10,
|
556 |
+
"total_flos": 5562330342162432.0,
|
557 |
"trial_name": null,
|
558 |
"trial_params": null
|
559 |
}
|