TachyHealthResearch
commited on
Commit
•
30a110a
1
Parent(s):
df7a137
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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee40a63c153af0b9f73825f7f38fef512f1ace91e267526b36cc1f6946bd0795
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63350356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5056f228f865430bfe4e00440c0f8934a8e1fc1e938d3a02996b9d09898a2bb1
|
3 |
size 63350356
|
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 sha256:8bb115e5ab94d968710c7b1278747dfbb15e5fca1a53624a1aa871bb9a0a1c7b
|
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 sha256:479698cf1fa3e8710aea592da04136d35bad3d39e7bddbd54c7d7b87963a2cf4
|
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,
|
@@ -517,13 +517,43 @@
|
|
517 |
"learning_rate": 3.0927835051546395e-05,
|
518 |
"loss": 1.5566,
|
519 |
"step": 85
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
520 |
}
|
521 |
],
|
522 |
"logging_steps": 1,
|
523 |
"max_steps": 100,
|
524 |
"num_train_epochs": 1,
|
525 |
"save_steps": 5,
|
526 |
-
"total_flos":
|
527 |
"trial_name": null,
|
528 |
"trial_params": null
|
529 |
}
|
|
|
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,
|
|
|
517 |
"learning_rate": 3.0927835051546395e-05,
|
518 |
"loss": 1.5566,
|
519 |
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.03,
|
523 |
+
"learning_rate": 2.8865979381443297e-05,
|
524 |
+
"loss": 1.5145,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.03,
|
529 |
+
"learning_rate": 2.6804123711340206e-05,
|
530 |
+
"loss": 1.377,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.04,
|
535 |
+
"learning_rate": 2.4742268041237116e-05,
|
536 |
+
"loss": 1.6574,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.04,
|
541 |
+
"learning_rate": 2.268041237113402e-05,
|
542 |
+
"loss": 1.6581,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.04,
|
547 |
+
"learning_rate": 2.0618556701030927e-05,
|
548 |
+
"loss": 1.872,
|
549 |
+
"step": 90
|
550 |
}
|
551 |
],
|
552 |
"logging_steps": 1,
|
553 |
"max_steps": 100,
|
554 |
"num_train_epochs": 1,
|
555 |
"save_steps": 5,
|
556 |
+
"total_flos": 1.043070722727936e+16,
|
557 |
"trial_name": null,
|
558 |
"trial_params": null
|
559 |
}
|