Spaces:
Paused
Paused
Upload 7 files (#1)
Browse files- Upload 7 files (c42519fcb58682c3574889de020f0d6eca13ddcb)
Co-authored-by: Nádila da Silva de Azevedo <[email protected]>
- checkpoint-50/optimizer.pt +3 -0
- checkpoint-50/pytorch_model.bin +3 -0
- checkpoint-50/rng_state.pth +3 -0
- checkpoint-50/scaler.pt +3 -0
- checkpoint-50/scheduler.pt +3 -0
- checkpoint-50/trainer_state.json +36 -0
- checkpoint-50/training_args.bin +3 -0
checkpoint-50/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bedeef904c7d541999b3e34b5ee347a5fcc36f929292675c66c80c53f9d67f29
|
| 3 |
+
size 143357381
|
checkpoint-50/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48026f969f2e5b30ea45477ee02ecfa74dbd8598f58bef934f44cc49c46d7816
|
| 3 |
+
size 71703053
|
checkpoint-50/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be5fca5b7173138e11ada6b23265c1d171e6158b7b473891b903109e95b0e9a9
|
| 3 |
+
size 14575
|
checkpoint-50/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:236bb8f9013eba8043ce754790a6effa495ab32eee8780a6f1e845063b069a9b
|
| 3 |
+
size 557
|
checkpoint-50/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cd52e80acfa47edb0a1496625e1b04281631053c1e0dd6f9593fdd29b907a20
|
| 3 |
+
size 627
|
checkpoint-50/trainer_state.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.083932638168335,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/7b/checkpoint-50",
|
| 4 |
+
"epoch": 0.08800880088008801,
|
| 5 |
+
"global_step": 50,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 13 |
+
"loss": 2.0006,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 5.85e-05,
|
| 19 |
+
"loss": 1.6054,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"eval_loss": 1.083932638168335,
|
| 25 |
+
"eval_runtime": 1647.9375,
|
| 26 |
+
"eval_samples_per_second": 9.456,
|
| 27 |
+
"eval_steps_per_second": 1.182,
|
| 28 |
+
"step": 50
|
| 29 |
+
}
|
| 30 |
+
],
|
| 31 |
+
"max_steps": 568,
|
| 32 |
+
"num_train_epochs": 1,
|
| 33 |
+
"total_flos": 6.52559141044224e+16,
|
| 34 |
+
"trial_name": null,
|
| 35 |
+
"trial_params": null
|
| 36 |
+
}
|
checkpoint-50/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e643caa7ea58e2f3a7ae5696d3533277c2a20873ea2d495263cc2a8ab48f64
|
| 3 |
+
size 3579
|