Upload folder using huggingface_hub
Browse files- README.md +0 -3
- tb_logs.parquet +3 -0
- version_8/events.out.tfevents.1741137579.gpu-q-76.876292.0 +3 -0
- version_8/hparams.yaml +31 -0
README.md
CHANGED
@@ -1,6 +1,3 @@
|
|
1 |
-
---
|
2 |
-
{}
|
3 |
-
---
|
4 |
## Experiment Configuration
|
5 |
```yaml
|
6 |
callbacks:
|
|
|
|
|
|
|
|
|
1 |
## Experiment Configuration
|
2 |
```yaml
|
3 |
callbacks:
|
tb_logs.parquet
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22a65a0c6dc9ca4a5ba7033e207c5136041fd65c1ed80429593bceae08d338d3
|
3 |
+
size 316054
|
version_8/events.out.tfevents.1741137579.gpu-q-76.876292.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f6009b6c8bd0a033d3a7678418cfc340c6f2a56cb88218a114ceeb5d747a579
|
3 |
+
size 4781371
|
version_8/hparams.yaml
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
dataloader_config: !!python/object:src.datamodule.DataloaderConfig
|
2 |
+
batch_size: 16
|
3 |
+
drop_last: false
|
4 |
+
eval_batch_size: 64
|
5 |
+
multiprocessing_context: null
|
6 |
+
num_workers: 12
|
7 |
+
persistent_workers: false
|
8 |
+
pin_memory: true
|
9 |
+
prefetch_factor: 2
|
10 |
+
shuffle: true
|
11 |
+
eod_token_id: 0
|
12 |
+
max_position_embeddings: 2048
|
13 |
+
optim_config: !!python/object:src.module.OptimCofig
|
14 |
+
keller_kwargs: {}
|
15 |
+
lr: 0.0006
|
16 |
+
num_warmup_steps: 2000
|
17 |
+
optim_kwargs:
|
18 |
+
betas:
|
19 |
+
- 0.9
|
20 |
+
- 0.95
|
21 |
+
eps: 1.0e-08
|
22 |
+
fused: true
|
23 |
+
optim_name: adamw
|
24 |
+
scheduler_kwargs:
|
25 |
+
min_lr_ratio: 0.01
|
26 |
+
num_decay_steps: 2000
|
27 |
+
num_stable_steps: 46000
|
28 |
+
scheduler_name: warmup_stable_decay
|
29 |
+
weight_decay: 0.1
|
30 |
+
train_data_path: /home/pl487/rds/hpc-work/rdd/data/minipile/bpe32000minipile/train
|
31 |
+
val_data_path: /home/pl487/rds/hpc-work/rdd/data/minipile/bpe32000minipile/validation
|