austindavis
commited on
End of training
Browse files- README.md +61 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: austindavis/gpt2-pretrained-lichess-uci
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: gpt2-pretrained-lichess-uci-finetuned-lichess-uci
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# gpt2-pretrained-lichess-uci-finetuned-lichess-uci
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [austindavis/gpt2-pretrained-lichess-uci](https://huggingface.co/austindavis/gpt2-pretrained-lichess-uci) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.3084
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0002
|
37 |
+
- train_batch_size: 16
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: cosine
|
42 |
+
- num_epochs: 6
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
+
| 1.6794 | 1.0 | 4099 | 1.5886 |
|
49 |
+
| 1.5251 | 2.0 | 8198 | 1.4533 |
|
50 |
+
| 1.429 | 3.0 | 12297 | 1.3812 |
|
51 |
+
| 1.3611 | 4.0 | 16396 | 1.3369 |
|
52 |
+
| 1.3108 | 5.0 | 20495 | 1.3135 |
|
53 |
+
| 1.2809 | 6.0 | 24594 | 1.3084 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.40.1
|
59 |
+
- Pytorch 2.3.0
|
60 |
+
- Datasets 2.19.1
|
61 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.40.1"
|
6 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 103134952
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34f12fdd2886f4c95767955161f8b0d513375e9132857494af5b1ce12e4a6bc8
|
3 |
size 103134952
|