End of training
Browse files- README.md +3 -11
- config.json +33 -24
- model.safetensors +2 -2
- special_tokens_map.json +4 -28
- tokenizer.json +0 -0
- tokenizer_config.json +7 -17
- training_args.bin +1 -1
- vocab.json +0 -0
README.md
CHANGED
@@ -1,13 +1,11 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
license:
|
4 |
-
base_model:
|
5 |
tags:
|
6 |
- trl
|
7 |
- reward-trainer
|
8 |
- generated_from_trainer
|
9 |
-
metrics:
|
10 |
-
- accuracy
|
11 |
model-index:
|
12 |
- name: reward_modeling_anthropic_hh
|
13 |
results: []
|
@@ -18,10 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# reward_modeling_anthropic_hh
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
-
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.6029
|
24 |
-
- Accuracy: 0.6612
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -52,9 +47,6 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
56 |
-
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
57 |
-
| 0.6125 | 0.8696 | 500 | 0.6029 | 0.6612 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: gpt2
|
5 |
tags:
|
6 |
- trl
|
7 |
- reward-trainer
|
8 |
- generated_from_trainer
|
|
|
|
|
9 |
model-index:
|
10 |
- name: reward_modeling_anthropic_hh
|
11 |
results: []
|
|
|
16 |
|
17 |
# reward_modeling_anthropic_hh
|
18 |
|
19 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
config.json
CHANGED
@@ -1,37 +1,46 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"
|
4 |
-
"activation_dropout": 0.0,
|
5 |
-
"activation_function": "relu",
|
6 |
"architectures": [
|
7 |
-
"
|
8 |
],
|
9 |
-
"
|
10 |
-
"bos_token_id":
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"enable_bias": true,
|
14 |
-
"eos_token_id": 2,
|
15 |
-
"ffn_dim": 4096,
|
16 |
-
"hidden_size": 1024,
|
17 |
"id2label": {
|
18 |
"0": "LABEL_0"
|
19 |
},
|
20 |
-
"
|
21 |
"label2id": {
|
22 |
"LABEL_0": 0
|
23 |
},
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
"torch_dtype": "float32",
|
33 |
"transformers_version": "4.44.1",
|
34 |
"use_cache": true,
|
35 |
-
"vocab_size":
|
36 |
-
"word_embed_proj_dim": 512
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
|
|
|
|
4 |
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
|
|
|
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0"
|
13 |
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
"label2id": {
|
16 |
"LABEL_0": 0
|
17 |
},
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "gpt2",
|
20 |
+
"n_ctx": 1024,
|
21 |
+
"n_embd": 768,
|
22 |
+
"n_head": 12,
|
23 |
+
"n_inner": null,
|
24 |
+
"n_layer": 12,
|
25 |
+
"n_positions": 1024,
|
26 |
+
"pad_token_id": 50256,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
"torch_dtype": "float32",
|
43 |
"transformers_version": "4.44.1",
|
44 |
"use_cache": true,
|
45 |
+
"vocab_size": 50257
|
|
|
46 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae2e0ac6d11fd8f3beebe3a70dcd3ae8fa4fcd213ea68c868c11e9b5859ad95a
|
3 |
+
size 497777360
|
special_tokens_map.json
CHANGED
@@ -1,30 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<pad>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "</s>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": true,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,17 +1,8 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
-
"
|
6 |
-
"content": "
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": true,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"2": {
|
14 |
-
"content": "</s>",
|
15 |
"lstrip": false,
|
16 |
"normalized": true,
|
17 |
"rstrip": false,
|
@@ -19,12 +10,11 @@
|
|
19 |
"special": true
|
20 |
}
|
21 |
},
|
22 |
-
"bos_token": "
|
23 |
"clean_up_tokenization_spaces": true,
|
24 |
-
"eos_token": "
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"pad_token": "<pad>",
|
28 |
"tokenizer_class": "GPT2Tokenizer",
|
29 |
-
"unk_token": "
|
30 |
}
|
|
|
1 |
{
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"lstrip": false,
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
|
|
10 |
"special": true
|
11 |
}
|
12 |
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
|
|
18 |
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
20 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a63c9bda74d37531557c8758fde795b9e8a8a39621a60642aa6690a5089e8f88
|
3 |
size 5304
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|