Commit
•
30a3b64
1
Parent(s):
773eec0
Training in progress, epoch 1
Browse files- README.md +79 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: mNLP-project/distilgpt2-finetuned
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: distilgpt2-dpo
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# distilgpt2-dpo
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [mNLP-project/distilgpt2-finetuned](https://huggingface.co/mNLP-project/distilgpt2-finetuned) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.1792
|
21 |
+
- Rewards/chosen: 6.1190
|
22 |
+
- Rewards/rejected: 5.0796
|
23 |
+
- Rewards/accuracies: 0.6061
|
24 |
+
- Rewards/margins: 1.0394
|
25 |
+
- Logps/rejected: -703.7405
|
26 |
+
- Logps/chosen: -844.3468
|
27 |
+
- Logits/rejected: -11.5397
|
28 |
+
- Logits/chosen: -8.7315
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 5e-05
|
48 |
+
- train_batch_size: 8
|
49 |
+
- eval_batch_size: 8
|
50 |
+
- seed: 42
|
51 |
+
- gradient_accumulation_steps: 2
|
52 |
+
- total_train_batch_size: 16
|
53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
+
- lr_scheduler_type: linear
|
55 |
+
- lr_scheduler_warmup_ratio: 0.1
|
56 |
+
- num_epochs: 10
|
57 |
+
|
58 |
+
### Training results
|
59 |
+
|
60 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
61 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
62 |
+
| 1.2146 | 1.0 | 1337 | 1.1792 | 6.1190 | 5.0796 | 0.6061 | 1.0394 | -703.7405 | -844.3468 | -11.5397 | -8.7315 |
|
63 |
+
| 0.8026 | 2.0 | 2674 | 1.1980 | 6.3028 | 5.0877 | 0.6142 | 1.2151 | -703.6594 | -842.5087 | -9.1682 | -7.1950 |
|
64 |
+
| 0.3605 | 3.0 | 4011 | 1.3136 | 5.3889 | 4.2456 | 0.5960 | 1.1433 | -712.0801 | -851.6475 | -8.0251 | -5.8074 |
|
65 |
+
| 0.117 | 4.0 | 5348 | 1.4214 | 6.6526 | 5.0410 | 0.6134 | 1.6116 | -704.1267 | -839.0112 | -6.1296 | -4.2746 |
|
66 |
+
| 0.0663 | 5.0 | 6685 | 1.5485 | 5.0321 | 3.6157 | 0.5947 | 1.4164 | -718.3795 | -855.2162 | -2.6173 | -0.7400 |
|
67 |
+
| 0.0078 | 6.0 | 8022 | 1.7565 | 5.1090 | 3.1954 | 0.6059 | 1.9136 | -722.5821 | -854.4468 | -4.4487 | -2.6082 |
|
68 |
+
| 0.0095 | 7.0 | 9359 | 1.7638 | 4.7802 | 2.8888 | 0.6043 | 1.8913 | -725.6480 | -857.7352 | -3.9409 | -2.1229 |
|
69 |
+
| 0.0178 | 8.0 | 10696 | 1.9119 | 3.9489 | 1.9819 | 0.5990 | 1.9669 | -734.7172 | -866.0483 | -4.2940 | -2.5345 |
|
70 |
+
| 0.0089 | 9.0 | 12033 | 1.9710 | 3.7315 | 1.6704 | 0.5966 | 2.0611 | -737.8326 | -868.2217 | -5.5045 | -3.8933 |
|
71 |
+
| 0.0046 | 10.0 | 13370 | 2.0149 | 3.5136 | 1.4530 | 0.5940 | 2.0606 | -740.0063 | -870.4007 | -5.9962 | -4.4521 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.40.2
|
77 |
+
- Pytorch 2.1.0+cu118
|
78 |
+
- Datasets 2.19.1
|
79 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mNLP-project/gpt2-finetuned",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.40.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.40.2"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d277e129f92f753a3a09b1d97ebbdc53248fefb3a5df22aa6acf32f222355b5
|
3 |
+
size 497774208
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": 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
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e9fe933f136ec8b8d9bd5296ef093520541ada90df3f9fead74fec43b3c51e9
|
3 |
+
size 4984
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|