Hugging Face's logo

thobuiq
/
mistral-dpo

Text Generation
PEFT
Safetensors
mistral
Generated from Trainer
4-bit precision
gptq
Model card Files Community
thobuiq commited on
Commit
09dff77
·
verified ·
1 Parent(s): e064acb

Upload 10 files

Browse files
Files changed (9) hide show
  1. README.md +93 -0
  2. adapter_config.json +26 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +4 -0
  5. special_tokens_map.json +35 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +64 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
7
+ model-index:
8
+ - name: mistral-dpo
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # mistral-dpo
16
+
17
+ This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8911
20
+ - Rewards/chosen: 0.5387
21
+ - Rewards/rejected: 0.4878
22
+ - Rewards/accuracies: 0.5096
23
+ - Rewards/margins: 0.0509
24
+ - Logps/rejected: -174.3804
25
+ - Logps/chosen: -178.5185
26
+ - Logits/rejected: -2.5028
27
+ - Logits/chosen: -2.5350
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 0.0002
47
+ - train_batch_size: 1
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 2
53
+ - training_steps: 250
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
60
+ | 0.6703 | 0.0 | 10 | 0.6842 | -0.0001 | -0.0268 | 0.5865 | 0.0267 | -179.5257 | -183.9063 | -2.4290 | -2.4720 |
61
+ | 0.7119 | 0.0 | 20 | 0.6751 | 0.1584 | 0.0990 | 0.5769 | 0.0594 | -178.2678 | -182.3211 | -2.4542 | -2.4988 |
62
+ | 0.647 | 0.0 | 30 | 0.6702 | 0.3569 | 0.2540 | 0.5769 | 0.1029 | -176.7180 | -180.3367 | -2.4886 | -2.5306 |
63
+ | 0.6748 | 0.0 | 40 | 0.6712 | 0.3439 | 0.2229 | 0.5288 | 0.1210 | -177.0292 | -180.4664 | -2.5206 | -2.5581 |
64
+ | 0.6513 | 0.0 | 50 | 0.6707 | 0.4403 | 0.2838 | 0.5577 | 0.1565 | -176.4200 | -179.5021 | -2.5608 | -2.5853 |
65
+ | 0.6103 | 0.0 | 60 | 0.6695 | 0.6831 | 0.4769 | 0.5577 | 0.2063 | -174.4892 | -177.0740 | -2.5719 | -2.5933 |
66
+ | 1.0313 | 0.01 | 70 | 0.6724 | 0.7062 | 0.5084 | 0.5577 | 0.1978 | -174.1739 | -176.8436 | -2.5543 | -2.5843 |
67
+ | 0.6876 | 0.01 | 80 | 0.6804 | 0.6995 | 0.5144 | 0.5385 | 0.1850 | -174.1135 | -176.9104 | -2.5443 | -2.5829 |
68
+ | 0.9661 | 0.01 | 90 | 0.6828 | 0.7118 | 0.5376 | 0.5385 | 0.1742 | -173.8821 | -176.7873 | -2.5479 | -2.5846 |
69
+ | 0.7354 | 0.01 | 100 | 0.6757 | 0.6765 | 0.5039 | 0.5577 | 0.1726 | -174.2186 | -177.1401 | -2.5399 | -2.5758 |
70
+ | 1.0127 | 0.01 | 110 | 0.7129 | 0.6089 | 0.4855 | 0.5288 | 0.1234 | -174.4033 | -177.8165 | -2.5464 | -2.5760 |
71
+ | 1.0366 | 0.01 | 120 | 0.7440 | 0.6068 | 0.4946 | 0.5481 | 0.1122 | -174.3115 | -177.8369 | -2.5516 | -2.5804 |
72
+ | 1.2145 | 0.01 | 130 | 0.7564 | 0.6521 | 0.5396 | 0.5673 | 0.1125 | -173.8620 | -177.3846 | -2.5608 | -2.5878 |
73
+ | 0.8342 | 0.01 | 140 | 0.7649 | 0.6639 | 0.5519 | 0.5385 | 0.1119 | -173.7388 | -177.2668 | -2.5547 | -2.5828 |
74
+ | 0.7402 | 0.01 | 150 | 0.7991 | 0.5831 | 0.4883 | 0.5 | 0.0948 | -174.3747 | -178.0745 | -2.5498 | -2.5775 |
75
+ | 0.7162 | 0.01 | 160 | 0.8396 | 0.6134 | 0.5474 | 0.5096 | 0.0659 | -173.7835 | -177.7718 | -2.5445 | -2.5713 |
76
+ | 0.9396 | 0.01 | 170 | 0.8573 | 0.5700 | 0.5144 | 0.5288 | 0.0556 | -174.1144 | -178.2057 | -2.5326 | -2.5629 |
77
+ | 0.5958 | 0.01 | 180 | 0.8708 | 0.5526 | 0.5017 | 0.5288 | 0.0509 | -174.2406 | -178.3789 | -2.5227 | -2.5540 |
78
+ | 0.7588 | 0.02 | 190 | 0.8865 | 0.5428 | 0.4977 | 0.5288 | 0.0450 | -174.2806 | -178.4775 | -2.5207 | -2.5493 |
79
+ | 0.7811 | 0.02 | 200 | 0.8933 | 0.5797 | 0.5429 | 0.5192 | 0.0368 | -173.8286 | -178.1080 | -2.5171 | -2.5434 |
80
+ | 0.5735 | 0.02 | 210 | 0.8907 | 0.5577 | 0.5174 | 0.5288 | 0.0403 | -174.0838 | -178.3279 | -2.5069 | -2.5366 |
81
+ | 0.7709 | 0.02 | 220 | 0.8886 | 0.5602 | 0.5167 | 0.5192 | 0.0435 | -174.0907 | -178.3035 | -2.5041 | -2.5361 |
82
+ | 0.4914 | 0.02 | 230 | 0.8884 | 0.5237 | 0.4766 | 0.5192 | 0.0471 | -174.4924 | -178.6684 | -2.5050 | -2.5375 |
83
+ | 0.739 | 0.02 | 240 | 0.8910 | 0.5281 | 0.4796 | 0.5192 | 0.0485 | -174.4621 | -178.6240 | -2.5027 | -2.5351 |
84
+ | 0.5743 | 0.02 | 250 | 0.8911 | 0.5387 | 0.4878 | 0.5096 | 0.0509 | -174.3804 | -178.5185 | -2.5028 | -2.5350 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - PEFT 0.7.1
90
+ - Transformers 4.36.0
91
+ - Pytorch 2.0.1+cu117
92
+ - Datasets 2.15.0
93
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TheBloke/OpenHermes-2-Mistral-7B-GPTQ",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 6,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 4,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05bfcc1a19705d6a2dc9ccb8a065fb44b1d97e6f64a331ef90a6dabaad1a5e80
3
+ size 135
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|im_end|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<unk>",
48
+ "<s>",
49
+ "</s>"
50
+ ],
51
+ "bos_token": "<s>",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|im_end|>",
54
+ "legacy": true,
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": "</s>",
57
+ "sp_model_kwargs": {},
58
+ "spaces_between_special_tokens": false,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "trust_remote_code": false,
61
+ "unk_token": "<unk>",
62
+ "use_default_system_prompt": true,
63
+ "use_fast": true
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a744ecc30871a71a7fc5ed07942856a6e759e716fa13531c07b20ed7930a0f2e
3
+ size 4219