AlbelTec commited on
Commit
c60f908
1 Parent(s): b1ef526

AlbelTec/dpo_mistral_7B_v_0_1

Browse files
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ base_model: TheBloke/Mistral-7B-v0.1-GPTQ
9
+ model-index:
10
+ - name: mistral-dpo
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # mistral-dpo
18
+
19
+ This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0000
22
+ - Rewards/chosen: -2.0502
23
+ - Rewards/rejected: -28.3632
24
+ - Rewards/accuracies: 1.0
25
+ - Rewards/margins: 26.3129
26
+ - Logps/rejected: -399.8283
27
+ - Logps/chosen: -35.7179
28
+ - Logits/rejected: -2.1171
29
+ - Logits/chosen: -1.8480
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 0.0002
49
+ - train_batch_size: 1
50
+ - eval_batch_size: 8
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 2
55
+ - training_steps: 250
56
+ - mixed_precision_training: Native AMP
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
+ | 0.6453 | 0.2 | 10 | 0.4086 | 0.1393 | -0.7001 | 1.0 | 0.8394 | -123.1976 | -13.8225 | -2.5461 | -2.5162 |
63
+ | 0.1759 | 0.4 | 20 | 0.0051 | 0.3963 | -6.4413 | 1.0 | 6.8376 | -180.6101 | -11.2527 | -2.5253 | -2.4045 |
64
+ | 0.0015 | 0.6 | 30 | 0.0000 | 0.2885 | -20.7441 | 1.0 | 21.0326 | -323.6376 | -12.3309 | -2.2440 | -1.8851 |
65
+ | 0.0 | 0.8 | 40 | 0.0000 | -0.6913 | -26.5964 | 1.0 | 25.9051 | -382.1607 | -22.1282 | -1.9054 | -1.5507 |
66
+ | 0.0 | 1.0 | 50 | 0.0000 | -1.6661 | -28.8376 | 1.0 | 27.1715 | -404.5731 | -31.8766 | -1.7581 | -1.4145 |
67
+ | 0.0 | 1.2 | 60 | 0.0000 | -2.1659 | -29.6823 | 1.0 | 27.5164 | -413.0200 | -36.8745 | -1.7071 | -1.3649 |
68
+ | 0.0 | 1.4 | 70 | 0.0000 | -2.0973 | -30.0476 | 1.0 | 27.9503 | -416.6729 | -36.1886 | -1.6955 | -1.3541 |
69
+ | 0.0 | 1.6 | 80 | 0.0000 | -2.0065 | -30.1726 | 1.0 | 28.1661 | -417.9230 | -35.2805 | -1.6941 | -1.3519 |
70
+ | 0.0 | 1.8 | 90 | 0.0000 | -1.9541 | -30.2266 | 1.0 | 28.2724 | -418.4622 | -34.7568 | -1.6935 | -1.3518 |
71
+ | 0.0023 | 2.0 | 100 | 0.0000 | -0.7061 | -30.2814 | 1.0 | 29.5753 | -419.0107 | -22.2763 | -1.7664 | -1.4215 |
72
+ | 0.0 | 2.2 | 110 | 0.0000 | -1.6234 | -29.4682 | 1.0 | 27.8448 | -410.8783 | -31.4494 | -2.0371 | -1.7164 |
73
+ | 0.0 | 2.4 | 120 | 0.0000 | -1.9528 | -28.6154 | 1.0 | 26.6626 | -402.3507 | -34.7431 | -2.0991 | -1.8126 |
74
+ | 0.0 | 2.6 | 130 | 0.0000 | -2.0210 | -28.3739 | 1.0 | 26.3529 | -399.9358 | -35.4253 | -2.1141 | -1.8394 |
75
+ | 0.0 | 2.8 | 140 | 0.0000 | -2.0443 | -28.2878 | 1.0 | 26.2435 | -399.0752 | -35.6588 | -2.1185 | -1.8487 |
76
+ | 0.0 | 3.0 | 150 | 0.0000 | -2.0504 | -28.2651 | 1.0 | 26.2147 | -398.8474 | -35.7192 | -2.1201 | -1.8510 |
77
+ | 0.0 | 3.2 | 160 | 0.0000 | -2.0500 | -28.2657 | 1.0 | 26.2157 | -398.8541 | -35.7157 | -2.1202 | -1.8519 |
78
+ | 0.0 | 3.4 | 170 | 0.0000 | -2.0530 | -28.2687 | 1.0 | 26.2157 | -398.8837 | -35.7460 | -2.1205 | -1.8521 |
79
+ | 0.0 | 3.6 | 180 | 0.0000 | -2.0529 | -28.2660 | 1.0 | 26.2131 | -398.8570 | -35.7444 | -2.1202 | -1.8515 |
80
+ | 0.0 | 3.8 | 190 | 0.0000 | -2.0531 | -28.2649 | 1.0 | 26.2119 | -398.8461 | -35.7464 | -2.1202 | -1.8519 |
81
+ | 0.0 | 4.0 | 200 | 0.0000 | -2.0579 | -28.3150 | 1.0 | 26.2571 | -399.3466 | -35.7943 | -2.1191 | -1.8507 |
82
+ | 0.0 | 4.2 | 210 | 0.0000 | -2.0509 | -28.3341 | 1.0 | 26.2832 | -399.5381 | -35.7246 | -2.1178 | -1.8487 |
83
+ | 0.0 | 4.4 | 220 | 0.0000 | -2.0516 | -28.3405 | 1.0 | 26.2889 | -399.6018 | -35.7316 | -2.1178 | -1.8490 |
84
+ | 0.0 | 4.6 | 230 | 0.0000 | -2.0516 | -28.3495 | 1.0 | 26.2979 | -399.6917 | -35.7317 | -2.1176 | -1.8489 |
85
+ | 0.0 | 4.8 | 240 | 0.0000 | -2.0508 | -28.3684 | 1.0 | 26.3176 | -399.8806 | -35.7236 | -2.1173 | -1.8488 |
86
+ | 0.0 | 5.0 | 250 | 0.0000 | -2.0502 | -28.3632 | 1.0 | 26.3129 | -399.8283 | -35.7179 | -2.1171 | -1.8480 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - PEFT 0.7.1
92
+ - Transformers 4.36.2
93
+ - Pytorch 2.0.1+cu118
94
+ - Datasets 2.15.0
95
+ - 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/Mistral-7B-v0.1-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
+ "v_proj",
23
+ "q_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 sha256:7f2938efd7419eaf8c1f9d06c878141649471a41c08f6698cff91d23c7d7e9a1
3
+ size 6832600
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
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.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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfccc0fe051dacb57a127d5cddec12bcaa5a126c50cbaf4655f1d80b9c78ceb7
3
+ size 4219