Hugging Face's logo

sosuke
/
preference_tuning_results

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files
xet
Community
sosuke commited on
Commit
4081876
·
verified ·
1 Parent(s): d8ff46a

sosuke/Swallow-7b-hf-oasst1-21k-ja-hh-rlhf-12k-ja

Browse files
Files changed (9) hide show
  1. README.md +99 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +5 -0
  5. special_tokens_map.json +33 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +71 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: llm-book/Swallow-7b-hf-oasst1-21k-ja
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: preference_tuning_results
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
+ # preference_tuning_results
17
+
18
+ This model is a fine-tuned version of [llm-book/Swallow-7b-hf-oasst1-21k-ja](https://huggingface.co/llm-book/Swallow-7b-hf-oasst1-21k-ja) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6610
21
+ - Rewards/chosen: -0.1479
22
+ - Rewards/rejected: -0.2665
23
+ - Rewards/accuracies: 0.5917
24
+ - Rewards/margins: 0.1186
25
+ - Logps/rejected: -146.9710
26
+ - Logps/chosen: -134.8070
27
+ - Logits/rejected: 0.3116
28
+ - Logits/chosen: 0.3255
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-06
48
+ - train_batch_size: 4
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 8
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: cosine
55
+ - lr_scheduler_warmup_ratio: 0.1
56
+ - num_epochs: 1
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
+ | 0.6935 | 0.0337 | 50 | 0.6908 | 0.0025 | -0.0026 | 0.5417 | 0.0050 | -144.3320 | -133.3038 | 0.1607 | 0.1710 |
63
+ | 0.6936 | 0.0673 | 100 | 0.6915 | 0.0016 | -0.0021 | 0.5750 | 0.0037 | -144.3277 | -133.3129 | 0.1674 | 0.1783 |
64
+ | 0.6905 | 0.1010 | 150 | 0.6889 | 0.0026 | -0.0067 | 0.5167 | 0.0093 | -144.3729 | -133.3024 | 0.1746 | 0.1857 |
65
+ | 0.6891 | 0.1347 | 200 | 0.6886 | 0.0109 | 0.0007 | 0.5250 | 0.0102 | -144.2993 | -133.2191 | 0.1697 | 0.1812 |
66
+ | 0.6866 | 0.1684 | 250 | 0.6865 | 0.0219 | 0.0071 | 0.5917 | 0.0148 | -144.2358 | -133.1099 | 0.1783 | 0.1895 |
67
+ | 0.6851 | 0.2020 | 300 | 0.6826 | 0.0255 | 0.0020 | 0.6000 | 0.0234 | -144.2859 | -133.0740 | 0.1736 | 0.1853 |
68
+ | 0.6842 | 0.2357 | 350 | 0.6820 | 0.0240 | -0.0014 | 0.6083 | 0.0254 | -144.3206 | -133.0886 | 0.1721 | 0.1833 |
69
+ | 0.679 | 0.2694 | 400 | 0.6761 | 0.0333 | -0.0070 | 0.5750 | 0.0404 | -144.3764 | -132.9950 | 0.1766 | 0.1877 |
70
+ | 0.6814 | 0.3030 | 450 | 0.6741 | 0.0215 | -0.0244 | 0.5333 | 0.0459 | -144.5500 | -133.1130 | 0.1943 | 0.2060 |
71
+ | 0.674 | 0.3367 | 500 | 0.6693 | 0.0179 | -0.0423 | 0.5667 | 0.0602 | -144.7297 | -133.1494 | 0.2098 | 0.2217 |
72
+ | 0.6748 | 0.3704 | 550 | 0.6691 | -0.0133 | -0.0788 | 0.5583 | 0.0655 | -145.0942 | -133.4615 | 0.2477 | 0.2594 |
73
+ | 0.6673 | 0.4040 | 600 | 0.6615 | -0.0450 | -0.1350 | 0.6000 | 0.0899 | -145.6558 | -133.7786 | 0.3043 | 0.3172 |
74
+ | 0.6769 | 0.4377 | 650 | 0.6654 | -0.0385 | -0.1222 | 0.6000 | 0.0837 | -145.5283 | -133.7136 | 0.2800 | 0.2928 |
75
+ | 0.6677 | 0.4714 | 700 | 0.6643 | -0.0537 | -0.1442 | 0.6167 | 0.0905 | -145.7482 | -133.8651 | 0.2681 | 0.2808 |
76
+ | 0.675 | 0.5051 | 750 | 0.6596 | -0.0396 | -0.1394 | 0.6083 | 0.0998 | -145.7003 | -133.7247 | 0.2512 | 0.2644 |
77
+ | 0.6633 | 0.5387 | 800 | 0.6607 | -0.0756 | -0.1792 | 0.5833 | 0.1036 | -146.0984 | -134.0848 | 0.2626 | 0.2751 |
78
+ | 0.6661 | 0.5724 | 850 | 0.6603 | -0.0903 | -0.2000 | 0.6000 | 0.1097 | -146.3066 | -134.2316 | 0.2735 | 0.2861 |
79
+ | 0.6677 | 0.6061 | 900 | 0.6619 | -0.0994 | -0.2070 | 0.5750 | 0.1076 | -146.3762 | -134.3224 | 0.2735 | 0.2864 |
80
+ | 0.6614 | 0.6397 | 950 | 0.6615 | -0.1019 | -0.2104 | 0.5750 | 0.1084 | -146.4101 | -134.3480 | 0.2690 | 0.2818 |
81
+ | 0.6514 | 0.6734 | 1000 | 0.6610 | -0.1138 | -0.2245 | 0.6000 | 0.1107 | -146.5513 | -134.4665 | 0.2835 | 0.2963 |
82
+ | 0.6625 | 0.7071 | 1050 | 0.6602 | -0.1136 | -0.2259 | 0.5833 | 0.1124 | -146.5656 | -134.4642 | 0.2873 | 0.3006 |
83
+ | 0.6421 | 0.7407 | 1100 | 0.6610 | -0.1285 | -0.2408 | 0.5833 | 0.1122 | -146.7140 | -134.6137 | 0.2892 | 0.3024 |
84
+ | 0.6438 | 0.7744 | 1150 | 0.6585 | -0.1373 | -0.2590 | 0.5750 | 0.1217 | -146.8963 | -134.7020 | 0.3015 | 0.3152 |
85
+ | 0.6534 | 0.8081 | 1200 | 0.6603 | -0.1478 | -0.2671 | 0.5917 | 0.1192 | -146.9771 | -134.8070 | 0.3120 | 0.3259 |
86
+ | 0.653 | 0.8418 | 1250 | 0.6607 | -0.1460 | -0.2651 | 0.5917 | 0.1191 | -146.9573 | -134.7881 | 0.3120 | 0.3259 |
87
+ | 0.6667 | 0.8754 | 1300 | 0.6599 | -0.1475 | -0.2678 | 0.5917 | 0.1203 | -146.9841 | -134.8036 | 0.3108 | 0.3247 |
88
+ | 0.6596 | 0.9091 | 1350 | 0.6606 | -0.1452 | -0.2632 | 0.6000 | 0.1181 | -146.9385 | -134.7802 | 0.3114 | 0.3255 |
89
+ | 0.648 | 0.9428 | 1400 | 0.6614 | -0.1475 | -0.2644 | 0.6000 | 0.1169 | -146.9505 | -134.8035 | 0.3118 | 0.3258 |
90
+ | 0.641 | 0.9764 | 1450 | 0.6610 | -0.1479 | -0.2665 | 0.5917 | 0.1186 | -146.9710 | -134.8070 | 0.3116 | 0.3255 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - PEFT 0.11.1
96
+ - Transformers 4.41.2
97
+ - Pytorch 2.3.0+cu121
98
+ - Datasets 2.20.0
99
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "llm-book/Swallow-7b-hf-oasst1-21k-ja",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "gate_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "q_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d650fc565f3c4cf719b01a989a9b75310bb908df55630f49a0dad1d07a4daf7c
3
+ size 1279323952
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 43178,
3
+ "<|assistant|>": 43177,
4
+ "<|user|>": 43176
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
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:c877c5ca885bad5c19d1b1706a2703f8b30de90f03c1f834f8bdb9faf79821e8
3
+ size 914000
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "43176": {
31
+ "content": "<|user|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "43177": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "43178": {
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ }
54
+ },
55
+ "additional_special_tokens": [
56
+ "<pad>"
57
+ ],
58
+ "bos_token": "<s>",
59
+ "chat_template": "{%- for message in messages %}\n{%- if message['role'] == 'user' %}\n{{ '<|user|>' + message['content'] + eos_token }}\n{%- elif message['role'] == 'assistant' %}\n{{ '<|assistant|>' + message['content'] + eos_token }}\n{%- endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{%- endif %}\n{% endfor %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "</s>",
62
+ "legacy": false,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<pad>",
65
+ "padding_side": "left",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "tokenizer_class": "LlamaTokenizer",
69
+ "unk_token": "<unk>",
70
+ "use_default_system_prompt": false
71
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5188022b4947d7154a7a82dc35181d581ffa2a4caa5f7082e0d73d9539a0ea
3
+ size 5752