tulidivyansh25 commited on
Commit
2423fd5
1 Parent(s): 754dbbe

tulidivyansh25/mistral_youtube_dpo

Browse files
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: mistral-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
+ # mistral-dpo
17
+
18
+ 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.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7137
21
+ - Rewards/chosen: 1.0722
22
+ - Rewards/rejected: 0.8993
23
+ - Rewards/accuracies: 0.5962
24
+ - Rewards/margins: 0.1729
25
+ - Logps/rejected: -188.1420
26
+ - Logps/chosen: -180.8729
27
+ - Logits/rejected: -2.4148
28
+ - Logits/chosen: -2.4328
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: 0.0002
48
+ - train_batch_size: 1
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 2
54
+ - training_steps: 250
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
60
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
61
+ | 0.7053 | 0.0 | 10 | 0.6892 | 0.0818 | 0.0724 | 0.5962 | 0.0094 | -196.4110 | -190.7768 | -2.3946 | -2.4152 |
62
+ | 0.6805 | 0.0 | 20 | 0.6918 | -0.0354 | -0.0484 | 0.6346 | 0.0130 | -197.6190 | -191.9491 | -2.4006 | -2.4157 |
63
+ | 0.834 | 0.0 | 30 | 0.7086 | -0.2432 | -0.2641 | 0.5962 | 0.0210 | -199.7762 | -194.0263 | -2.4164 | -2.4252 |
64
+ | 0.8729 | 0.0 | 40 | 0.6981 | -0.1038 | -0.1416 | 0.6058 | 0.0377 | -198.5504 | -192.6330 | -2.4265 | -2.4351 |
65
+ | 0.838 | 0.0 | 50 | 0.6864 | 0.2782 | 0.2234 | 0.6058 | 0.0549 | -194.9011 | -188.8124 | -2.4238 | -2.4335 |
66
+ | 0.7253 | 0.0 | 60 | 0.6779 | 0.5564 | 0.4647 | 0.5865 | 0.0917 | -192.4881 | -186.0311 | -2.4271 | -2.4351 |
67
+ | 0.5718 | 0.01 | 70 | 0.6798 | 0.8872 | 0.7700 | 0.5769 | 0.1172 | -189.4352 | -182.7231 | -2.4266 | -2.4337 |
68
+ | 0.6437 | 0.01 | 80 | 0.6759 | 1.0681 | 0.9182 | 0.5096 | 0.1500 | -187.9532 | -180.9136 | -2.4499 | -2.4314 |
69
+ | 0.6098 | 0.01 | 90 | 0.7191 | 0.5345 | -0.0458 | 0.5577 | 0.5803 | -197.5928 | -186.2494 | -2.4888 | -2.4677 |
70
+ | 0.461 | 0.01 | 100 | 0.6948 | 1.0460 | 0.6785 | 0.5481 | 0.3675 | -190.3493 | -181.1343 | -2.4687 | -2.4447 |
71
+ | 1.0876 | 0.01 | 110 | 0.7081 | 1.0687 | 0.9388 | 0.5288 | 0.1299 | -187.7468 | -180.9077 | -2.4276 | -2.4196 |
72
+ | 0.5964 | 0.01 | 120 | 0.7045 | 0.9387 | 0.7995 | 0.5673 | 0.1391 | -189.1394 | -182.2079 | -2.4186 | -2.4276 |
73
+ | 0.6637 | 0.01 | 130 | 0.7018 | 0.9248 | 0.7781 | 0.5865 | 0.1466 | -189.3533 | -182.3472 | -2.4240 | -2.4395 |
74
+ | 0.5702 | 0.01 | 140 | 0.6985 | 0.8728 | 0.7128 | 0.6058 | 0.1600 | -190.0070 | -182.8667 | -2.4273 | -2.4452 |
75
+ | 0.8064 | 0.01 | 150 | 0.6941 | 0.8313 | 0.6588 | 0.6058 | 0.1725 | -190.5471 | -183.2818 | -2.4245 | -2.4424 |
76
+ | 0.7656 | 0.01 | 160 | 0.6877 | 0.7222 | 0.5277 | 0.5962 | 0.1945 | -191.8579 | -184.3729 | -2.4206 | -2.4390 |
77
+ | 0.6725 | 0.01 | 170 | 0.6949 | 0.8229 | 0.6362 | 0.5865 | 0.1867 | -190.7732 | -183.3658 | -2.4268 | -2.4442 |
78
+ | 0.6524 | 0.01 | 180 | 0.7100 | 0.9856 | 0.8195 | 0.5673 | 0.1660 | -188.9394 | -181.7392 | -2.4317 | -2.4486 |
79
+ | 1.0287 | 0.02 | 190 | 0.7161 | 1.0244 | 0.8611 | 0.5769 | 0.1634 | -188.5242 | -181.3504 | -2.4263 | -2.4431 |
80
+ | 0.8451 | 0.02 | 200 | 0.7186 | 1.0966 | 0.9354 | 0.5769 | 0.1613 | -187.7810 | -180.6283 | -2.4266 | -2.4435 |
81
+ | 0.6098 | 0.02 | 210 | 0.7159 | 1.1066 | 0.9427 | 0.5865 | 0.1639 | -187.7074 | -180.5288 | -2.4209 | -2.4382 |
82
+ | 0.5698 | 0.02 | 220 | 0.7149 | 1.1019 | 0.9356 | 0.5962 | 0.1663 | -187.7789 | -180.5757 | -2.4156 | -2.4336 |
83
+ | 0.7013 | 0.02 | 230 | 0.7145 | 1.0913 | 0.9216 | 0.5962 | 0.1697 | -187.9192 | -180.6817 | -2.4142 | -2.4319 |
84
+ | 2.6822 | 0.02 | 240 | 0.7143 | 1.0768 | 0.9049 | 0.5962 | 0.1720 | -188.0860 | -180.8263 | -2.4140 | -2.4322 |
85
+ | 0.9203 | 0.02 | 250 | 0.7137 | 1.0722 | 0.8993 | 0.5962 | 0.1729 | -188.1420 | -180.8729 | -2.4148 | -2.4328 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.35.2
91
+ - Pytorch 2.0.1+cu117
92
+ - Datasets 2.15.0
93
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8cbce642555b6775df9e02c7bfd958cef6c2c34543be48513d1207b323468e7
3
+ size 6832600
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
runs/Feb01_11-13-05_4a3bccaa89dc/events.out.tfevents.1706786144.4a3bccaa89dc.335.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc70fb52bc2b03d28bd33dc7a7b4904e4c9a6947940ac4beb2cdb6b23ef09e8d
3
+ size 39878
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:d51f8ce7c0eecd8c9fcd73d2a41645458d96096dcf85df0c4ca95ec10f12d599
3
+ size 4091