nolo99 commited on
Commit
d40c530
1 Parent(s): 03238d1

nolo99/DPO-mistral-dpo-gptq

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: openhermes-mistral-dpo-gptq
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
+ # openhermes-mistral-dpo-gptq
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: 0.8471
21
+ - Rewards/chosen: -0.2589
22
+ - Rewards/rejected: -0.1510
23
+ - Rewards/accuracies: 0.375
24
+ - Rewards/margins: -0.1079
25
+ - Logps/rejected: -116.0277
26
+ - Logps/chosen: -111.7328
27
+ - Logits/rejected: -2.2331
28
+ - Logits/chosen: -2.3546
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: 50
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
+ | 0.6755 | 0.1 | 10 | 0.7298 | -0.0301 | -0.0035 | 0.375 | -0.0266 | -114.5520 | -109.4439 | -2.2395 | -2.3722 |
62
+ | 0.6379 | 0.2 | 20 | 0.7804 | -0.1600 | -0.1132 | 0.375 | -0.0468 | -115.6494 | -110.7433 | -2.2341 | -2.3621 |
63
+ | 0.7061 | 0.3 | 30 | 0.8180 | -0.2242 | -0.1463 | 0.375 | -0.0779 | -115.9803 | -111.3849 | -2.2357 | -2.3577 |
64
+ | 0.6503 | 0.4 | 40 | 0.8460 | -0.2548 | -0.1442 | 0.375 | -0.1106 | -115.9595 | -111.6915 | -2.2330 | -2.3554 |
65
+ | 0.9618 | 0.5 | 50 | 0.8471 | -0.2589 | -0.1510 | 0.375 | -0.1079 | -116.0277 | -111.7328 | -2.2331 | -2.3546 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.35.2
71
+ - Pytorch 2.0.1+cu117
72
+ - Datasets 2.17.0
73
+ - Tokenizers 0.15.2
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": 8,
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": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_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 sha256:8abe158e2ad3998712499113705f762cd50cd5eccae26df80dcbd72ea33993a5
3
+ size 13648432
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
runs/Feb15_23-04-33_d28669ee3e9a/events.out.tfevents.1708038425.d28669ee3e9a.164.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc580efbe736cf3623fbf1b5df3a8d1b5100c05986a69c878eca855ab9c24b7
3
+ size 12594
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 sha256:1e3615e08fbcd891ab3692f90b13cbc03bf1aff7ac3b2df0b00b24926542e07b
3
+ size 4155