Hugging Face's logo

codewizardUV
/
genProj_mistral-7B

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Community
codewizardUV commited on
Commit
2df2d27
·
verified ·
1 Parent(s): 773dc84

End of training

Browse files
Files changed (7) hide show
  1. README.md +139 -0
  2. adapter_config.json +35 -0
  3. adapter_model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +42 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-v0.1
9
+ model-index:
10
+ - name: genProj_mistral-7B
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
+ # genProj_mistral-7B
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6692
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.00025
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: constant
46
+ - lr_scheduler_warmup_ratio: 0.03
47
+ - num_epochs: 5
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.0215 | 0.0634 | 100 | 1.2005 |
54
+ | 0.9657 | 0.1267 | 200 | 0.9706 |
55
+ | 0.8585 | 0.1901 | 300 | 0.9458 |
56
+ | 0.842 | 0.2535 | 400 | 0.8757 |
57
+ | 0.8587 | 0.3169 | 500 | 0.8758 |
58
+ | 0.8501 | 0.3802 | 600 | 0.7813 |
59
+ | 0.8453 | 0.4436 | 700 | 0.9362 |
60
+ | 0.789 | 0.5070 | 800 | 0.7702 |
61
+ | 0.7213 | 0.5703 | 900 | 0.7641 |
62
+ | 0.7335 | 0.6337 | 1000 | 0.7707 |
63
+ | 0.6989 | 0.6971 | 1100 | 0.7480 |
64
+ | 0.7739 | 0.7605 | 1200 | 0.7210 |
65
+ | 0.6785 | 0.8238 | 1300 | 0.7150 |
66
+ | 0.7198 | 0.8872 | 1400 | 0.7126 |
67
+ | 0.7726 | 0.9506 | 1500 | 0.6919 |
68
+ | 0.495 | 1.0139 | 1600 | 0.6501 |
69
+ | 0.5318 | 1.0773 | 1700 | 0.6376 |
70
+ | 0.5124 | 1.1407 | 1800 | 0.6373 |
71
+ | 0.5404 | 1.2041 | 1900 | 0.6379 |
72
+ | 0.5133 | 1.2674 | 2000 | 0.6633 |
73
+ | 0.516 | 1.3308 | 2100 | 0.6579 |
74
+ | 0.5092 | 1.3942 | 2200 | 0.6525 |
75
+ | 0.6288 | 1.4575 | 2300 | 0.6438 |
76
+ | 0.4935 | 1.5209 | 2400 | 0.6255 |
77
+ | 0.5334 | 1.5843 | 2500 | 0.6246 |
78
+ | 0.6021 | 1.6477 | 2600 | 0.6102 |
79
+ | 0.5625 | 1.7110 | 2700 | 0.6191 |
80
+ | 0.5425 | 1.7744 | 2800 | 0.6301 |
81
+ | 0.5302 | 1.8378 | 2900 | 0.6058 |
82
+ | 0.5443 | 1.9011 | 3000 | 0.6218 |
83
+ | 0.5023 | 1.9645 | 3100 | 0.6129 |
84
+ | 0.3902 | 2.0279 | 3200 | 0.6478 |
85
+ | 0.4046 | 2.0913 | 3300 | 0.6345 |
86
+ | 0.424 | 2.1546 | 3400 | 0.6489 |
87
+ | 0.47 | 2.2180 | 3500 | 0.6729 |
88
+ | 0.419 | 2.2814 | 3600 | 0.6524 |
89
+ | 0.433 | 2.3447 | 3700 | 0.6450 |
90
+ | 0.3993 | 2.4081 | 3800 | 0.6598 |
91
+ | 0.469 | 2.4715 | 3900 | 0.6608 |
92
+ | 0.4909 | 2.5349 | 4000 | 0.6856 |
93
+ | 0.4797 | 2.5982 | 4100 | 0.6924 |
94
+ | 0.4186 | 2.6616 | 4200 | 0.6857 |
95
+ | 0.5057 | 2.7250 | 4300 | 0.6717 |
96
+ | 0.4601 | 2.7883 | 4400 | 0.6723 |
97
+ | 0.4862 | 2.8517 | 4500 | 0.7063 |
98
+ | 0.4926 | 2.9151 | 4600 | 0.6399 |
99
+ | 0.4886 | 2.9785 | 4700 | 0.6538 |
100
+ | 0.4015 | 3.0418 | 4800 | 0.6485 |
101
+ | 0.3844 | 3.1052 | 4900 | 0.6756 |
102
+ | 0.4271 | 3.1686 | 5000 | 0.6801 |
103
+ | 0.4245 | 3.2319 | 5100 | 0.6789 |
104
+ | 0.4393 | 3.2953 | 5200 | 0.6881 |
105
+ | 0.436 | 3.3587 | 5300 | 0.6710 |
106
+ | 0.4717 | 3.4221 | 5400 | 0.6746 |
107
+ | 0.4221 | 3.4854 | 5500 | 0.7194 |
108
+ | 0.487 | 3.5488 | 5600 | 0.6693 |
109
+ | 0.4547 | 3.6122 | 5700 | 0.6742 |
110
+ | 0.4949 | 3.6755 | 5800 | 0.6795 |
111
+ | 0.4865 | 3.7389 | 5900 | 0.7108 |
112
+ | 0.5139 | 3.8023 | 6000 | 0.6612 |
113
+ | 0.4512 | 3.8657 | 6100 | 0.6799 |
114
+ | 0.5094 | 3.9290 | 6200 | 0.6759 |
115
+ | 0.4989 | 3.9924 | 6300 | 0.6649 |
116
+ | 0.3635 | 4.0558 | 6400 | 0.6683 |
117
+ | 0.3599 | 4.1191 | 6500 | 0.6765 |
118
+ | 0.3789 | 4.1825 | 6600 | 0.7041 |
119
+ | 0.3897 | 4.2459 | 6700 | 0.6771 |
120
+ | 0.3753 | 4.3093 | 6800 | 0.6831 |
121
+ | 0.389 | 4.3726 | 6900 | 0.6954 |
122
+ | 0.4111 | 4.4360 | 7000 | 0.7050 |
123
+ | 0.4016 | 4.4994 | 7100 | 0.6762 |
124
+ | 0.3798 | 4.5627 | 7200 | 0.7055 |
125
+ | 0.4121 | 4.6261 | 7300 | 0.6707 |
126
+ | 0.4127 | 4.6895 | 7400 | 0.6976 |
127
+ | 0.4523 | 4.7529 | 7500 | 0.6520 |
128
+ | 0.4035 | 4.8162 | 7600 | 0.7363 |
129
+ | 0.4152 | 4.8796 | 7700 | 0.7270 |
130
+ | 0.4615 | 4.9430 | 7800 | 0.6692 |
131
+
132
+
133
+ ### Framework versions
134
+
135
+ - PEFT 0.11.0
136
+ - Transformers 4.40.2
137
+ - Pytorch 2.3.0+cu121
138
+ - Datasets 2.19.1
139
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
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": 16,
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": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "up_proj",
25
+ "gate_proj",
26
+ "o_proj",
27
+ "q_proj",
28
+ "v_proj",
29
+ "k_proj",
30
+ "lm_head"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d21b5aa0d1a0a54d6cba2684762457e0310b0d9d1c6dd2cbc738ed9cf371050
3
+ size 609397376
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
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_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": 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
+ },
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": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfe1b3cbc9a2b683feb7d0a823144534433a41823a71e64ac0aa60ddc7800d2
3
+ size 4984