Hugging Face's logo

12yuens2
/
hotpotqa-unsloth-mistral-7b-4bit-1024

PEFT
Safetensors
trl
sft
unsloth
Generated from Trainer
Model card Files Community
12yuens2 commited on
Commit
e8af196
•
1 Parent(s): fee4aa1

unsloth-mistral-hototqa

Browse files
Files changed (8) hide show
  1. README.md +122 -0
  2. adapter_config.json +33 -0
  3. adapter_model.safetensors +3 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +44 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - unsloth
8
+ - unsloth
9
+ - unsloth
10
+ - generated_from_trainer
11
+ base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
12
+ model-index:
13
+ - name: mistral-7b-instruct-v0.2-bnb-4bit1024
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # mistral-7b-instruct-v0.2-bnb-4bit1024
21
+
22
+ This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.6953
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 8
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 8
48
+ - total_train_batch_size: 64
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.05
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 1.8431 | 0.02 | 25 | 1.4131 |
59
+ | 0.8021 | 0.04 | 50 | 0.7911 |
60
+ | 0.7972 | 0.05 | 75 | 0.7886 |
61
+ | 0.7886 | 0.07 | 100 | 0.7780 |
62
+ | 0.7762 | 0.09 | 125 | 0.7546 |
63
+ | 0.7338 | 0.11 | 150 | 0.7332 |
64
+ | 0.707 | 0.12 | 175 | 0.7399 |
65
+ | 0.7252 | 0.14 | 200 | 0.7303 |
66
+ | 0.7513 | 0.16 | 225 | 0.7384 |
67
+ | 0.7275 | 0.18 | 250 | 0.7380 |
68
+ | 0.7283 | 0.19 | 275 | 0.7285 |
69
+ | 0.7132 | 0.21 | 300 | 0.7452 |
70
+ | 0.7273 | 0.23 | 325 | 0.7370 |
71
+ | 0.7353 | 0.25 | 350 | 0.7388 |
72
+ | 0.7457 | 0.27 | 375 | 0.7292 |
73
+ | 0.7404 | 0.28 | 400 | 0.7315 |
74
+ | 0.7312 | 0.3 | 425 | 0.7341 |
75
+ | 0.7285 | 0.32 | 450 | 0.7277 |
76
+ | 0.7331 | 0.34 | 475 | 0.7318 |
77
+ | 0.7179 | 0.35 | 500 | 0.7401 |
78
+ | 0.7432 | 0.37 | 525 | 0.7399 |
79
+ | 0.7305 | 0.39 | 550 | 0.7463 |
80
+ | 0.723 | 0.41 | 575 | 0.7448 |
81
+ | 0.7303 | 0.42 | 600 | 0.7339 |
82
+ | 0.7213 | 0.44 | 625 | 0.7320 |
83
+ | 0.7236 | 0.46 | 650 | 0.7378 |
84
+ | 0.7263 | 0.48 | 675 | 0.7451 |
85
+ | 0.7462 | 0.5 | 700 | 0.7238 |
86
+ | 0.7287 | 0.51 | 725 | 0.7274 |
87
+ | 0.7364 | 0.53 | 750 | 0.7369 |
88
+ | 0.7276 | 0.55 | 775 | 0.7282 |
89
+ | 0.7268 | 0.57 | 800 | 0.7431 |
90
+ | 0.7382 | 0.58 | 825 | 0.7376 |
91
+ | 0.7185 | 0.6 | 850 | 0.7402 |
92
+ | 0.7153 | 0.62 | 875 | 0.7362 |
93
+ | 0.7314 | 0.64 | 900 | 0.7395 |
94
+ | 0.7465 | 0.65 | 925 | 0.7378 |
95
+ | 0.7228 | 0.67 | 950 | 0.7333 |
96
+ | 0.7336 | 0.69 | 975 | 0.7337 |
97
+ | 0.72 | 0.71 | 1000 | 0.7313 |
98
+ | 0.7258 | 0.73 | 1025 | 0.7379 |
99
+ | 0.7312 | 0.74 | 1050 | 0.7342 |
100
+ | 0.7268 | 0.76 | 1075 | 0.7350 |
101
+ | 0.7137 | 0.78 | 1100 | 0.7401 |
102
+ | 0.7277 | 0.8 | 1125 | 0.7277 |
103
+ | 0.7314 | 0.81 | 1150 | 0.7388 |
104
+ | 0.7106 | 0.83 | 1175 | 0.7371 |
105
+ | 0.7226 | 0.85 | 1200 | 0.7326 |
106
+ | 0.7262 | 0.87 | 1225 | 0.7328 |
107
+ | 0.7356 | 0.88 | 1250 | 0.7408 |
108
+ | 0.7245 | 0.9 | 1275 | 0.7365 |
109
+ | 0.7221 | 0.92 | 1300 | 0.7404 |
110
+ | 0.7194 | 0.94 | 1325 | 0.7418 |
111
+ | 0.7209 | 0.96 | 1350 | 0.7380 |
112
+ | 0.7205 | 0.97 | 1375 | 0.7279 |
113
+ | 0.6788 | 0.99 | 1400 | 0.6953 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - PEFT 0.9.0
119
+ - Transformers 4.38.2
120
+ - Pytorch 2.2.1
121
+ - Datasets 2.18.0
122
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
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": 16,
13
+ "lora_dropout": 0,
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": "unsloth",
21
+ "target_modules": [
22
+ "v_proj",
23
+ "gate_proj",
24
+ "down_proj",
25
+ "o_proj",
26
+ "up_proj",
27
+ "q_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b27ff41f78960da573cda8952c93fb1bddfcc46b5034d40157b6bc2ef4f3e6
3
+ size 83945296
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ '[INST] ' + messages[0]['content'] + ' ' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 32768,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ad53f4ed85c735643f9709b63466606803db049f4e1ee052ef90ead019f02a
3
+ size 4984