mnlp-nsoai/mistral-7b-scientific-mcq
Browse files- README.md +114 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-Instruct-v0.2
|
9 |
+
model-index:
|
10 |
+
- name: mistral-7b-scientific-mcq
|
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 |
+
# mistral-7b-scientific-mcq
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.7480
|
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: 5e-05
|
41 |
+
- train_batch_size: 4
|
42 |
+
- eval_batch_size: 4
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_steps: 100
|
49 |
+
- num_epochs: 3.0
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 0.9911 | 0.0581 | 100 | 0.8124 |
|
56 |
+
| 0.879 | 0.1162 | 200 | 0.7703 |
|
57 |
+
| 0.9359 | 0.1743 | 300 | 0.7576 |
|
58 |
+
| 0.7608 | 0.2325 | 400 | 0.7523 |
|
59 |
+
| 0.8144 | 0.2906 | 500 | 0.7469 |
|
60 |
+
| 0.8655 | 0.3487 | 600 | 0.7435 |
|
61 |
+
| 0.6748 | 0.4068 | 700 | 0.7390 |
|
62 |
+
| 0.7004 | 0.4649 | 800 | 0.7369 |
|
63 |
+
| 0.7561 | 0.5230 | 900 | 0.7351 |
|
64 |
+
| 0.7053 | 0.5811 | 1000 | 0.7317 |
|
65 |
+
| 0.7122 | 0.6393 | 1100 | 0.7294 |
|
66 |
+
| 0.7431 | 0.6974 | 1200 | 0.7279 |
|
67 |
+
| 0.6102 | 0.7555 | 1300 | 0.7255 |
|
68 |
+
| 0.7041 | 0.8136 | 1400 | 0.7244 |
|
69 |
+
| 0.7339 | 0.8717 | 1500 | 0.7227 |
|
70 |
+
| 0.6648 | 0.9298 | 1600 | 0.7207 |
|
71 |
+
| 0.5682 | 0.9879 | 1700 | 0.7192 |
|
72 |
+
| 0.6745 | 1.0461 | 1800 | 0.7242 |
|
73 |
+
| 0.6003 | 1.1042 | 1900 | 0.7258 |
|
74 |
+
| 0.6755 | 1.1623 | 2000 | 0.7273 |
|
75 |
+
| 0.6815 | 1.2204 | 2100 | 0.7265 |
|
76 |
+
| 0.5531 | 1.2785 | 2200 | 0.7253 |
|
77 |
+
| 0.5 | 1.3366 | 2300 | 0.7250 |
|
78 |
+
| 0.666 | 1.3947 | 2400 | 0.7236 |
|
79 |
+
| 0.518 | 1.4529 | 2500 | 0.7247 |
|
80 |
+
| 0.6223 | 1.5110 | 2600 | 0.7240 |
|
81 |
+
| 0.565 | 1.5691 | 2700 | 0.7234 |
|
82 |
+
| 0.5541 | 1.6272 | 2800 | 0.7220 |
|
83 |
+
| 0.7622 | 1.6853 | 2900 | 0.7220 |
|
84 |
+
| 0.5212 | 1.7434 | 3000 | 0.7223 |
|
85 |
+
| 0.6089 | 1.8015 | 3100 | 0.7205 |
|
86 |
+
| 0.6908 | 1.8597 | 3200 | 0.7210 |
|
87 |
+
| 0.6138 | 1.9178 | 3300 | 0.7204 |
|
88 |
+
| 0.6425 | 1.9759 | 3400 | 0.7199 |
|
89 |
+
| 0.4918 | 2.0340 | 3500 | 0.7416 |
|
90 |
+
| 0.5432 | 2.0921 | 3600 | 0.7468 |
|
91 |
+
| 0.6497 | 2.1502 | 3700 | 0.7463 |
|
92 |
+
| 0.5068 | 2.2083 | 3800 | 0.7448 |
|
93 |
+
| 0.5502 | 2.2665 | 3900 | 0.7475 |
|
94 |
+
| 0.4795 | 2.3246 | 4000 | 0.7482 |
|
95 |
+
| 0.5718 | 2.3827 | 4100 | 0.7486 |
|
96 |
+
| 0.5154 | 2.4408 | 4200 | 0.7474 |
|
97 |
+
| 0.6959 | 2.4989 | 4300 | 0.7479 |
|
98 |
+
| 0.5848 | 2.5570 | 4400 | 0.7473 |
|
99 |
+
| 0.5662 | 2.6151 | 4500 | 0.7479 |
|
100 |
+
| 0.4357 | 2.6733 | 4600 | 0.7482 |
|
101 |
+
| 0.5318 | 2.7314 | 4700 | 0.7476 |
|
102 |
+
| 0.4631 | 2.7895 | 4800 | 0.7480 |
|
103 |
+
| 0.5852 | 2.8476 | 4900 | 0.7481 |
|
104 |
+
| 0.5633 | 2.9057 | 5000 | 0.7480 |
|
105 |
+
| 0.5831 | 2.9638 | 5100 | 0.7480 |
|
106 |
+
|
107 |
+
|
108 |
+
### Framework versions
|
109 |
+
|
110 |
+
- PEFT 0.11.1
|
111 |
+
- Transformers 4.41.2
|
112 |
+
- Pytorch 2.3.0+cu121
|
113 |
+
- Datasets 2.19.2
|
114 |
+
- 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": "mistralai/Mistral-7B-Instruct-v0.2",
|
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": 32,
|
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": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"up_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:b71591490cf44b865cc1aeb07a4a00396980de99aafcad1b6da61d5e4b37bb17
|
3 |
+
size 167832240
|
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.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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% 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": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6c4553b8cdc1874e0ee64b1cf628de61bacf498d7810c4a91c35390a727ae97
|
3 |
+
size 5432
|