anantg/Mixtral-Finetuned
Browse files- README.md +168 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
11 |
+
model-index:
|
12 |
+
- name: Mixtral-Finetune-Output
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# Mixtral-Finetune-Output
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.3062
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0001
|
43 |
+
- train_batch_size: 1
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 0.03
|
49 |
+
- num_epochs: 1
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 1.5745 | 0.01 | 10 | 1.4701 |
|
56 |
+
| 1.5372 | 0.02 | 20 | 1.4541 |
|
57 |
+
| 1.4147 | 0.03 | 30 | 1.4433 |
|
58 |
+
| 1.423 | 0.04 | 40 | 1.4366 |
|
59 |
+
| 1.5318 | 0.05 | 50 | 1.4326 |
|
60 |
+
| 1.334 | 0.06 | 60 | 1.4296 |
|
61 |
+
| 1.364 | 0.07 | 70 | 1.4244 |
|
62 |
+
| 1.332 | 0.08 | 80 | 1.4194 |
|
63 |
+
| 1.3742 | 0.09 | 90 | 1.4163 |
|
64 |
+
| 1.4497 | 0.1 | 100 | 1.4124 |
|
65 |
+
| 1.4145 | 0.1 | 110 | 1.4098 |
|
66 |
+
| 1.4224 | 0.11 | 120 | 1.4050 |
|
67 |
+
| 1.4013 | 0.12 | 130 | 1.4017 |
|
68 |
+
| 1.547 | 0.13 | 140 | 1.4020 |
|
69 |
+
| 1.4969 | 0.14 | 150 | 1.3967 |
|
70 |
+
| 1.5716 | 0.15 | 160 | 1.3943 |
|
71 |
+
| 1.3677 | 0.16 | 170 | 1.3915 |
|
72 |
+
| 1.3789 | 0.17 | 180 | 1.3901 |
|
73 |
+
| 1.3188 | 0.18 | 190 | 1.3869 |
|
74 |
+
| 1.3317 | 0.19 | 200 | 1.3846 |
|
75 |
+
| 1.2552 | 0.2 | 210 | 1.3809 |
|
76 |
+
| 1.2584 | 0.21 | 220 | 1.3788 |
|
77 |
+
| 1.3958 | 0.22 | 230 | 1.3776 |
|
78 |
+
| 1.3345 | 0.23 | 240 | 1.3755 |
|
79 |
+
| 1.3562 | 0.24 | 250 | 1.3723 |
|
80 |
+
| 1.343 | 0.25 | 260 | 1.3726 |
|
81 |
+
| 1.3705 | 0.26 | 270 | 1.3695 |
|
82 |
+
| 1.5719 | 0.27 | 280 | 1.3687 |
|
83 |
+
| 1.3634 | 0.28 | 290 | 1.3652 |
|
84 |
+
| 1.4465 | 0.29 | 300 | 1.3668 |
|
85 |
+
| 1.3949 | 0.29 | 310 | 1.3642 |
|
86 |
+
| 1.3147 | 0.3 | 320 | 1.3631 |
|
87 |
+
| 1.368 | 0.31 | 330 | 1.3613 |
|
88 |
+
| 1.3482 | 0.32 | 340 | 1.3603 |
|
89 |
+
| 1.3143 | 0.33 | 350 | 1.3591 |
|
90 |
+
| 1.4717 | 0.34 | 360 | 1.3568 |
|
91 |
+
| 1.2089 | 0.35 | 370 | 1.3555 |
|
92 |
+
| 1.4223 | 0.36 | 380 | 1.3529 |
|
93 |
+
| 1.3895 | 0.37 | 390 | 1.3523 |
|
94 |
+
| 1.309 | 0.38 | 400 | 1.3504 |
|
95 |
+
| 1.3698 | 0.39 | 410 | 1.3487 |
|
96 |
+
| 1.2834 | 0.4 | 420 | 1.3468 |
|
97 |
+
| 1.2747 | 0.41 | 430 | 1.3471 |
|
98 |
+
| 1.3167 | 0.42 | 440 | 1.3460 |
|
99 |
+
| 1.3232 | 0.43 | 450 | 1.3438 |
|
100 |
+
| 1.3628 | 0.44 | 460 | 1.3422 |
|
101 |
+
| 1.3828 | 0.45 | 470 | 1.3417 |
|
102 |
+
| 1.3756 | 0.46 | 480 | 1.3412 |
|
103 |
+
| 1.385 | 0.47 | 490 | 1.3418 |
|
104 |
+
| 1.3622 | 0.48 | 500 | 1.3392 |
|
105 |
+
| 1.3322 | 0.49 | 510 | 1.3381 |
|
106 |
+
| 1.368 | 0.49 | 520 | 1.3365 |
|
107 |
+
| 1.3373 | 0.5 | 530 | 1.3355 |
|
108 |
+
| 1.4931 | 0.51 | 540 | 1.3354 |
|
109 |
+
| 1.3986 | 0.52 | 550 | 1.3333 |
|
110 |
+
| 1.3053 | 0.53 | 560 | 1.3312 |
|
111 |
+
| 1.2736 | 0.54 | 570 | 1.3297 |
|
112 |
+
| 1.2903 | 0.55 | 580 | 1.3298 |
|
113 |
+
| 1.328 | 0.56 | 590 | 1.3290 |
|
114 |
+
| 1.4081 | 0.57 | 600 | 1.3290 |
|
115 |
+
| 1.2852 | 0.58 | 610 | 1.3279 |
|
116 |
+
| 1.3636 | 0.59 | 620 | 1.3268 |
|
117 |
+
| 1.3448 | 0.6 | 630 | 1.3265 |
|
118 |
+
| 1.2061 | 0.61 | 640 | 1.3252 |
|
119 |
+
| 1.3519 | 0.62 | 650 | 1.3244 |
|
120 |
+
| 1.3632 | 0.63 | 660 | 1.3248 |
|
121 |
+
| 1.3784 | 0.64 | 670 | 1.3238 |
|
122 |
+
| 1.3349 | 0.65 | 680 | 1.3216 |
|
123 |
+
| 1.2603 | 0.66 | 690 | 1.3215 |
|
124 |
+
| 1.3566 | 0.67 | 700 | 1.3224 |
|
125 |
+
| 1.316 | 0.68 | 710 | 1.3208 |
|
126 |
+
| 1.1818 | 0.69 | 720 | 1.3203 |
|
127 |
+
| 1.3631 | 0.69 | 730 | 1.3190 |
|
128 |
+
| 1.3234 | 0.7 | 740 | 1.3184 |
|
129 |
+
| 1.2759 | 0.71 | 750 | 1.3177 |
|
130 |
+
| 1.3332 | 0.72 | 760 | 1.3177 |
|
131 |
+
| 1.2764 | 0.73 | 770 | 1.3165 |
|
132 |
+
| 1.2056 | 0.74 | 780 | 1.3155 |
|
133 |
+
| 1.4285 | 0.75 | 790 | 1.3158 |
|
134 |
+
| 1.3733 | 0.76 | 800 | 1.3150 |
|
135 |
+
| 1.2735 | 0.77 | 810 | 1.3143 |
|
136 |
+
| 1.3502 | 0.78 | 820 | 1.3137 |
|
137 |
+
| 1.093 | 0.79 | 830 | 1.3130 |
|
138 |
+
| 1.3451 | 0.8 | 840 | 1.3123 |
|
139 |
+
| 1.2942 | 0.81 | 850 | 1.3119 |
|
140 |
+
| 1.3258 | 0.82 | 860 | 1.3117 |
|
141 |
+
| 1.2139 | 0.83 | 870 | 1.3114 |
|
142 |
+
| 1.2773 | 0.84 | 880 | 1.3109 |
|
143 |
+
| 1.2324 | 0.85 | 890 | 1.3101 |
|
144 |
+
| 1.4134 | 0.86 | 900 | 1.3097 |
|
145 |
+
| 1.3464 | 0.87 | 910 | 1.3095 |
|
146 |
+
| 1.2972 | 0.88 | 920 | 1.3090 |
|
147 |
+
| 1.3305 | 0.88 | 930 | 1.3086 |
|
148 |
+
| 1.3394 | 0.89 | 940 | 1.3082 |
|
149 |
+
| 1.3666 | 0.9 | 950 | 1.3078 |
|
150 |
+
| 1.3703 | 0.91 | 960 | 1.3077 |
|
151 |
+
| 1.3019 | 0.92 | 970 | 1.3077 |
|
152 |
+
| 1.2618 | 0.93 | 980 | 1.3073 |
|
153 |
+
| 1.2808 | 0.94 | 990 | 1.3071 |
|
154 |
+
| 1.2927 | 0.95 | 1000 | 1.3069 |
|
155 |
+
| 1.2688 | 0.96 | 1010 | 1.3067 |
|
156 |
+
| 1.3312 | 0.97 | 1020 | 1.3065 |
|
157 |
+
| 1.2406 | 0.98 | 1030 | 1.3064 |
|
158 |
+
| 1.3341 | 0.99 | 1040 | 1.3062 |
|
159 |
+
| 1.3531 | 1.0 | 1050 | 1.3062 |
|
160 |
+
|
161 |
+
|
162 |
+
### Framework versions
|
163 |
+
|
164 |
+
- PEFT 0.7.1
|
165 |
+
- Transformers 4.36.2
|
166 |
+
- Pytorch 2.1.0+cu121
|
167 |
+
- Datasets 2.16.1
|
168 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
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": 32,
|
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 |
+
"self_attn.o_proj",
|
23 |
+
"self_attn.k_proj",
|
24 |
+
"self_attn.v_proj",
|
25 |
+
"self_attn.q_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f38ce8cd4bda4f6cb0ae2446e04915778c4996ec00325313fe9410f85829d603
|
3 |
+
size 27297032
|
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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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:c0db1c27b4e171bc8bf399197cd830184b9ebcdf54c7cc4010a111f40ee53b2e
|
3 |
+
size 4664
|