End of training
Browse files- README.md +105 -0
- adapter_config.json +26 -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 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: radia-fine-tune-mistral-7b-lora
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# radia-fine-tune-mistral-7b-lora
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4616
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0002
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 2
|
42 |
+
- total_train_batch_size: 16
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: constant
|
45 |
+
- lr_scheduler_warmup_ratio: 0.3
|
46 |
+
- num_epochs: 4
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.038 | 0.09 | 5 | 0.7930 |
|
53 |
+
| 0.8312 | 0.17 | 10 | 0.7245 |
|
54 |
+
| 0.6972 | 0.26 | 15 | 0.6791 |
|
55 |
+
| 0.6848 | 0.34 | 20 | 0.6456 |
|
56 |
+
| 0.6457 | 0.43 | 25 | 0.6159 |
|
57 |
+
| 0.6261 | 0.52 | 30 | 0.5927 |
|
58 |
+
| 0.5639 | 0.6 | 35 | 0.5718 |
|
59 |
+
| 0.5723 | 0.69 | 40 | 0.5540 |
|
60 |
+
| 0.5473 | 0.78 | 45 | 0.5389 |
|
61 |
+
| 0.5209 | 0.86 | 50 | 0.5284 |
|
62 |
+
| 0.4591 | 0.95 | 55 | 0.5177 |
|
63 |
+
| 0.5233 | 1.03 | 60 | 0.5080 |
|
64 |
+
| 0.4805 | 1.12 | 65 | 0.5030 |
|
65 |
+
| 0.3604 | 1.21 | 70 | 0.4987 |
|
66 |
+
| 0.3927 | 1.29 | 75 | 0.4907 |
|
67 |
+
| 0.3934 | 1.38 | 80 | 0.4849 |
|
68 |
+
| 0.3859 | 1.47 | 85 | 0.4761 |
|
69 |
+
| 0.3779 | 1.55 | 90 | 0.4748 |
|
70 |
+
| 0.3929 | 1.64 | 95 | 0.4655 |
|
71 |
+
| 0.3973 | 1.72 | 100 | 0.4635 |
|
72 |
+
| 0.3512 | 1.81 | 105 | 0.4599 |
|
73 |
+
| 0.4027 | 1.9 | 110 | 0.4575 |
|
74 |
+
| 0.3917 | 1.98 | 115 | 0.4504 |
|
75 |
+
| 0.3069 | 2.07 | 120 | 0.4667 |
|
76 |
+
| 0.3203 | 2.16 | 125 | 0.4569 |
|
77 |
+
| 0.2807 | 2.24 | 130 | 0.4615 |
|
78 |
+
| 0.2471 | 2.33 | 135 | 0.4612 |
|
79 |
+
| 0.2724 | 2.41 | 140 | 0.4553 |
|
80 |
+
| 0.2976 | 2.5 | 145 | 0.4665 |
|
81 |
+
| 0.2873 | 2.59 | 150 | 0.4551 |
|
82 |
+
| 0.2968 | 2.67 | 155 | 0.4568 |
|
83 |
+
| 0.2577 | 2.76 | 160 | 0.4564 |
|
84 |
+
| 0.2569 | 2.84 | 165 | 0.4496 |
|
85 |
+
| 0.2167 | 2.93 | 170 | 0.4486 |
|
86 |
+
| 0.2785 | 3.02 | 175 | 0.4518 |
|
87 |
+
| 0.176 | 3.1 | 180 | 0.4798 |
|
88 |
+
| 0.1909 | 3.19 | 185 | 0.4588 |
|
89 |
+
| 0.1883 | 3.28 | 190 | 0.4768 |
|
90 |
+
| 0.1806 | 3.36 | 195 | 0.4693 |
|
91 |
+
| 0.1998 | 3.45 | 200 | 0.4732 |
|
92 |
+
| 0.1573 | 3.53 | 205 | 0.4745 |
|
93 |
+
| 0.1908 | 3.62 | 210 | 0.4627 |
|
94 |
+
| 0.2042 | 3.71 | 215 | 0.4695 |
|
95 |
+
| 0.1918 | 3.79 | 220 | 0.4620 |
|
96 |
+
| 0.2163 | 3.88 | 225 | 0.4574 |
|
97 |
+
| 0.2189 | 3.97 | 230 | 0.4616 |
|
98 |
+
|
99 |
+
|
100 |
+
### Framework versions
|
101 |
+
|
102 |
+
- Transformers 4.36.0.dev0
|
103 |
+
- Pytorch 2.1.0+cu118
|
104 |
+
- Datasets 2.15.0
|
105 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-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 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
+
"o_proj",
|
21 |
+
"gate_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1e26eddfea1746db094353ce94c5237587779275f10a34b8a3787c7633f6b90
|
3 |
+
size 92317600
|
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": true,
|
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": true
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:626217f494b3571c6e983b4103e8f492f47f85097ea0d37eb20228fd3e6e6144
|
3 |
+
size 4664
|