mistral-lp2-org_aug_b
Browse files- README.md +77 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +50 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: mistralai/Mistral-7B-v0.1
|
7 |
+
model-index:
|
8 |
+
- name: org_model
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# org_model
|
16 |
+
|
17 |
+
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.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.9527
|
20 |
+
- F1 Micro: 0.8011
|
21 |
+
- F1 Macro: 0.7779
|
22 |
+
- F1 Weighted: 0.8108
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.0001
|
42 |
+
- train_batch_size: 32
|
43 |
+
- eval_batch_size: 32
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- training_steps: 400
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|
|
53 |
+
| 1.5515 | 0.0064 | 25 | 1.3111 | 0.7801 | 0.7504 | 0.7890 |
|
54 |
+
| 1.2983 | 0.0127 | 50 | 1.2188 | 0.7748 | 0.7572 | 0.7891 |
|
55 |
+
| 1.2193 | 0.0191 | 75 | 1.1271 | 0.7855 | 0.7583 | 0.7937 |
|
56 |
+
| 1.1269 | 0.0255 | 100 | 1.0890 | 0.7952 | 0.7639 | 0.8015 |
|
57 |
+
| 1.0734 | 0.0318 | 125 | 1.0594 | 0.7949 | 0.7635 | 0.8008 |
|
58 |
+
| 1.0384 | 0.0382 | 150 | 1.0389 | 0.7857 | 0.7614 | 0.7937 |
|
59 |
+
| 1.0168 | 0.0446 | 175 | 1.0126 | 0.8045 | 0.7794 | 0.8133 |
|
60 |
+
| 1.0043 | 0.0510 | 200 | 0.9998 | 0.8034 | 0.7786 | 0.8123 |
|
61 |
+
| 1.0406 | 0.0573 | 225 | 0.9874 | 0.8074 | 0.7803 | 0.8153 |
|
62 |
+
| 1.0488 | 0.0637 | 250 | 0.9838 | 0.7922 | 0.7664 | 0.8000 |
|
63 |
+
| 0.9894 | 0.0701 | 275 | 0.9673 | 0.8034 | 0.7780 | 0.8122 |
|
64 |
+
| 0.9969 | 0.0764 | 300 | 0.9629 | 0.7992 | 0.7720 | 0.8069 |
|
65 |
+
| 1.0047 | 0.0828 | 325 | 0.9655 | 0.8000 | 0.7689 | 0.8058 |
|
66 |
+
| 0.9812 | 0.0892 | 350 | 0.9623 | 0.8049 | 0.7839 | 0.8159 |
|
67 |
+
| 0.9681 | 0.0955 | 375 | 0.9551 | 0.8016 | 0.7794 | 0.8118 |
|
68 |
+
| 1.0594 | 0.1019 | 400 | 0.9527 | 0.8011 | 0.7779 | 0.8108 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- PEFT 0.10.0
|
74 |
+
- Transformers 4.40.2
|
75 |
+
- Pytorch 2.3.0+cu118
|
76 |
+
- Datasets 2.19.0
|
77 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": 8,
|
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 |
+
"q_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "SEQ_CLS",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b85215f09cdaa6df88c3cc47626b89e43c3e757c0812dfd8eb6bf5146d5812a
|
3 |
+
size 578898352
|
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 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"32000": {
|
30 |
+
"content": "[LP2]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [],
|
39 |
+
"bos_token": "<s>",
|
40 |
+
"clean_up_tokenization_spaces": false,
|
41 |
+
"eos_token": "</s>",
|
42 |
+
"legacy": true,
|
43 |
+
"model_max_length": 1000000000000000019884624838656,
|
44 |
+
"pad_token": "</s>",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"tokenizer_class": "LlamaTokenizer",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": false
|
50 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30e08f5be53f4133530eaeb78ee7110f2419649486cf505c3734bc1d9de5378e
|
3 |
+
size 4920
|