mistral-lora-token-classification
Browse files- README.md +73 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- accuracy
|
10 |
+
base_model: mistralai/Mistral-7B-v0.1
|
11 |
+
model-index:
|
12 |
+
- name: mistral-lora-token-classification
|
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 |
+
# mistral-lora-token-classification
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.0675
|
24 |
+
- Precision: 0.7504
|
25 |
+
- Recall: 0.6836
|
26 |
+
- F1-score: 0.7154
|
27 |
+
- Accuracy: 0.7676
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.0001
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: constant
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 5
|
54 |
+
- mixed_precision_training: Native AMP
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1-score | Accuracy |
|
59 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
|
60 |
+
| 1.3948 | 1.0 | 762 | 1.2063 | 0.7208 | 0.6344 | 0.6748 | 0.7387 |
|
61 |
+
| 0.8588 | 2.0 | 1524 | 1.1396 | 0.6313 | 0.8310 | 0.7175 | 0.7203 |
|
62 |
+
| 0.7512 | 3.0 | 2286 | 1.0329 | 0.7281 | 0.7404 | 0.7342 | 0.7708 |
|
63 |
+
| 0.6143 | 4.0 | 3048 | 1.0510 | 0.6917 | 0.7512 | 0.7202 | 0.7505 |
|
64 |
+
| 0.5564 | 5.0 | 3810 | 1.0675 | 0.7504 | 0.6836 | 0.7154 | 0.7676 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- PEFT 0.9.0
|
70 |
+
- Transformers 4.38.2
|
71 |
+
- Pytorch 2.1.0+cu121
|
72 |
+
- Datasets 2.18.0
|
73 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
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": 2,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "SEQ_CLS",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f01fa178f33300b3c72ee4d1bbc92985a4b8c34b00a423e1fa0d194073befceb
|
3 |
+
size 3457552
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d76a2e9aa8dac7924fcc09c9becee6c3070880df72137455dcd363c497ef3006
|
3 |
+
size 4920
|