Upload model
Browse files- README.md +71 -0
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: distilbert-base-uncased-lora-text-classification
|
10 |
+
results: []
|
11 |
+
library_name: peft
|
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 |
+
# distilbert-base-uncased-lora-text-classification
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0049
|
22 |
+
- Accuracy: {'accuracy': 0.883}
|
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: 0.001
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 10
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
|
53 |
+
| No log | 1.0 | 250 | 0.3972 | {'accuracy': 0.858} |
|
54 |
+
| 0.4079 | 2.0 | 500 | 0.4154 | {'accuracy': 0.878} |
|
55 |
+
| 0.4079 | 3.0 | 750 | 0.6355 | {'accuracy': 0.87} |
|
56 |
+
| 0.1558 | 4.0 | 1000 | 0.7310 | {'accuracy': 0.876} |
|
57 |
+
| 0.1558 | 5.0 | 1250 | 0.8508 | {'accuracy': 0.877} |
|
58 |
+
| 0.0432 | 6.0 | 1500 | 0.9112 | {'accuracy': 0.876} |
|
59 |
+
| 0.0432 | 7.0 | 1750 | 1.0137 | {'accuracy': 0.873} |
|
60 |
+
| 0.0208 | 8.0 | 2000 | 0.9952 | {'accuracy': 0.88} |
|
61 |
+
| 0.0208 | 9.0 | 2250 | 0.9904 | {'accuracy': 0.881} |
|
62 |
+
| 0.0035 | 10.0 | 2500 | 1.0049 | {'accuracy': 0.883} |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- PEFT 0.5.0
|
68 |
+
- Transformers 4.32.1
|
69 |
+
- Pytorch 2.1.0.dev20230905
|
70 |
+
- Datasets 2.14.4
|
71 |
+
- Tokenizers 0.13.3
|
adapter_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "distilbert-base-uncased",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.01,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_lin"
|
18 |
+
],
|
19 |
+
"task_type": "SEQ_CLS"
|
20 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0173313b7aaa52287e75f0aa50180806d9f6bee89dc3aa1a608b09da3ccc48d1
|
3 |
+
size 2669598
|