ThreeBlessings
commited on
Commit
•
02f258c
1
Parent(s):
18e2547
Upload model
Browse files- README.md +97 -0
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- marsyas/gtzan
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
base_model: ntu-spml/distilhubert
|
11 |
+
model-index:
|
12 |
+
- name: distilhubert-finetuned-gtzan
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
type: audio-classification
|
16 |
+
name: Audio Classification
|
17 |
+
dataset:
|
18 |
+
name: GTZAN
|
19 |
+
type: marsyas/gtzan
|
20 |
+
split: None
|
21 |
+
metrics:
|
22 |
+
- type: accuracy
|
23 |
+
value: 0.9319319319319319
|
24 |
+
name: Accuracy
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# distilhubert-finetuned-gtzan
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.2387
|
35 |
+
- Accuracy: 0.9319
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.001
|
55 |
+
- train_batch_size: 6
|
56 |
+
- eval_batch_size: 6
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
61 |
+
- num_epochs: 15
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 1.7644 | 1.0 | 167 | 1.7832 | 0.3554 |
|
69 |
+
| 1.2856 | 2.0 | 334 | 1.4226 | 0.4745 |
|
70 |
+
| 1.2123 | 3.0 | 501 | 1.0047 | 0.6737 |
|
71 |
+
| 0.6613 | 4.0 | 668 | 0.8091 | 0.6987 |
|
72 |
+
| 0.6442 | 5.0 | 835 | 0.6713 | 0.7858 |
|
73 |
+
| 0.7172 | 6.0 | 1002 | 0.5749 | 0.8238 |
|
74 |
+
| 0.5394 | 7.0 | 1169 | 0.5079 | 0.8408 |
|
75 |
+
| 0.3853 | 8.0 | 1336 | 0.4574 | 0.8539 |
|
76 |
+
| 0.5441 | 9.0 | 1503 | 0.3729 | 0.8869 |
|
77 |
+
| 0.5062 | 10.0 | 1670 | 0.3319 | 0.9009 |
|
78 |
+
| 0.3955 | 11.0 | 1837 | 0.3745 | 0.8849 |
|
79 |
+
| 0.3112 | 12.0 | 2004 | 0.2752 | 0.9289 |
|
80 |
+
| 0.2887 | 13.0 | 2171 | 0.2544 | 0.9289 |
|
81 |
+
| 0.2038 | 14.0 | 2338 | 0.2344 | 0.9329 |
|
82 |
+
| 0.2374 | 15.0 | 2505 | 0.2387 | 0.9319 |
|
83 |
+
|
84 |
+
|
85 |
+
### Framework versions
|
86 |
+
|
87 |
+
- Transformers 4.35.2
|
88 |
+
- Pytorch 2.1.1+cu121
|
89 |
+
- Datasets 2.15.0
|
90 |
+
- Tokenizers 0.15.0
|
91 |
+
## Training procedure
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
|
97 |
+
- PEFT 0.6.2
|
adapter_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "HubertForSequenceClassification",
|
5 |
+
"parent_library": "transformers.models.hubert.modeling_hubert"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "ntu-spml/distilhubert",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"lora_alpha": 1,
|
15 |
+
"lora_dropout": 0.0,
|
16 |
+
"modules_to_save": [
|
17 |
+
"classifier"
|
18 |
+
],
|
19 |
+
"peft_type": "LORA",
|
20 |
+
"r": 1,
|
21 |
+
"rank_pattern": {},
|
22 |
+
"revision": null,
|
23 |
+
"target_modules": [
|
24 |
+
"output_dense",
|
25 |
+
"projector",
|
26 |
+
"out_proj",
|
27 |
+
"q_proj",
|
28 |
+
"intermediate_dense",
|
29 |
+
"k_proj",
|
30 |
+
"v_proj"
|
31 |
+
],
|
32 |
+
"task_type": null
|
33 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4972889e485c53e67906a9e6e3a78133c5bdf3324e5715ac7f9dd9407a9856ba
|
3 |
+
size 128760
|