zeon8985army
commited on
Commit
•
c8537a2
1
Parent(s):
6052b6e
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: zeon8985army/IndonesiaLukasLargeV3_2
|
3 |
+
datasets:
|
4 |
+
- '-'
|
5 |
+
language:
|
6 |
+
- id
|
7 |
+
library_name: peft
|
8 |
+
tags:
|
9 |
+
- id-asr-leaderboard
|
10 |
+
- generated_from_trainer
|
11 |
+
model-index:
|
12 |
+
- name: zeon8985army/IndonesiaLukasLargeV3_3
|
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 |
+
# zeon8985army/IndonesiaLukasLargeV3_3
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [zeon8985army/IndonesiaLukasLargeV3_3](https://huggingface.co/zeon8985army/IndonesiaLukasLargeV3_3) on the Mozilla & GoogleFleur dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1630
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 6e-05
|
43 |
+
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 16
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 12
|
49 |
+
- training_steps: 585
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
56 |
+
| 0.1375 | 0.1047 | 36 | 0.1698 |
|
57 |
+
| 0.1478 | 0.2093 | 72 | 0.1691 |
|
58 |
+
| 0.1443 | 0.3140 | 108 | 0.1684 |
|
59 |
+
| 0.1428 | 0.4186 | 144 | 0.1679 |
|
60 |
+
| 0.1339 | 0.5233 | 180 | 0.1675 |
|
61 |
+
| 0.1442 | 0.6279 | 216 | 0.1666 |
|
62 |
+
| 0.1473 | 0.7326 | 252 | 0.1666 |
|
63 |
+
| 0.1372 | 0.8372 | 288 | 0.1662 |
|
64 |
+
| 0.1585 | 0.9419 | 324 | 0.1650 |
|
65 |
+
| 0.1356 | 1.0465 | 360 | 0.1642 |
|
66 |
+
| 0.1402 | 1.1512 | 396 | 0.1639 |
|
67 |
+
| 0.1245 | 1.2558 | 432 | 0.1627 |
|
68 |
+
| 0.1231 | 1.3605 | 468 | 0.1635 |
|
69 |
+
| 0.1345 | 1.4651 | 504 | 0.1631 |
|
70 |
+
| 0.1256 | 1.5698 | 540 | 0.1636 |
|
71 |
+
| 0.1426 | 1.6744 | 576 | 0.1630 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- PEFT 0.9.0
|
77 |
+
- Transformers 4.44.2
|
78 |
+
- Pytorch 2.4.1+cu121
|
79 |
+
- Datasets 3.0.1
|
80 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "WhisperForConditionalGeneration",
|
5 |
+
"parent_library": "transformers.models.whisper.modeling_whisper"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "zeon8985army/IndonesiaLukasLargeV3_2",
|
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 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 64,
|
16 |
+
"lora_dropout": 0.1,
|
17 |
+
"megatron_config": null,
|
18 |
+
"megatron_core": "megatron.core",
|
19 |
+
"modules_to_save": null,
|
20 |
+
"peft_type": "LORA",
|
21 |
+
"r": 32,
|
22 |
+
"rank_pattern": {},
|
23 |
+
"revision": null,
|
24 |
+
"target_modules": [
|
25 |
+
"q_proj",
|
26 |
+
"v_proj"
|
27 |
+
],
|
28 |
+
"task_type": null,
|
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 sha256:1a337a622c25dca9ec72cd567c50ed145850d966dabecfd51fc54d375ea82c88
|
3 |
+
size 62969640
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 128,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
runs/Oct11_10-53-06_646df5c95099/events.out.tfevents.1728644003.646df5c95099.1185.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:464d740b54e5e5b223d5bd1482ce8b7190ad54491ee9eb0e497c7e86a0790470
|
3 |
+
size 14347
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf95eb3b6fb86d971e7896226d8dbd4698cf2ba53baead9069972ebcd236ec20
|
3 |
+
size 5368
|