End of training
Browse files- README.md +88 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/Oct11_07-30-06_c5413c524785/events.out.tfevents.1728631821.c5413c524785.352.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: zeon8985army/IndonesiaLukasLargeV3
|
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/IndonesiaLukasLargeV3-2
|
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/IndonesiaLukasLargeV3-2
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [zeon8985army/IndonesiaLukasLargeV3-2](https://huggingface.co/zeon8985army/IndonesiaLukasLargeV3-2) on the Mozilla & GoogleFleur dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1613
|
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: 552
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
56 |
+
| 0.2396 | 0.0785 | 23 | 0.2246 |
|
57 |
+
| 0.2199 | 0.1570 | 46 | 0.2234 |
|
58 |
+
| 0.1963 | 0.2355 | 69 | 0.2176 |
|
59 |
+
| 0.206 | 0.3140 | 92 | 0.2117 |
|
60 |
+
| 0.1755 | 0.3925 | 115 | 0.1899 |
|
61 |
+
| 0.1713 | 0.4710 | 138 | 0.2041 |
|
62 |
+
| 0.2126 | 0.5495 | 161 | 0.1806 |
|
63 |
+
| 0.1778 | 0.6280 | 184 | 0.1787 |
|
64 |
+
| 0.1646 | 0.7065 | 207 | 0.1767 |
|
65 |
+
| 0.1674 | 0.7850 | 230 | 0.1746 |
|
66 |
+
| 0.1545 | 0.8635 | 253 | 0.1725 |
|
67 |
+
| 0.1742 | 0.9420 | 276 | 0.1708 |
|
68 |
+
| 0.1434 | 1.0205 | 299 | 0.1687 |
|
69 |
+
| 0.15 | 1.0990 | 322 | 0.1679 |
|
70 |
+
| 0.1374 | 1.1775 | 345 | 0.1671 |
|
71 |
+
| 0.136 | 1.2560 | 368 | 0.1650 |
|
72 |
+
| 0.1407 | 1.3345 | 391 | 0.1642 |
|
73 |
+
| 0.153 | 1.4130 | 414 | 0.1629 |
|
74 |
+
| 0.1505 | 1.4915 | 437 | 0.1632 |
|
75 |
+
| 0.1543 | 1.5700 | 460 | 0.1624 |
|
76 |
+
| 0.1394 | 1.6485 | 483 | 0.1616 |
|
77 |
+
| 0.1255 | 1.7270 | 506 | 0.1617 |
|
78 |
+
| 0.1342 | 1.8055 | 529 | 0.1613 |
|
79 |
+
| 0.1459 | 1.8840 | 552 | 0.1613 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- PEFT 0.9.0
|
85 |
+
- Transformers 4.44.2
|
86 |
+
- Pytorch 2.4.1+cu121
|
87 |
+
- Datasets 3.0.1
|
88 |
+
- 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",
|
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 sha256:1fbe76dc9655dc7bf2d8975b5763dc824d30e58838f901a2341d798a8c329181
|
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_07-30-06_c5413c524785/events.out.tfevents.1728631821.c5413c524785.352.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d91873eda93c2441f9336a3fdabff81ff9b00b0a7f97dc5d3f0731badc303389
|
3 |
+
size 18183
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:975e4b155394d88023574701fdf5ff967c2544556d3bf2450fc72bb49fc39315
|
3 |
+
size 5368
|