End of training
Browse files- README.md +116 -0
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/Mar29_07-14-17_073f1c70a700/events.out.tfevents.1743232566.073f1c70a700.2147.0 +3 -0
- runs/Mar29_07-17-25_073f1c70a700/events.out.tfevents.1743232653.073f1c70a700.2147.1 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
language:
|
4 |
+
- sw
|
5 |
+
license: apache-2.0
|
6 |
+
base_model: openai/whisper-medium
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- fsicoli/common_voice_19_0
|
11 |
+
model-index:
|
12 |
+
- name: eolang/sw-peft-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 |
+
# eolang/sw-peft-2
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 19 dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3697
|
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: 0.001
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 50
|
49 |
+
- num_epochs: 1
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
56 |
+
| 1.5084 | 0.0191 | 100 | 1.0225 |
|
57 |
+
| 0.9199 | 0.0382 | 200 | 0.9041 |
|
58 |
+
| 0.8295 | 0.0573 | 300 | 0.8428 |
|
59 |
+
| 0.8404 | 0.0764 | 400 | 0.8142 |
|
60 |
+
| 0.8215 | 0.0955 | 500 | 0.8141 |
|
61 |
+
| 0.7527 | 0.1147 | 600 | 0.7640 |
|
62 |
+
| 0.7494 | 0.1338 | 700 | 0.7652 |
|
63 |
+
| 0.7693 | 0.1529 | 800 | 0.7081 |
|
64 |
+
| 0.7104 | 0.1720 | 900 | 0.7238 |
|
65 |
+
| 0.6975 | 0.1911 | 1000 | 0.6990 |
|
66 |
+
| 0.7164 | 0.2102 | 1100 | 0.7002 |
|
67 |
+
| 0.6693 | 0.2293 | 1200 | 0.6842 |
|
68 |
+
| 0.7043 | 0.2484 | 1300 | 0.6831 |
|
69 |
+
| 0.6521 | 0.2675 | 1400 | 0.6527 |
|
70 |
+
| 0.6468 | 0.2866 | 1500 | 0.6563 |
|
71 |
+
| 0.6376 | 0.3058 | 1600 | 0.6180 |
|
72 |
+
| 0.6008 | 0.3249 | 1700 | 0.6223 |
|
73 |
+
| 0.6353 | 0.3440 | 1800 | 0.6113 |
|
74 |
+
| 0.5885 | 0.3631 | 1900 | 0.6033 |
|
75 |
+
| 0.598 | 0.3822 | 2000 | 0.5987 |
|
76 |
+
| 0.5749 | 0.4013 | 2100 | 0.5792 |
|
77 |
+
| 0.5714 | 0.4204 | 2200 | 0.5772 |
|
78 |
+
| 0.5438 | 0.4395 | 2300 | 0.5688 |
|
79 |
+
| 0.5442 | 0.4586 | 2400 | 0.5711 |
|
80 |
+
| 0.5165 | 0.4777 | 2500 | 0.5588 |
|
81 |
+
| 0.4971 | 0.4968 | 2600 | 0.5408 |
|
82 |
+
| 0.5026 | 0.5160 | 2700 | 0.5365 |
|
83 |
+
| 0.5278 | 0.5351 | 2800 | 0.5112 |
|
84 |
+
| 0.5371 | 0.5542 | 2900 | 0.5160 |
|
85 |
+
| 0.5013 | 0.5733 | 3000 | 0.5041 |
|
86 |
+
| 0.4867 | 0.5924 | 3100 | 0.4978 |
|
87 |
+
| 0.4938 | 0.6115 | 3200 | 0.4830 |
|
88 |
+
| 0.4522 | 0.6306 | 3300 | 0.4798 |
|
89 |
+
| 0.4515 | 0.6497 | 3400 | 0.4751 |
|
90 |
+
| 0.4593 | 0.6688 | 3500 | 0.4631 |
|
91 |
+
| 0.4539 | 0.6879 | 3600 | 0.4561 |
|
92 |
+
| 0.4557 | 0.7071 | 3700 | 0.4467 |
|
93 |
+
| 0.417 | 0.7262 | 3800 | 0.4419 |
|
94 |
+
| 0.4251 | 0.7453 | 3900 | 0.4368 |
|
95 |
+
| 0.4062 | 0.7644 | 4000 | 0.4277 |
|
96 |
+
| 0.3815 | 0.7835 | 4100 | 0.4271 |
|
97 |
+
| 0.3832 | 0.8026 | 4200 | 0.4155 |
|
98 |
+
| 0.3818 | 0.8217 | 4300 | 0.4098 |
|
99 |
+
| 0.3988 | 0.8408 | 4400 | 0.4005 |
|
100 |
+
| 0.4073 | 0.8599 | 4500 | 0.3964 |
|
101 |
+
| 0.3894 | 0.8790 | 4600 | 0.3898 |
|
102 |
+
| 0.3464 | 0.8981 | 4700 | 0.3858 |
|
103 |
+
| 0.3626 | 0.9173 | 4800 | 0.3800 |
|
104 |
+
| 0.3753 | 0.9364 | 4900 | 0.3771 |
|
105 |
+
| 0.3734 | 0.9555 | 5000 | 0.3733 |
|
106 |
+
| 0.3362 | 0.9746 | 5100 | 0.3718 |
|
107 |
+
| 0.3607 | 0.9937 | 5200 | 0.3697 |
|
108 |
+
|
109 |
+
|
110 |
+
### Framework versions
|
111 |
+
|
112 |
+
- PEFT 0.14.0
|
113 |
+
- Transformers 4.47.0
|
114 |
+
- Pytorch 2.5.1+cu121
|
115 |
+
- Datasets 3.3.1
|
116 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "openai/whisper-medium",
|
8 |
+
"bias": "none",
|
9 |
+
"eva_config": null,
|
10 |
+
"exclude_modules": null,
|
11 |
+
"fan_in_fan_out": false,
|
12 |
+
"inference_mode": true,
|
13 |
+
"init_lora_weights": true,
|
14 |
+
"layer_replication": null,
|
15 |
+
"layers_pattern": null,
|
16 |
+
"layers_to_transform": null,
|
17 |
+
"loftq_config": {},
|
18 |
+
"lora_alpha": 64,
|
19 |
+
"lora_bias": false,
|
20 |
+
"lora_dropout": 0.05,
|
21 |
+
"megatron_config": null,
|
22 |
+
"megatron_core": "megatron.core",
|
23 |
+
"modules_to_save": null,
|
24 |
+
"peft_type": "LORA",
|
25 |
+
"r": 32,
|
26 |
+
"rank_pattern": {},
|
27 |
+
"revision": null,
|
28 |
+
"target_modules": [
|
29 |
+
"q_proj",
|
30 |
+
"v_proj"
|
31 |
+
],
|
32 |
+
"task_type": null,
|
33 |
+
"use_dora": false,
|
34 |
+
"use_rslora": false
|
35 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f87469cc9c7d027fbbfdfb9d69a025aa2c47ef5902e83089891627be9d537fd
|
3 |
+
size 37789960
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 80,
|
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/Mar29_07-14-17_073f1c70a700/events.out.tfevents.1743232566.073f1c70a700.2147.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7229dde2f0f82e73618b1be80f0a689e46dac9c2440e53bab73ec467ca7bb3e5
|
3 |
+
size 7328
|
runs/Mar29_07-17-25_073f1c70a700/events.out.tfevents.1743232653.073f1c70a700.2147.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee252bb4bfb22e077f058cc10770a55270693f33182dfd0e3c5e9044b0466edd
|
3 |
+
size 32737
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd1c679cbf8e1af26be2afca9901deb238954d34480e62744698faff2eec8f2f
|
3 |
+
size 5496
|