Hugging Face's logo

shray98
/
temp

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
shray98 commited on
Commit
f74bd50
·
verified ·
1 Parent(s): 9381b05

End of training

Browse files
Files changed (10) hide show
  1. README.md +63 -0
  2. adapter_config.json +32 -0
  3. adapter_model.safetensors +3 -0
  4. preprocessor_config.json +14 -0
  5. runs/Aug08_10-36-24_hal/events.out.tfevents.1723127825.hal.530769.0 +3 -0
  6. runs/Aug08_12-58-27_hal/events.out.tfevents.1723136310.hal.533927.0 +3 -0
  7. runs/Aug08_15-34-21_hal/events.out.tfevents.1723145663.hal.536523.0 +3 -0
  8. runs/Aug08_15-49-00_hal/events.out.tfevents.1723146651.hal.536890.0 +3 -0
  9. runs/Aug08_16-00-18_hal/events.out.tfevents.1723147336.hal.537292.0 +3 -0
  10. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: openai/whisper-large-v2
3
+ library_name: peft
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: whisper-large-v2-peft
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # whisper-large-v2-peft
16
+
17
+ This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the CFN Proposal Audio dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.3257
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 50
45
+ - num_epochs: 3
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.3738 | 1.0 | 191 | 0.3743 |
53
+ | 0.2406 | 2.0 | 382 | 0.3242 |
54
+ | 0.1474 | 3.0 | 573 | 0.3257 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.12.1.dev0
60
+ - Transformers 4.43.4
61
+ - Pytorch 2.3.1+cu121
62
+ - Datasets 2.20.0
63
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-large-v2",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "v_proj"
28
+ ],
29
+ "task_type": null,
30
+ "use_dora": false,
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f83bd7d12ae83c88c367531cb9262e32b2fefcbe0098f74233cbb15788f24d2
3
+ size 62969640
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/Aug08_10-36-24_hal/events.out.tfevents.1723127825.hal.530769.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775430681c9c724c505ca0fe2238f3caafe2577c7f145022d8f1f5b155a8c7b6
3
+ size 6186
runs/Aug08_12-58-27_hal/events.out.tfevents.1723136310.hal.533927.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff95375764595d141f0b8188a3d1fdaf7375963ae6cbd5ddbd899585489242e
3
+ size 11494
runs/Aug08_15-34-21_hal/events.out.tfevents.1723145663.hal.536523.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21738592c802232a7421e7c7758de9a7835afb0cd53a503619d9f73824b2e77
3
+ size 11490
runs/Aug08_15-49-00_hal/events.out.tfevents.1723146651.hal.536890.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9360f2f9abbacfbb9df57e9e2f1ddc37b84d7216f2d87cf30622f0ae64547c2
3
+ size 11494
runs/Aug08_16-00-18_hal/events.out.tfevents.1723147336.hal.537292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19608d79a8916ba37261d0e1531c854c4cd89af82280e94a6af5fa292fb44d3f
3
+ size 8697
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592fb47456bf56fc10beb09f66bba4aaae6223e44cbf27cd8f51cfced8029087
3
+ size 5304