Hugging Face's logo

Samandards
/
temp

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Samandards commited on
Commit
9f83121
•
1 Parent(s): aa7f811

Samandards/fine-tune-300

Browse files
Files changed (12) hide show
  1. README.md +5 -5
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +2 -2
  4. runs/Jun27_11-43-05_ee932f09385c/events.out.tfevents.1719488586.ee932f09385c.23217.0 +3 -0
  5. runs/Jun27_11-43-43_ee932f09385c/events.out.tfevents.1719488624.ee932f09385c.23217.1 +3 -0
  6. runs/Jun27_11-44-16_ee932f09385c/events.out.tfevents.1719488658.ee932f09385c.23217.2 +3 -0
  7. runs/Jun27_11-44-34_ee932f09385c/events.out.tfevents.1719488676.ee932f09385c.23217.3 +3 -0
  8. runs/Jun27_11-44-50_ee932f09385c/events.out.tfevents.1719488692.ee932f09385c.23217.4 +3 -0
  9. runs/Jun27_11-45-12_ee932f09385c/events.out.tfevents.1719488714.ee932f09385c.23217.5 +3 -0
  10. runs/Jun27_11-45-25_ee932f09385c/events.out.tfevents.1719488726.ee932f09385c.23217.6 +3 -0
  11. runs/Jun27_11-49-12_ee932f09385c/events.out.tfevents.1719488953.ee932f09385c.31350.0 +3 -0
  12. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_14_0 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.0173
22
 
23
  ## Model description
24
 
@@ -38,8 +38,8 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.001
41
- - train_batch_size: 32
42
- - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | No log | 1.0 | 10 | 3.0208 |
55
- | No log | 2.0 | 20 | 2.0173 |
56
 
57
 
58
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_14_0 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.0663
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.001
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.2676 | 1.0 | 151 | 1.1656 |
55
+ | 0.8175 | 2.0 | 302 | 1.0663 |
56
 
57
 
58
  ### Framework versions
adapter_config.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": {
4
- "base_model_class": "PeftModel",
5
- "parent_library": "peft.peft_model"
6
  },
7
- "base_model_name_or_path": null,
8
  "bias": "none",
9
  "fan_in_fan_out": false,
10
  "inference_mode": true,
@@ -13,13 +13,13 @@
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": [
 
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,
 
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
+ "lora_alpha": 8,
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": 4,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b5853f230fc56b2fb40ccada51b590f0e0f8d0cb92aef12d179e121add0d1e2
3
- size 62989224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b875ad4e6b7a923bc700444a532ca1c8eda88c100c009f22e1b1d7f5199bb57e
3
+ size 7918280
runs/Jun27_11-43-05_ee932f09385c/events.out.tfevents.1719488586.ee932f09385c.23217.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c715d7c520c2795aeb519219d0a6971d788f12c396b5c78de02bfb138fe3dad
3
+ size 6132
runs/Jun27_11-43-43_ee932f09385c/events.out.tfevents.1719488624.ee932f09385c.23217.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a078480ffd7f58631b1a09eaa460345d22e13d71c8af9eb0d58f20c0e80bbb94
3
+ size 4184
runs/Jun27_11-44-16_ee932f09385c/events.out.tfevents.1719488658.ee932f09385c.23217.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e04c5c385d8a7f438a25db45f1e1bb99d6a7cc07d3dbffb4c28e8c783acfa8
3
+ size 4184
runs/Jun27_11-44-34_ee932f09385c/events.out.tfevents.1719488676.ee932f09385c.23217.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a459179ff2e38a583bd8f862e9d4da74801f52265b491bd8b3671d5a4198e74c
3
+ size 4184
runs/Jun27_11-44-50_ee932f09385c/events.out.tfevents.1719488692.ee932f09385c.23217.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd468cf60ca71f500530085be06ab92c5b22bfe825c8de9c471fd0a27003fc8
3
+ size 4184
runs/Jun27_11-45-12_ee932f09385c/events.out.tfevents.1719488714.ee932f09385c.23217.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a7929567d90c1265f34f6d5e903342f1929c21de094c369d420c8268a46da8
3
+ size 4184
runs/Jun27_11-45-25_ee932f09385c/events.out.tfevents.1719488726.ee932f09385c.23217.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8f77446040d14f42b7e63b24b6a3c97bbc62e834eb5f6d7d0388d4660d15b9
3
+ size 4184
runs/Jun27_11-49-12_ee932f09385c/events.out.tfevents.1719488953.ee932f09385c.31350.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1351639ae5fd6a63179b3b138b7c28fe78afd08b7025f2fc78b614832fef5285
3
+ size 9538
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83ece4177ecedbd4559e1582eb16dd06e2ffaa4d7446936897f54fb492d98f33
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ea730e8e63071c7043b70dff341110d268b6fc3cc25a9e49e8d0f02367edc1
3
  size 5240