Hugging Face's logo

xuliu15
/
English_32r_LoRA_1h

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
xuliu15 commited on
Commit
aea07a0
•
1 Parent(s): a7ff898

End of training

Browse files
Files changed (14) hide show
  1. README.md +18 -3
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +2 -2
  4. runs/May24_18-29-03_a100gpu5/events.out.tfevents.1716568161.a100gpu5.2421461.12 +3 -0
  5. runs/May24_18-29-03_a100gpu5/events.out.tfevents.1716568181.a100gpu5.2421461.13 +3 -0
  6. runs/May24_18-30-06_a100gpu5/events.out.tfevents.1716568218.a100gpu5.2421461.14 +3 -0
  7. runs/May24_18-39-39_a100gpu5/events.out.tfevents.1716568787.a100gpu5.2421461.15 +3 -0
  8. runs/May24_18-39-39_a100gpu5/events.out.tfevents.1716568807.a100gpu5.2421461.16 +3 -0
  9. runs/May24_18-40-31_a100gpu5/events.out.tfevents.1716568838.a100gpu5.2421461.17 +3 -0
  10. runs/May24_18-40-31_a100gpu5/events.out.tfevents.1716568854.a100gpu5.2421461.18 +3 -0
  11. runs/May24_18-45-43_a100gpu5/events.out.tfevents.1716569151.a100gpu5.2421461.19 +3 -0
  12. runs/May24_18-48-05_a100gpu5/events.out.tfevents.1716569309.a100gpu5.2421461.20 +3 -0
  13. runs/May24_18-51-40_a100gpu5/events.out.tfevents.1716569510.a100gpu5.2421461.21 +3 -0
  14. training_args.bin +1 -1
README.md CHANGED
@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
  # Whisper Small English 1h
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the librispeech dataset.
 
 
20
 
21
  ## Model description
22
 
@@ -37,14 +39,27 @@ More information needed
37
  The following hyperparameters were used during training:
38
  - learning_rate: 1e-06
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: 500
45
- - training_steps: 1000
46
  - mixed_precision_training: Native AMP
47
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - PEFT 0.10.0
 
17
  # Whisper Small English 1h
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the librispeech dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.1439
22
 
23
  ## Model description
24
 
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-06
41
  - train_batch_size: 8
42
+ - eval_batch_size: 4
43
  - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 50
49
+ - num_epochs: 5
50
  - mixed_precision_training: Native AMP
51
 
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | No log | 0.9744 | 19 | 2.1913 |
57
+ | 1.3757 | 2.0 | 39 | 2.1791 |
58
+ | 1.3932 | 2.9744 | 58 | 2.1605 |
59
+ | 1.3541 | 4.0 | 78 | 2.1477 |
60
+ | 1.3541 | 4.8718 | 95 | 2.1439 |
61
+
62
+
63
  ### Framework versions
64
 
65
  - PEFT 0.10.0
adapter_config.json CHANGED
@@ -1,10 +1,10 @@
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-small",
8
  "bias": "none",
9
  "fan_in_fan_out": false,
10
  "inference_mode": true,
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7fe9c6a3ea803b8811057b21591fd979e347b8c260acad92ea0075fd5c5011
3
- size 14176064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4153156a54f7050d5b3d54208d038bfc32207fbc9740347a4e1649d40ff8650e
3
+ size 14180960
runs/May24_18-29-03_a100gpu5/events.out.tfevents.1716568161.a100gpu5.2421461.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e368c87166f7f6d99e41d149f048484021553bd1ddff38d87399df31df816f66
3
+ size 5517
runs/May24_18-29-03_a100gpu5/events.out.tfevents.1716568181.a100gpu5.2421461.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a83e24bbbfee68a26b458cce8567f5d92b73b8de41becb276ed401227173fd
3
+ size 5517
runs/May24_18-30-06_a100gpu5/events.out.tfevents.1716568218.a100gpu5.2421461.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fa0516c36071fa6a145706b6395d52c23fd45e8bd93e2de1399e9aa5157cb3
3
+ size 5517
runs/May24_18-39-39_a100gpu5/events.out.tfevents.1716568787.a100gpu5.2421461.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946830d19722e667225a0da64c7d73e6e89e80c2d07fb3cda03ce6229791138c
3
+ size 5517
runs/May24_18-39-39_a100gpu5/events.out.tfevents.1716568807.a100gpu5.2421461.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0dde07f5e5c14583a30bc35b32104bc1d4bda8af09eabb1e1d44429c2c4e567
3
+ size 5517
runs/May24_18-40-31_a100gpu5/events.out.tfevents.1716568838.a100gpu5.2421461.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0950d3510037ec040dbd66e7eaaeb1c87cfb59b2f112a5d156a6a39699406fa2
3
+ size 5517
runs/May24_18-40-31_a100gpu5/events.out.tfevents.1716568854.a100gpu5.2421461.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f2ae852221d54d0cef78a2a31e0109d7030f6d70d011f57bf45bc8e45edc55
3
+ size 5724
runs/May24_18-45-43_a100gpu5/events.out.tfevents.1716569151.a100gpu5.2421461.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91af591e019f20f6f6c95daf88de0010a49e95a0293cb187c734aed5306f508b
3
+ size 5724
runs/May24_18-48-05_a100gpu5/events.out.tfevents.1716569309.a100gpu5.2421461.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9bc6c8f58eba8d01bb6ea56efb94d3337a3a6b1099a6f624c750cf58e8f3bc
3
+ size 5517
runs/May24_18-51-40_a100gpu5/events.out.tfevents.1716569510.a100gpu5.2421461.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:877330029b7d1497edf12eedec73ebb1929680f9ce68acbb05f4f70b75dcd497
3
+ size 7816
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:837816d131a3f9f5b0a9f42de3ed679ede040c18b3481f2199d21913ffa0e692
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:902bb609ad4ac1b4da303f86c3f183a488e834f9d1e48d97f97f0b7dfc3c7d41
3
  size 5176