Hugging Face's logo

xuliu15
/
32r_LoRA_10m

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
xuliu15 commited on
Commit
a34806a
·
verified ·
1 Parent(s): 1f3450e

End of training

Browse files
Files changed (4) hide show
  1. README.md +17 -5
  2. adapter_model.safetensors +2 -2
  3. runs/May25_13-13-12_a100gpu3/events.out.tfevents.1716635599.a100gpu3.378824.10 +3 -0
  4. 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-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_6_1 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.1163
22
 
23
  ## Model description
24
 
@@ -44,16 +44,28 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 50
47
- - num_epochs: 3.0
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | No log | 1.0 | 15 | 3.9085 |
55
- | 4.3885 | 2.0 | 30 | 2.5102 |
56
- | 4.3885 | 3.0 | 45 | 2.1163 |
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_6_1 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.5372
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 50
47
+ - num_epochs: 15
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | No log | 1.0 | 15 | 3.9123 |
55
+ | 4.3581 | 2.0 | 30 | 2.4747 |
56
+ | 4.3581 | 3.0 | 45 | 2.1013 |
57
+ | 2.0139 | 4.0 | 60 | 1.7239 |
58
+ | 0.8458 | 5.0 | 75 | 1.5361 |
59
+ | 0.8458 | 6.0 | 90 | 1.5255 |
60
+ | 0.2525 | 7.0 | 105 | 1.5009 |
61
+ | 0.2525 | 8.0 | 120 | 1.5346 |
62
+ | 0.0726 | 9.0 | 135 | 1.5020 |
63
+ | 0.0233 | 10.0 | 150 | 1.5250 |
64
+ | 0.0233 | 11.0 | 165 | 1.5127 |
65
+ | 0.0152 | 12.0 | 180 | 1.5213 |
66
+ | 0.0152 | 13.0 | 195 | 1.5306 |
67
+ | 0.0104 | 14.0 | 210 | 1.5349 |
68
+ | 0.0093 | 15.0 | 225 | 1.5372 |
69
 
70
 
71
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a86fe0977f2964aca2db35d22cfa86af24d319ee00c9442fc90b030d4e8350a2
3
- size 14178512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fdaa64a03c02260b54098a09677a8bc5ef829aa235baecfe6fca11a9352ab6
3
+ size 14183408
runs/May25_13-13-12_a100gpu3/events.out.tfevents.1716635599.a100gpu3.378824.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052f86231661541893fd6c73efbd7b43d283f4b8373e07186cf8341a4b15a641
3
+ size 11757
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca6cc67a77c259ac61277be0c743f47b2d03bd1e8d6879ef618a026aad572f5e
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fd1a3c8784c9db0dc3f378bf3c38d92ebdfa8fc915f0c3c1d88a0d80db0dc0
3
  size 5176