End of training
Browse files
README.md
CHANGED
|
@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# whisper-base-akan-v1
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.0715
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,37 +33,19 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate:
|
| 39 |
- train_batch_size: 16
|
| 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 |
-
- training_steps:
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
-
### Training results
|
| 49 |
-
|
| 50 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
-
| 1.8659 | 5.0 | 250 | 1.6244 |
|
| 53 |
-
| 1.2252 | 10.0 | 500 | 1.3473 |
|
| 54 |
-
| 1.0708 | 15.0 | 750 | 1.2260 |
|
| 55 |
-
| 0.922 | 20.0 | 1000 | 1.1617 |
|
| 56 |
-
| 0.8532 | 25.0 | 1250 | 1.1217 |
|
| 57 |
-
| 0.7747 | 30.0 | 1500 | 1.0973 |
|
| 58 |
-
| 0.7356 | 35.0 | 1750 | 1.0864 |
|
| 59 |
-
| 0.6894 | 40.0 | 2000 | 1.0767 |
|
| 60 |
-
| 0.6671 | 45.0 | 2250 | 1.0746 |
|
| 61 |
-
| 0.642 | 50.0 | 2500 | 1.0719 |
|
| 62 |
-
| 0.6306 | 55.0 | 2750 | 1.0707 |
|
| 63 |
-
| 0.6225 | 60.0 | 3000 | 1.0715 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
-
- PEFT 0.13.
|
| 69 |
- Transformers 4.44.2
|
| 70 |
- Pytorch 2.4.1+cu121
|
| 71 |
- Datasets 3.0.1
|
|
|
|
| 15 |
# whisper-base-akan-v1
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 1e-05
|
| 37 |
- train_batch_size: 16
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- lr_scheduler_warmup_steps: 50
|
| 43 |
+
- training_steps: 2000
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
+
- PEFT 0.13.3.dev0
|
| 49 |
- Transformers 4.44.2
|
| 50 |
- Pytorch 2.4.1+cu121
|
| 51 |
- Datasets 3.0.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b8ae7f43a782a7b30a0d4776d643910e5a9765d8b0173430c43b391ebd04f41
|
| 3 |
size 4728680
|
runs/Oct13_23-57-47_98cca06a2d23/events.out.tfevents.1728863869.98cca06a2d23.828.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db284859fbcdb97407aaa413ed143e58c939eb160378c6effd0e61dd5d8a659c
|
| 3 |
+
size 88
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:303e7d5e843cca2a33d629278d84865964172bbf0fa7b76ab7c9459f6ed0e636
|
| 3 |
size 5432
|