End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: speech_emotion_is25
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# speech_emotion_is25
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.9786
|
| 22 |
+
- F1: 0.1507
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 32
|
| 43 |
+
- eval_batch_size: 32
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 10
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 56 |
+
| 8.3207 | 1.0 | 73 | 2.0793 | 0.0288 |
|
| 57 |
+
| 8.3072 | 2.0 | 146 | 2.0790 | 0.0379 |
|
| 58 |
+
| 8.2824 | 3.0 | 219 | 2.0707 | 0.1134 |
|
| 59 |
+
| 8.178 | 4.0 | 292 | 2.0244 | 0.1204 |
|
| 60 |
+
| 8.0941 | 5.0 | 365 | 2.0037 | 0.1380 |
|
| 61 |
+
| 8.0498 | 6.0 | 438 | 1.9927 | 0.1395 |
|
| 62 |
+
| 7.9997 | 7.0 | 511 | 1.9860 | 0.1379 |
|
| 63 |
+
| 7.9315 | 8.0 | 584 | 1.9829 | 0.1485 |
|
| 64 |
+
| 7.9988 | 9.0 | 657 | 1.9797 | 0.1464 |
|
| 65 |
+
| 7.9838 | 9.8690 | 720 | 1.9786 | 0.1507 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.47.1
|
| 71 |
+
- Pytorch 2.5.1+cu121
|
| 72 |
+
- Datasets 3.2.0
|
| 73 |
+
- Tokenizers 0.21.0
|