End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Eimhin03/output_model_shunyalabs_data_base_model
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: output_model_shunyalabs_data_base_model_more_steps
|
| 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 |
+
# output_model_shunyalabs_data_base_model_more_steps
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Eimhin03/output_model_shunyalabs_data_base_model](https://huggingface.co/Eimhin03/output_model_shunyalabs_data_base_model) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.8582
|
| 22 |
+
- Wer: 28.5187
|
| 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: 0.0001
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- training_steps: 100000
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-------:|:------:|:---------------:|:-------:|
|
| 55 |
+
| 0.0443 | 7.8125 | 10000 | 0.8899 | 40.4519 |
|
| 56 |
+
| 0.0167 | 15.625 | 20000 | 0.9089 | 36.5973 |
|
| 57 |
+
| 0.0206 | 23.4375 | 30000 | 0.9090 | 34.8545 |
|
| 58 |
+
| 0.0031 | 31.25 | 40000 | 0.8985 | 34.9284 |
|
| 59 |
+
| 0.0016 | 39.0625 | 50000 | 0.9108 | 34.0718 |
|
| 60 |
+
| 0.0008 | 46.875 | 60000 | 0.8898 | 32.7426 |
|
| 61 |
+
| 0.0004 | 54.6875 | 70000 | 0.8897 | 30.7931 |
|
| 62 |
+
| 0.0003 | 62.5 | 80000 | 0.8849 | 30.2023 |
|
| 63 |
+
| 0.0000 | 70.3125 | 90000 | 0.8603 | 29.9365 |
|
| 64 |
+
| 0.0000 | 78.125 | 100000 | 0.8582 | 28.5187 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 5.2.0.dev0
|
| 70 |
+
- Pytorch 2.9.0+cu126
|
| 71 |
+
- Datasets 4.0.0
|
| 72 |
+
- Tokenizers 0.22.2
|