End of training
Browse files- README.md +109 -0
- generation_config.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: Mehrdad-S/common_voice_clone
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: common_voice_clone_continued
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# common_voice_clone_continued
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [Mehrdad-S/common_voice_clone](https://huggingface.co/Mehrdad-S/common_voice_clone) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.4442
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 3e-06
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 64
|
| 43 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- training_steps: 5000
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 52 |
+
| 0.4885 | 0.4002 | 100 | 0.4510 |
|
| 53 |
+
| 0.486 | 0.8004 | 200 | 0.4516 |
|
| 54 |
+
| 0.4836 | 1.2041 | 300 | 0.4500 |
|
| 55 |
+
| 0.4803 | 1.6043 | 400 | 0.4493 |
|
| 56 |
+
| 0.4873 | 2.0080 | 500 | 0.4510 |
|
| 57 |
+
| 0.4833 | 2.4082 | 600 | 0.4495 |
|
| 58 |
+
| 0.4869 | 2.8084 | 700 | 0.4486 |
|
| 59 |
+
| 0.4802 | 3.2121 | 800 | 0.4488 |
|
| 60 |
+
| 0.4758 | 3.6123 | 900 | 0.4470 |
|
| 61 |
+
| 0.4879 | 4.0160 | 1000 | 0.4472 |
|
| 62 |
+
| 0.4825 | 4.4162 | 1100 | 0.4480 |
|
| 63 |
+
| 0.4727 | 4.8164 | 1200 | 0.4457 |
|
| 64 |
+
| 0.4777 | 5.2201 | 1300 | 0.4485 |
|
| 65 |
+
| 0.4854 | 5.6203 | 1400 | 0.4488 |
|
| 66 |
+
| 0.4881 | 6.0240 | 1500 | 0.4472 |
|
| 67 |
+
| 0.481 | 6.4242 | 1600 | 0.4472 |
|
| 68 |
+
| 0.474 | 6.8244 | 1700 | 0.4471 |
|
| 69 |
+
| 0.4836 | 7.2281 | 1800 | 0.4468 |
|
| 70 |
+
| 0.4852 | 7.6283 | 1900 | 0.4480 |
|
| 71 |
+
| 0.479 | 8.0320 | 2000 | 0.4449 |
|
| 72 |
+
| 0.4805 | 8.4322 | 2100 | 0.4463 |
|
| 73 |
+
| 0.4743 | 8.8324 | 2200 | 0.4477 |
|
| 74 |
+
| 0.4792 | 9.2361 | 2300 | 0.4473 |
|
| 75 |
+
| 0.475 | 9.6363 | 2400 | 0.4451 |
|
| 76 |
+
| 0.4878 | 10.0400 | 2500 | 0.4456 |
|
| 77 |
+
| 0.478 | 10.4402 | 2600 | 0.4461 |
|
| 78 |
+
| 0.4805 | 10.8404 | 2700 | 0.4453 |
|
| 79 |
+
| 0.4773 | 11.2441 | 2800 | 0.4459 |
|
| 80 |
+
| 0.48 | 11.6443 | 2900 | 0.4453 |
|
| 81 |
+
| 0.479 | 12.0480 | 3000 | 0.4448 |
|
| 82 |
+
| 0.475 | 12.4482 | 3100 | 0.4437 |
|
| 83 |
+
| 0.4752 | 12.8484 | 3200 | 0.4461 |
|
| 84 |
+
| 0.4767 | 13.2521 | 3300 | 0.4434 |
|
| 85 |
+
| 0.4739 | 13.6523 | 3400 | 0.4458 |
|
| 86 |
+
| 0.4762 | 14.0560 | 3500 | 0.4431 |
|
| 87 |
+
| 0.4722 | 14.4562 | 3600 | 0.4450 |
|
| 88 |
+
| 0.4742 | 14.8564 | 3700 | 0.4442 |
|
| 89 |
+
| 0.4809 | 15.2601 | 3800 | 0.4448 |
|
| 90 |
+
| 0.475 | 15.6603 | 3900 | 0.4457 |
|
| 91 |
+
| 0.4789 | 16.0640 | 4000 | 0.4454 |
|
| 92 |
+
| 0.4709 | 16.4642 | 4100 | 0.4450 |
|
| 93 |
+
| 0.4826 | 16.8644 | 4200 | 0.4454 |
|
| 94 |
+
| 0.4735 | 17.2681 | 4300 | 0.4446 |
|
| 95 |
+
| 0.4727 | 17.6683 | 4400 | 0.4433 |
|
| 96 |
+
| 0.4867 | 18.0720 | 4500 | 0.4450 |
|
| 97 |
+
| 0.4804 | 18.4722 | 4600 | 0.4427 |
|
| 98 |
+
| 0.4802 | 18.8724 | 4700 | 0.4448 |
|
| 99 |
+
| 0.4798 | 19.2761 | 4800 | 0.4459 |
|
| 100 |
+
| 0.4788 | 19.6763 | 4900 | 0.4438 |
|
| 101 |
+
| 0.4772 | 20.0800 | 5000 | 0.4442 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- Transformers 4.47.0
|
| 107 |
+
- Pytorch 2.5.1+cu121
|
| 108 |
+
- Datasets 3.3.1
|
| 109 |
+
- Tokenizers 0.21.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.47.0",
|
| 8 |
+
"use_cache": false
|
| 9 |
+
}
|