Model save
Browse files- README.md +72 -0
- generation_config.json +6 -0
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/mt5-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: mt5-base
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# mt5-base
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0516
|
| 21 |
+
- Wer: 0.0392
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0003
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 2000
|
| 47 |
+
- num_epochs: 10
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 3.4396 | 0.81 | 4000 | 0.3368 | 0.3043 |
|
| 54 |
+
| 0.4257 | 1.62 | 8000 | 0.1328 | 0.1205 |
|
| 55 |
+
| 0.2185 | 2.42 | 12000 | 0.0929 | 0.0879 |
|
| 56 |
+
| 0.1506 | 3.23 | 16000 | 0.0762 | 0.0708 |
|
| 57 |
+
| 0.1133 | 4.04 | 20000 | 0.0663 | 0.0587 |
|
| 58 |
+
| 0.092 | 4.85 | 24000 | 0.0620 | 0.0551 |
|
| 59 |
+
| 0.0739 | 5.66 | 28000 | 0.0583 | 0.0507 |
|
| 60 |
+
| 0.0649 | 6.46 | 32000 | 0.0572 | 0.0465 |
|
| 61 |
+
| 0.0564 | 7.27 | 36000 | 0.0545 | 0.0439 |
|
| 62 |
+
| 0.0494 | 8.08 | 40000 | 0.0533 | 0.0425 |
|
| 63 |
+
| 0.0433 | 8.89 | 44000 | 0.0522 | 0.0405 |
|
| 64 |
+
| 0.0396 | 9.7 | 48000 | 0.0516 | 0.0392 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.33.0
|
| 70 |
+
- Pytorch 2.0.0
|
| 71 |
+
- Datasets 2.1.0
|
| 72 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.33.0"
|
| 6 |
+
}
|