update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
+
model-index:
|
| 8 |
+
- name: mt5-aym-lex-try
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# mt5-aym-lex-try
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [alvations/mt5-aym-lex](https://huggingface.co/alvations/mt5-aym-lex) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2781
|
| 20 |
+
- Chrf: 15.5602
|
| 21 |
+
- Bleu: 0.7538
|
| 22 |
+
- Gen Len: 19.0
|
| 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: 5e-05
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 1
|
| 48 |
+
- training_steps: 100
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Chrf | Bleu | Gen Len |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|
|
| 54 |
+
| 0.2183 | 0.0 | 20 | 0.3002 | 16.5098 | 0.7277 | 19.0 |
|
| 55 |
+
| 0.1911 | 0.01 | 40 | 0.2852 | 16.9826 | 0.7635 | 19.0 |
|
| 56 |
+
| 0.2366 | 0.01 | 60 | 0.2800 | 15.7077 | 0.7476 | 19.0 |
|
| 57 |
+
| 0.1941 | 0.02 | 80 | 0.2785 | 15.5602 | 0.7538 | 19.0 |
|
| 58 |
+
| 0.1991 | 0.02 | 100 | 0.2781 | 15.5602 | 0.7538 | 19.0 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- Transformers 4.29.1
|
| 64 |
+
- Pytorch 2.0.0+cu118
|
| 65 |
+
- Datasets 2.12.0
|
| 66 |
+
- Tokenizers 0.13.3
|