Model save
Browse files- README.md +72 -0
- generation_config.json +5 -0
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: facebook/m2m100_418M
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: m2m100-lg-to-en-v2
|
| 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 |
+
# m2m100-lg-to-en-v2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 11.5952
|
| 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: 1e-08
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 16
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 15
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 12.3804 | 1.0 | 119 | 12.6272 |
|
| 51 |
+
| 12.389 | 2.0 | 238 | 12.5538 |
|
| 52 |
+
| 12.3486 | 3.0 | 357 | 12.4810 |
|
| 53 |
+
| 12.3239 | 4.0 | 476 | 12.4177 |
|
| 54 |
+
| 12.2828 | 5.0 | 595 | 12.1366 |
|
| 55 |
+
| 12.0986 | 6.0 | 714 | 12.0700 |
|
| 56 |
+
| 12.0733 | 7.0 | 833 | 12.0214 |
|
| 57 |
+
| 12.0746 | 8.0 | 952 | 11.9687 |
|
| 58 |
+
| 12.0377 | 9.0 | 1071 | 11.9397 |
|
| 59 |
+
| 12.0163 | 10.0 | 1190 | 11.9031 |
|
| 60 |
+
| 11.95 | 11.0 | 1309 | 11.8120 |
|
| 61 |
+
| 11.9303 | 12.0 | 1428 | 11.7297 |
|
| 62 |
+
| 11.8673 | 13.0 | 1547 | 11.6198 |
|
| 63 |
+
| 11.8117 | 14.0 | 1666 | 11.5958 |
|
| 64 |
+
| 11.7915 | 15.0 | 1785 | 11.5952 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.41.1
|
| 70 |
+
- Pytorch 2.1.2
|
| 71 |
+
- Datasets 2.19.1
|
| 72 |
+
- Tokenizers 0.19.1
|
generation_config.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"early_stopping": true,
|
|
|
|
| 3 |
"max_length": 200,
|
| 4 |
"num_beams": 5,
|
|
|
|
| 5 |
"transformers_version": "4.41.1"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
"max_length": 200,
|
| 8 |
"num_beams": 5,
|
| 9 |
+
"pad_token_id": 1,
|
| 10 |
"transformers_version": "4.41.1"
|
| 11 |
}
|