Virus-Proton/Bn_GEDC
Browse files- README.md +113 -0
- generation_config.json +11 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: facebook/mbart-large-50
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
- bleu
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Bn_GEDC
|
| 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 |
+
# Bn_GEDC
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1584
|
| 22 |
+
- Wer: 0.285
|
| 23 |
+
- Bleu: 0.525
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 16
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: reduce_lr_on_plateau
|
| 48 |
+
- num_epochs: 10
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Bleu |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-----:|:-----:|
|
| 54 |
+
| 1.514 | 0.016 | 500 | 0.0705 | 0.132 | 0.705 |
|
| 55 |
+
| 0.1289 | 0.032 | 1000 | 0.0761 | 0.129 | 0.712 |
|
| 56 |
+
| 0.102 | 0.048 | 1500 | 0.0756 | 0.128 | 0.709 |
|
| 57 |
+
| 0.0909 | 0.064 | 2000 | 0.0768 | 0.132 | 0.702 |
|
| 58 |
+
| 0.074 | 0.08 | 2500 | 0.0808 | 0.13 | 0.706 |
|
| 59 |
+
| 0.0685 | 0.096 | 3000 | 0.0821 | 0.132 | 0.692 |
|
| 60 |
+
| 0.0609 | 0.112 | 3500 | 0.0858 | 0.134 | 0.695 |
|
| 61 |
+
| 0.1022 | 0.128 | 4000 | 0.1186 | 0.293 | 0.535 |
|
| 62 |
+
| 0.0532 | 0.144 | 4500 | 0.1323 | 0.288 | 0.538 |
|
| 63 |
+
| 0.0498 | 0.16 | 5000 | 0.1254 | 0.276 | 0.549 |
|
| 64 |
+
| 0.0477 | 0.176 | 5500 | 0.1310 | 0.27 | 0.554 |
|
| 65 |
+
| 0.0459 | 0.192 | 6000 | 0.1391 | 0.267 | 0.559 |
|
| 66 |
+
| 0.0447 | 0.208 | 6500 | 0.1300 | 0.278 | 0.545 |
|
| 67 |
+
| 0.0418 | 0.224 | 7000 | 0.1243 | 0.263 | 0.571 |
|
| 68 |
+
| 0.0403 | 0.24 | 7500 | 0.1288 | 0.275 | 0.549 |
|
| 69 |
+
| 0.038 | 0.256 | 8000 | 0.1315 | 0.278 | 0.547 |
|
| 70 |
+
| 0.0382 | 0.272 | 8500 | 0.1345 | 0.276 | 0.545 |
|
| 71 |
+
| 0.0372 | 0.288 | 9000 | 0.1381 | 0.29 | 0.528 |
|
| 72 |
+
| 0.0345 | 0.304 | 9500 | 0.1348 | 0.3 | 0.521 |
|
| 73 |
+
| 0.0361 | 0.32 | 10000 | 0.1342 | 0.274 | 0.548 |
|
| 74 |
+
| 0.0334 | 0.336 | 10500 | 0.1322 | 0.285 | 0.532 |
|
| 75 |
+
| 0.0332 | 0.352 | 11000 | 0.1346 | 0.299 | 0.525 |
|
| 76 |
+
| 0.0327 | 0.368 | 11500 | 0.1355 | 0.317 | 0.507 |
|
| 77 |
+
| 0.0323 | 0.384 | 12000 | 0.1368 | 0.293 | 0.525 |
|
| 78 |
+
| 0.0317 | 0.4 | 12500 | 0.1437 | 0.287 | 0.529 |
|
| 79 |
+
| 0.03 | 0.416 | 13000 | 0.1419 | 0.322 | 0.499 |
|
| 80 |
+
| 0.0299 | 0.432 | 13500 | 0.1427 | 0.315 | 0.503 |
|
| 81 |
+
| 0.0289 | 0.448 | 14000 | 0.1461 | 0.291 | 0.525 |
|
| 82 |
+
| 0.0292 | 0.464 | 14500 | 0.1512 | 0.297 | 0.516 |
|
| 83 |
+
| 0.029 | 0.48 | 15000 | 0.1518 | 0.308 | 0.506 |
|
| 84 |
+
| 0.0277 | 0.496 | 15500 | 0.1533 | 0.3 | 0.514 |
|
| 85 |
+
| 0.0285 | 0.512 | 16000 | 0.1550 | 0.28 | 0.532 |
|
| 86 |
+
| 0.0271 | 0.528 | 16500 | 0.1484 | 0.29 | 0.525 |
|
| 87 |
+
| 0.0272 | 0.544 | 17000 | 0.1490 | 0.293 | 0.522 |
|
| 88 |
+
| 0.0267 | 0.56 | 17500 | 0.1535 | 0.284 | 0.527 |
|
| 89 |
+
| 0.0271 | 0.576 | 18000 | 0.1547 | 0.278 | 0.532 |
|
| 90 |
+
| 0.0256 | 0.592 | 18500 | 0.1553 | 0.3 | 0.513 |
|
| 91 |
+
| 0.024 | 0.608 | 19000 | 0.1559 | 0.29 | 0.523 |
|
| 92 |
+
| 0.0236 | 0.624 | 19500 | 0.1553 | 0.289 | 0.523 |
|
| 93 |
+
| 0.0233 | 0.64 | 20000 | 0.1552 | 0.289 | 0.525 |
|
| 94 |
+
| 0.022 | 0.656 | 20500 | 0.1565 | 0.288 | 0.525 |
|
| 95 |
+
| 0.0222 | 0.672 | 21000 | 0.1568 | 0.288 | 0.522 |
|
| 96 |
+
| 0.022 | 0.688 | 21500 | 0.1564 | 0.286 | 0.525 |
|
| 97 |
+
| 0.0215 | 0.704 | 22000 | 0.1575 | 0.285 | 0.527 |
|
| 98 |
+
| 0.0216 | 0.72 | 22500 | 0.1569 | 0.289 | 0.523 |
|
| 99 |
+
| 0.0213 | 0.736 | 23000 | 0.1580 | 0.288 | 0.522 |
|
| 100 |
+
| 0.0218 | 0.752 | 23500 | 0.1581 | 0.286 | 0.525 |
|
| 101 |
+
| 0.0208 | 0.768 | 24000 | 0.1584 | 0.286 | 0.524 |
|
| 102 |
+
| 0.0212 | 0.784 | 24500 | 0.1581 | 0.287 | 0.523 |
|
| 103 |
+
| 0.0203 | 0.8 | 25000 | 0.1583 | 0.285 | 0.525 |
|
| 104 |
+
| 0.0205 | 0.816 | 25500 | 0.1584 | 0.286 | 0.524 |
|
| 105 |
+
| 0.0204 | 0.832 | 26000 | 0.1584 | 0.285 | 0.525 |
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
### Framework versions
|
| 109 |
+
|
| 110 |
+
- Transformers 4.40.2
|
| 111 |
+
- Pytorch 2.3.0+cu121
|
| 112 |
+
- Datasets 2.19.1
|
| 113 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"max_length": 200,
|
| 8 |
+
"num_beams": 5,
|
| 9 |
+
"pad_token_id": 1,
|
| 10 |
+
"transformers_version": "4.40.2"
|
| 11 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2444578688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:524ead1a3925b9f1a6f87b7610f1eddc51ff8fbe6dc411b10f8ccf6a6e3cf010
|
| 3 |
size 2444578688
|