File size: 6,223 Bytes
9931ce8 7654349 9931ce8 f77b605 9931ce8 f77b605 9931ce8 f77b605 9931ce8 f77b605 9931ce8 f77b605 9931ce8 f77b605 9931ce8 eb52421 9931ce8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 |
---
library_name: transformers
base_model: danasone/bart-small-ru-en
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: bart_hin_eng_mt
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bart_hin_eng_mt
This model is a fine-tuned version of [danasone/bart-small-ru-en](https://huggingface.co/danasone/bart-small-ru-en) on [cfilt/iitb-english-hindi](https://huggingface.co/datasets/cfilt/iitb-english-hindi) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9000
- Bleu: 12.0235
- Gen Len: 33.4107
## Model description
Machine Translation model from Hindi to English on bart small model.
## Inference and evaluation
```python
import torch
import evaluate
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
class BartSmall():
def __init__(self, model_path = 'ar5entum/bart_hin_eng_mt', device = None):
self.tokenizer = AutoTokenizer.from_pretrained(model_path)
self.model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
if not device:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
self.device = device
self.model.to(device)
def predict(self, input_text):
inputs = self.tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True).to(self.device)
pred_ids = self.model.generate(inputs.input_ids, max_length=512, num_beams=4, early_stopping=True)
prediction = self.tokenizer.decode(pred_ids[0], skip_special_tokens=True)
return prediction
def predict_batch(self, input_texts, batch_size=32):
all_predictions = []
for i in range(0, len(input_texts), batch_size):
batch_texts = input_texts[i:i+batch_size]
inputs = self.tokenizer(batch_texts, return_tensors="pt", max_length=512,
truncation=True, padding=True).to(self.device)
with torch.no_grad():
pred_ids = self.model.generate(inputs.input_ids,
max_length=512,
num_beams=4,
early_stopping=True)
predictions = self.tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
all_predictions.extend(predictions)
return all_predictions
model = BartSmall(device='cuda')
input_texts = [
"यह शोध्य रकम है।",
"जानने के लिए देखें ये वीडियो.",
"वह दो बेटियों व एक बेटे का पिता था।"
]
ground_truths = [
"This is a repayable amount.",
"Watch this video to find out.",
"He was a father of two daughters and a son."
]
import time
start = time.time()
predictions = model.predict_batch(input_texts, batch_size=len(input_texts))
end = time.time()
print("TIME: ", end-start)
for i in range(len(input_texts)):
print("‾‾‾‾‾‾‾‾‾‾‾‾")
print("Input text:\t", input_texts[i])
print("Prediction:\t", predictions[i])
print("Ground Truth:\t", ground_truths[i])
bleu = evaluate.load("bleu")
results = bleu.compute(predictions=predictions, references=ground_truths)
print(results)
# TIME: 1.2374696731567383
# ‾‾‾‾‾‾‾‾‾‾‾‾
# Input text: यह शोध्य रकम है।
# Prediction: This is a repayable amount.
# Ground Truth: This is a repayable amount.
# ‾‾‾‾‾‾‾‾‾‾‾‾
# Input text: जानने के लिए देखें ये वीडियो.
# Prediction: View these videos to know.
# Ground Truth: Watch this video to find out.
# ‾‾‾‾‾‾‾‾‾‾‾‾
# Input text: वह दो बेटियों व एक बेटे का पिता था।
# Prediction: He was a father of two daughters and a son.
# Ground Truth: He was a father of two daughters and a son.
# {'bleu': 0.747875245486914, 'precisions': [0.8260869565217391, 0.75, 0.7647058823529411, 0.7857142857142857], 'brevity_penalty': 0.9574533680683809, 'length_ratio': 0.9583333333333334, 'translation_length': 23, 'reference_length': 24}
```
## Training Procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 100
- eval_batch_size: 40
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 200
- total_eval_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 15.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|
| 2.6298 | 1.0 | 8265 | 2.6192 | 4.5435 | 39.8786 |
| 2.2656 | 2.0 | 16530 | 2.2836 | 8.2498 | 35.8339 |
| 2.0625 | 3.0 | 24795 | 2.1747 | 9.9182 | 35.5214 |
| 1.974 | 4.0 | 33060 | 2.0760 | 10.1515 | 33.9732 |
| 1.925 | 5.0 | 41325 | 2.0285 | 10.7702 | 34.175 |
| 1.8076 | 6.0 | 49590 | 1.9860 | 11.4286 | 34.8875 |
| 1.7817 | 7.0 | 57855 | 1.9664 | 11.4579 | 32.6411 |
| 1.7025 | 8.0 | 66120 | 1.9561 | 11.9226 | 33.5179 |
| 1.6691 | 9.0 | 74385 | 1.9354 | 11.7352 | 33.2161 |
| 1.6631 | 10.0 | 82650 | 1.9231 | 11.9303 | 32.7679 |
| 1.6317 | 11.0 | 90915 | 1.9264 | 11.5889 | 32.625 |
| 1.6449 | 12.0 | 99180 | 1.9047 | 11.8451 | 33.8554 |
| 1.6165 | 13.0 | 107445 | 1.9040 | 12.0755 | 32.7661 |
| 1.5826 | 14.0 | 115710 | 1.9000 | 12.3137 | 33.3536 |
| 1.5835 | 15.0 | 123975 | 1.9000 | 12.0235 | 33.4107 |
### Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
|