Model save
Browse files- README.md +74 -0
- generation_config.json +7 -0
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/mt5-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bengali_news_article_summarization_mt5
|
| 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 |
+
# bengali_news_article_summarization_mt5
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.2111
|
| 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: 0.001
|
| 38 |
+
- train_batch_size: 20
|
| 39 |
+
- eval_batch_size: 16
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 160
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine_with_restarts
|
| 45 |
+
- lr_scheduler_warmup_steps: 100
|
| 46 |
+
- num_epochs: 15
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| No log | 0.99 | 83 | 0.8963 |
|
| 53 |
+
| No log | 2.0 | 167 | 0.3201 |
|
| 54 |
+
| 9.149 | 2.99 | 250 | 0.2583 |
|
| 55 |
+
| 9.149 | 3.99 | 334 | 0.2372 |
|
| 56 |
+
| 0.3009 | 5.0 | 418 | 0.2298 |
|
| 57 |
+
| 0.3009 | 5.99 | 501 | 0.2244 |
|
| 58 |
+
| 0.3009 | 7.0 | 585 | 0.2213 |
|
| 59 |
+
| 0.2524 | 8.0 | 669 | 0.2163 |
|
| 60 |
+
| 0.2524 | 8.99 | 752 | 0.2136 |
|
| 61 |
+
| 0.2306 | 10.0 | 836 | 0.2126 |
|
| 62 |
+
| 0.2306 | 10.99 | 919 | 0.2117 |
|
| 63 |
+
| 0.2176 | 11.99 | 1003 | 0.2120 |
|
| 64 |
+
| 0.2176 | 13.0 | 1087 | 0.2116 |
|
| 65 |
+
| 0.2176 | 13.99 | 1170 | 0.2111 |
|
| 66 |
+
| 0.2119 | 14.89 | 1245 | 0.2111 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.39.3
|
| 72 |
+
- Pytorch 2.1.2
|
| 73 |
+
- Datasets 2.18.0
|
| 74 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.39.3"
|
| 7 |
+
}
|