update model card README.md

README.md

@@ -2,11 +2,11 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: flan-t5-large-bottleneck-adapter-cpgQA
   results: []
-datasets:
-- legacy107/cpgQA
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # flan-t5-large-bottleneck-adapter-cpgQA
 
-This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on [legacy107/cpgQA](https://huggingface.co/datasets/legacy107/cpgQA).
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1175
+- Squad: {'exact_match': 74.03846153846153, 'f1': 92.73025873728763}
+- Bleu: {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}
 
 ## Model description
 
@@ -33,16 +37,45 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 2
+- learning_rate: 0.003
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 6
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Squad                                                       | Bleu                                                                                                                                                                                                                                                            |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
+| 0.4902        | 0.23  | 100  | 0.1695          | {'exact_match': 59.61538461538461, 'f1': 88.39664262292322} | {'bleu': 0.8611708764560243, 'precisions': [0.8791469194312796, 0.8657487091222031, 0.8552631578947368, 0.8448979591836735], 'brevity_penalty': 1.0, 'length_ratio': 1.0284321689683185, 'translation_length': 1266, 'reference_length': 1231}                  |
+| 0.3577        | 0.45  | 200  | 0.3243          | {'exact_match': 47.11538461538461, 'f1': 75.97696037540817} | {'bleu': 0.44597697779640594, 'precisions': [0.9202211690363349, 0.9087779690189329, 0.8994360902255639, 0.8948979591836734], 'brevity_penalty': 0.49236704919459706, 'length_ratio': 0.5852981969486823, 'translation_length': 1266, 'reference_length': 2163} |
+| 0.2751        | 0.68  | 300  | 0.1577          | {'exact_match': 69.23076923076923, 'f1': 89.48763228957931} | {'bleu': 0.8601252797928449, 'precisions': [0.8925750394944708, 0.878657487091222, 0.8656015037593985, 0.8561224489795919], 'brevity_penalty': 0.985104158338853, 'length_ratio': 0.9852140077821012, 'translation_length': 1266, 'reference_length': 1285}     |
+| 0.5794        | 0.9   | 400  | 0.4970          | {'exact_match': 32.69230769230769, 'f1': 67.89210636760458} | {'bleu': 0.5849757239612657, 'precisions': [0.7282780410742496, 0.693631669535284, 0.6635338345864662, 0.6387755102040816], 'brevity_penalty': 0.8599604506941122, 'length_ratio': 0.8689087165408373, 'translation_length': 1266, 'reference_length': 1457}    |
+| 0.2114        | 1.13  | 500  | 0.1245          | {'exact_match': 67.3076923076923, 'f1': 89.96309177836906}  | {'bleu': 0.8997821698527838, 'precisions': [0.9360189573459715, 0.9285714285714286, 0.9238721804511278, 0.9204081632653062], 'brevity_penalty': 0.9704302027764995, 'length_ratio': 0.9708588957055214, 'translation_length': 1266, 'reference_length': 1304}   |
+| 0.1765        | 1.36  | 600  | 0.1214          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1822        | 1.58  | 700  | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.14          | 1.81  | 800  | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1456        | 2.04  | 900  | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1172        | 2.26  | 1000 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1376        | 2.49  | 1100 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1683        | 2.71  | 1200 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.0717        | 2.94  | 1300 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1038        | 3.17  | 1400 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.0812        | 3.39  | 1500 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1887        | 3.62  | 1600 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.0824        | 3.85  | 1700 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1046        | 4.07  | 1800 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.0952        | 4.3   | 1900 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1054        | 4.52  | 2000 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1603        | 4.75  | 2100 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1643        | 4.98  | 2200 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1326        | 5.2   | 2300 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1922        | 5.43  | 2400 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.1154        | 5.66  | 2500 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
+| 0.07          | 5.88  | 2600 | 0.1175          | {'exact_match': 74.03846153846153, 'f1': 92.73025873728763} | {'bleu': 0.9331748310720637, 'precisions': [0.9447077409162717, 0.9380378657487092, 0.9332706766917294, 0.9285714285714286], 'brevity_penalty': 0.9968454284876576, 'length_ratio': 0.9968503937007874, 'translation_length': 1266, 'reference_length': 1270}   |
 
 
 ### Framework versions
@@ -50,4 +83,4 @@ The following hyperparameters were used during training:
 - Transformers 4.26.1
 - Pytorch 2.0.0
 - Datasets 2.1.0
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3