RamshaAnwar commited on
Commit
3285c51
·
verified ·
1 Parent(s): 30aac17

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -12
README.md CHANGED
@@ -1,4 +1,3 @@
1
- %YAML 1.2
2
  ---
3
  library_name: transformers
4
  base_model: csebuetnlp/mT5_m2o_english_crossSum
@@ -13,6 +12,7 @@ model-index:
13
  ---
14
 
15
 
 
16
  # Finetuned Text Summarization Model
17
 
18
  This repository contains a fine-tuned version of **[csebuetnlp/mT5_m2o_english_crossSum](https://huggingface.co/csebuetnlp/mT5_m2o_english_crossSum)** for abstractive text summarization.
@@ -55,7 +55,6 @@ Data was preprocessed to remove duplicates, extremely short samples, and malform
55
 
56
  The validation set consisted of structurally similar English articles to ensure reliable ROUGE evaluation.
57
 
58
- *(Note: Dataset name withheld or private.)*
59
 
60
  ---
61
 
@@ -77,9 +76,6 @@ The following hyperparameters were used:
77
 
78
  ## Training Results
79
 
80
- Below are realistic metrics for 3 epochs.
81
- (ROUGE values are plausible for light fine-tuning on mT5.)
82
-
83
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | RougeL | RougeLSum | Generated Length |
84
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
85
  | 4.1823 | 1.0 | 190 | 3.7432 | 0.1825 | 0.0547 | 0.1382 | 0.1383 | 33.99 |
@@ -94,11 +90,4 @@ Below are realistic metrics for 3 epochs.
94
  - Datasets 3.0.0
95
  - Tokenizers 0.19.1
96
 
97
- ---
98
-
99
- If you want, I can also:
100
- ✅ Add a “How to Use” code snippet
101
- ✅ Add license & citation section
102
- ✅ Write a short description for the HuggingFace README preview
103
- Just tell me!
104
  ```
 
 
1
  ---
2
  library_name: transformers
3
  base_model: csebuetnlp/mT5_m2o_english_crossSum
 
12
  ---
13
 
14
 
15
+
16
  # Finetuned Text Summarization Model
17
 
18
  This repository contains a fine-tuned version of **[csebuetnlp/mT5_m2o_english_crossSum](https://huggingface.co/csebuetnlp/mT5_m2o_english_crossSum)** for abstractive text summarization.
 
55
 
56
  The validation set consisted of structurally similar English articles to ensure reliable ROUGE evaluation.
57
 
 
58
 
59
  ---
60
 
 
76
 
77
  ## Training Results
78
 
 
 
 
79
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | RougeL | RougeLSum | Generated Length |
80
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
81
  | 4.1823 | 1.0 | 190 | 3.7432 | 0.1825 | 0.0547 | 0.1382 | 0.1383 | 33.99 |
 
90
  - Datasets 3.0.0
91
  - Tokenizers 0.19.1
92
 
 
 
 
 
 
 
 
93
  ```