ntkhoi/mt5-vi-news-summarization

README.md

@@ -3,15 +3,11 @@ license: apache-2.0
 base_model: google/mt5-small
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: FastAbs-Fine-tuning-Text-Summarization
   results: []
-datasets:
-- vietgpt/news_summarization_vi
-language:
-- vi
-metrics:
-- rouge
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -20,6 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 # FastAbs-Fine-tuning-Text-Summarization
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8435
+- Rouge1: 71.033
+- Rouge2: 46.9902
+- Rougel: 49.8521
+- Rougelsum: 64.0283
+- Gen Len: 231.535
 
 ## Model description
 
@@ -39,8 +42,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 6
-- eval_batch_size: 4
+- train_batch_size: 12
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -56,4 +59,4 @@ The following hyperparameters were used during training:
 - Transformers 4.39.3
 - Pytorch 2.1.2
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

runs/Jun06_13-34-30_ff49f8f711b9/events.out.tfevents.1717701199.ff49f8f711b9.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0a15207563fb770b7a12ef7dbfb22b2cbdf68c94d52be70e0199a4ec252050
+size 613