update model card README.md

README.md

@@ -14,17 +14,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [fabiochiu/t5-base-tag-generation](https://huggingface.co/fabiochiu/t5-base-tag-generation) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.9747
-- eval_rouge1: 34.3533
-- eval_rouge2: 17.2404
-- eval_rougeL: 32.5248
-- eval_rougeLsum: 32.5145
-- eval_gen_len: 15.583
-- eval_runtime: 329.0338
-- eval_samples_per_second: 3.039
-- eval_steps_per_second: 0.38
-- epoch: 0.23
-- step: 1500
+- eval_loss: 0.8474
+- eval_rouge1: 38.6033
+- eval_rouge2: 20.5952
+- eval_rougeL: 36.4458
+- eval_rougeLsum: 36.3202
+- eval_gen_len: 15.257
+- eval_runtime: 343.6547
+- eval_samples_per_second: 2.91
+- eval_steps_per_second: 0.364
+- epoch: 0.31
+- step: 2000
 
 ## Model description
 
@@ -56,5 +56,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.19.2
 - Pytorch 1.11.0+cu113
-- Datasets 2.2.1
+- Datasets 2.2.2
 - Tokenizers 0.12.1