mt5-summarize-ch_trad

This model is a fine-tuned version of uer/t5-small-chinese-cluecorpussmall on the xlsum dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.2489
• eval_rouge1: 0.1313
• eval_rouge2: 0.0505
• eval_rougeL: 0.1275
• eval_rougeLsum: 0.1272
• eval_gen_len: 128.0
• eval_runtime: 541.5872
• eval_samples_per_second: 8.623
• eval_steps_per_second: 0.27
• epoch: 7.71
• step: 9000

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 10
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.0
• Datasets 2.1.0
• Tokenizers 0.13.2