Bart_pretrained_model

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

test-dialogue-summarization

This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set: eval_loss: 0.8548385500907898, eval_rouge1: 66.4768, eval_rouge2: 48.5059, eval_rougeL: 55.6107, eval_rougeLsum: 64.379, eval_gen_len: 135.19, eval_runtime: 106.4023, eval_samples_per_second: 0.94, eval_steps_per_second: 0.235, epoch: 5.0

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Epoch Training Loss Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len 1 No log 0.968213 59.682700 35.068600 44.651000 56.618200 137.666700 2 No log 0.961468 61.080300 37.609500 47.390200 58.380500 134.193300 3 No log 0.965955 62.082900 39.734400 48.736800 59.302500 135.833300 4 No log 0.975513 63.494900 42.147500 50.690800 60.831800 134.246700 5 No log 0.983745 64.556600 43.555200 51.977700 61.979700 134.180000

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.2
• Tokenizers 0.13.3