mrm8488/bloom-560m-ft-summarization-cnn

<!-- 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. -->

bloom-560m-ft-summarization-cnn

This model is a fine-tuned version of bigscience/bloom-560m on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

• —eval_loss: 2.6957
• —eval_runtime: 587.637
• —evalsamplesper_second: 10.398
• —evalstepsper_second: 5.199
• —epoch: 0.97
• —step: 130000

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: 5e-05
• —trainbatchsize: 1
• —evalbatchsize: 2
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 2
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.22.2
• —Pytorch 1.12.1+cu113
• —Datasets 2.5.2
• —Tokenizers 0.12.1