This model is a fine-tuned version of LA1512/Led-pubmed-20K-4096-epoch2 on an unknown dataset.
It achieves the following results on the evaluation set:
eval_loss: 3.4307
eval_rouge1: 42.7202
eval_rouge2: 13.8636
eval_rougeL: 21.0583
eval_rougeLsum: 37.393
eval_gen_len: 290.714
eval_runtime: 24465.3571
eval_samples_per_second: 0.02
eval_steps_per_second: 0.01
step: 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: 3e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
