metadata

base_model: google/pegasus-xsum
tags:
  - generated_from_trainer
metrics:
  - rouge
  - precision
  - recall
  - f1
model-index:
  - name: LLM_Teached_Pegasus_100k
    results: []

LLM_Teached_Pegasus_100k

This model is a fine-tuned version of google/pegasus-xsum on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.5409
Rouge1: 0.4869
Rouge2: 0.2373
Rougel: 0.406
Rougelsum: 0.4058
Gen Len: 25.3851
Precision: 0.9131
Recall: 0.9117
F1: 0.9123

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: 32
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Precision	Recall	F1
2.1501	1.0	781	1.7062	0.4566	0.209	0.3745	0.3744	25.4655	0.9082	0.9065	0.9072
1.7722	2.0	1562	1.6314	0.4712	0.2226	0.3906	0.3904	25.4298	0.9107	0.909	0.9097
1.7218	3.0	2343	1.5948	0.4776	0.2284	0.3965	0.3963	25.6569	0.9112	0.9103	0.9106
1.6668	4.0	3125	1.5708	0.481	0.2316	0.4002	0.4	25.3451	0.9122	0.9107	0.9112
1.6437	5.0	3906	1.5565	0.4844	0.2346	0.4034	0.4031	25.482	0.9127	0.9113	0.9118
1.6186	6.0	4687	1.5476	0.4852	0.236	0.4047	0.4044	25.4191	0.9129	0.9115	0.912
1.607	7.0	5468	1.5426	0.486	0.2367	0.4052	0.405	25.4949	0.9129	0.9118	0.9122
1.5972	8.0	6248	1.5409	0.4869	0.2373	0.406	0.4058	25.3851	0.9131	0.9117	0.9123

Framework versions

Transformers 4.36.0
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.15.0