metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- anli
metrics:
- rouge
model-index:
- name: gpt-j-claim-generator
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: anli
type: anli
config: plain_text
split: dev_r3
args: plain_text
metrics:
- name: Rouge1
type: rouge
value: 0.8913860940628431
gpt-j-claim-generator
This model is a fine-tuned version of EleutherAI/gpt-j-6b on the anli dataset. It achieves the following results on the evaluation set:
- Loss: 0.0232
- Rouge1: 0.8914
- Rouge2: 0.8240
- Rougel: 0.8863
- Rougelsum: 0.8864
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: 1e-05
- train_batch_size: 12
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- total_train_batch_size: 36
- total_eval_batch_size: 3
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
---|---|---|---|---|---|---|---|
0.013 | 1.79 | 5000 | 0.0200 | 0.8921 | 0.8194 | 0.8859 | 0.8860 |
0.0085 | 3.58 | 10000 | 0.0232 | 0.8914 | 0.8240 | 0.8863 | 0.8864 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3