metadata
base_model: google/paligemma-3b-pt-448
library_name: peft
license: other
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: train_2024-10-15-09-54-06
results: []
train_2024-10-15-09-54-06
This model is a fine-tuned version of google/paligemma-3b-pt-448 on the my_chartQA dataset. It achieves the following results on the evaluation set:
- Loss: 0.0002
- Num Input Tokens Seen: 5878272
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: 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
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1
- num_epochs: 2.0
Training results
Framework versions
- PEFT 0.12.0
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.20.1