metadata
library_name: peft
license: other
base_model: baidu/ERNIE-4.5-0.3B-PT
tags:
- base_model:adapter:baidu/ERNIE-4.5-0.3B-PT
- llama-factory
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: train_2025-12-23-16-11-58
results: []
train_2025-12-23-16-11-58
This model is a fine-tuned version of baidu/ERNIE-4.5-0.3B-PT on the synthetic_memories dataset. It achieves the following results on the evaluation set:
- Loss: 1.8149
- Num Input Tokens Seen: 3234144
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
Framework versions
- PEFT 0.17.1
- Transformers 4.54.0
- Pytorch 2.5.1+cu121
- Datasets 3.5.1
- Tokenizers 0.21.4