metadata
license: apache-2.0
base_model: Qwen/Qwen2-7B
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: LawToken-7B-baseline
results: []
LawToken-7B-baseline
This model is a fine-tuned version of Qwen/Qwen2-7B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.6543
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 8
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0922 | 0.13 | 10000 | 1.0421 |
| 0.8321 | 0.27 | 20000 | 0.9366 |
| 0.8339 | 0.4 | 30000 | 0.8672 |
| 0.7813 | 0.54 | 40000 | 0.8081 |
| 0.6781 | 0.67 | 50000 | 0.7532 |
| 0.7259 | 0.8 | 60000 | 0.6990 |
| 0.6767 | 0.94 | 70000 | 0.6543 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.19.1
- Tokenizers 0.15.2