metadata
license: other
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: tactic
results: []
tactic
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the chess_explain_tactic_00, the chess_explain_tactic_01, the chess_explain_tactic_02, the chess_explain_tactic_03, the chess_explain_tactic_04, the chess_explain_tactic_05, the chess_explain_tactic_06, the chess_explain_tactic_07, the chess_explain_tactic_08, the chess_explain_tactic_09, the chess_explain_tactic_10, the chess_explain_tactic_11, the chess_explain_tactic_12, the chess_explain_tactic_13 and the chess_explain_tactic_14 datasets. It achieves the following results on the evaluation set:
- Loss: 0.0171
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: 5e-06
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 512
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0169 | 1.6260 | 1000 | 0.0171 |
| 0.0049 | 3.2520 | 2000 | 0.0238 |
| 0.0005 | 4.8780 | 3000 | 0.0325 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1