metadata
base_model: OrionStarAI/Orion-14B-Chat
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- ikno/rinko_couple_v2.13
model-index:
- name: rinko-test
results: []
rinko-test
This model is a fine-tuned version of OrionStarAI/Orion-14B-Chat on the ikno/rinko_couple_v2.13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1707
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: 2e-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3348 | 0.99 | 62 | 0.2483 |
| 0.2659 | 2.0 | 125 | 0.1883 |
| 0.2447 | 2.98 | 186 | 0.1707 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.15.2