YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co./docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
tinyllama-sft-orca_chat-mix - AWQ
- Model creator: https://huggingface.co./andrewbai/
- Original model: https://huggingface.co./andrewbai/tinyllama-sft-orca_chat-mix/
Original model description:
license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T tags: - alignment-handbook - trl - sft - generated_from_trainer - trl - sft - generated_from_trainer datasets: - ucla-cmllab/orca-chat_100k-chat-format - ucla-cmllab/RedPajama_100k model-index: - name: tinyllama-sft-orca_chat-mix results: []
tinyllama-sft-orca_chat-mix
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the ucla-cmllab/orca-chat_100k-chat-format and the ucla-cmllab/RedPajama_100k datasets. It achieves the following results on the evaluation set:
- Loss: 0.9497
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-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9347 | 0.9994 | 781 | 0.9497 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0