metadata
library_name: peft
license: mit
base_model: microsoft/Phi-3-medium-128k-instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Adapter-Phi-3-medium-128k-instruct-lora-hrdx-gptq
results: []
Adapter-Phi-3-medium-128k-instruct-lora-hrdx-gptq
This model is a fine-tuned version of microsoft/Phi-3-medium-128k-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3389
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-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.4023 | 30 | 2.3964 |
| No log | 2.8046 | 60 | 2.1247 |
| No log | 4.2299 | 90 | 1.8968 |
| 2.2305 | 5.6322 | 120 | 1.7274 |
| 2.2305 | 7.0575 | 150 | 1.5368 |
| 2.2305 | 8.4598 | 180 | 1.3934 |
| 1.5516 | 9.8621 | 210 | 1.3389 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3