metadata
library_name: peft
base_model: Xenova/tiny-random-Phi3ForCausalLM
tags:
- axolotl
- generated_from_trainer
model-index:
- name: ab36070c-3df9-4b53-bd5b-5735cef88822
results: []
ab36070c-3df9-4b53-bd5b-5735cef88822
This model is a fine-tuned version of Xenova/tiny-random-Phi3ForCausalLM on the None dataset. It achieves the following results on the evaluation set:
- Loss: 10.1272
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: 0.0001001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.4016 | 0.0000 | 1 | 10.3968 |
| 10.2019 | 0.0008 | 50 | 10.1894 |
| 10.1395 | 0.0015 | 100 | 10.1393 |
| 10.1306 | 0.0023 | 150 | 10.1292 |
| 10.1334 | 0.0031 | 200 | 10.1272 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1