metadata
library_name: peft
license: apache-2.0
base_model: echarlaix/tiny-random-mistral
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 9747d29e-dac5-484e-b903-ce655a54e368
results: []
9747d29e-dac5-484e-b903-ce655a54e368
This model is a fine-tuned version of echarlaix/tiny-random-mistral on the None dataset. It achieves the following results on the evaluation set:
- Loss: 10.3203
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: 0.00010018
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 20.764 | 0.0021 | 1 | 10.3770 |
| 20.6957 | 0.1042 | 50 | 10.3349 |
| 20.6677 | 0.2083 | 100 | 10.3224 |
| 20.6558 | 0.3125 | 150 | 10.3210 |
| 20.6439 | 0.4167 | 200 | 10.3203 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1