metadata
library_name: peft
license: apache-2.0
base_model: echarlaix/tiny-random-PhiForCausalLM
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 03be64df-e585-404a-b455-8909f1fb17dc
results: []
03be64df-e585-404a-b455-8909f1fb17dc
This model is a fine-tuned version of echarlaix/tiny-random-PhiForCausalLM on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.7961
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: 0.000201
- 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=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0002 | 1 | 6.9331 |
| 6.8587 | 0.0118 | 50 | 6.8654 |
| 6.8111 | 0.0235 | 100 | 6.8337 |
| 6.7917 | 0.0353 | 150 | 6.8210 |
| 6.7795 | 0.0471 | 200 | 6.8123 |
| 6.7839 | 0.0588 | 250 | 6.8065 |
| 6.773 | 0.0706 | 300 | 6.8016 |
| 6.7748 | 0.0823 | 350 | 6.7987 |
| 6.774 | 0.0941 | 400 | 6.7967 |
| 6.7698 | 0.1059 | 450 | 6.7958 |
| 6.7577 | 0.1176 | 500 | 6.7961 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1