|
--- |
|
base_model: TinyLlama/TinyLlama_v1.1 |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: tinyllama_magiccoder_ortho |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# tinyllama_magiccoder_ortho |
|
|
|
This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4401 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.8608 | 0.0262 | 4 | 1.8810 | |
|
| 1.7875 | 0.0523 | 8 | 1.6839 | |
|
| 1.6211 | 0.0785 | 12 | 1.6379 | |
|
| 1.5275 | 0.1047 | 16 | 1.5652 | |
|
| 1.5674 | 0.1308 | 20 | 1.5608 | |
|
| 1.4798 | 0.1570 | 24 | 1.5422 | |
|
| 1.484 | 0.1832 | 28 | 1.5231 | |
|
| 1.524 | 0.2093 | 32 | 1.5137 | |
|
| 1.4406 | 0.2355 | 36 | 1.5169 | |
|
| 1.5328 | 0.2617 | 40 | 1.5073 | |
|
| 1.5037 | 0.2878 | 44 | 1.4938 | |
|
| 1.5445 | 0.3140 | 48 | 1.4939 | |
|
| 1.5157 | 0.3401 | 52 | 1.4924 | |
|
| 1.4724 | 0.3663 | 56 | 1.4748 | |
|
| 1.5457 | 0.3925 | 60 | 1.4869 | |
|
| 1.5126 | 0.4186 | 64 | 1.4744 | |
|
| 1.4564 | 0.4448 | 68 | 1.4726 | |
|
| 1.4628 | 0.4710 | 72 | 1.4695 | |
|
| 1.4244 | 0.4971 | 76 | 1.4711 | |
|
| 1.5274 | 0.5233 | 80 | 1.4654 | |
|
| 1.5459 | 0.5495 | 84 | 1.4615 | |
|
| 1.4562 | 0.5756 | 88 | 1.4600 | |
|
| 1.3771 | 0.6018 | 92 | 1.4578 | |
|
| 1.3837 | 0.6280 | 96 | 1.4537 | |
|
| 1.46 | 0.6541 | 100 | 1.4546 | |
|
| 1.4711 | 0.6803 | 104 | 1.4554 | |
|
| 1.4257 | 0.7065 | 108 | 1.4455 | |
|
| 1.4661 | 0.7326 | 112 | 1.4473 | |
|
| 1.4269 | 0.7588 | 116 | 1.4469 | |
|
| 1.4269 | 0.7850 | 120 | 1.4433 | |
|
| 1.4514 | 0.8111 | 124 | 1.4461 | |
|
| 1.4349 | 0.8373 | 128 | 1.4458 | |
|
| 1.3174 | 0.8635 | 132 | 1.4409 | |
|
| 1.4861 | 0.8896 | 136 | 1.4399 | |
|
| 1.3536 | 0.9158 | 140 | 1.4408 | |
|
| 1.408 | 0.9419 | 144 | 1.4404 | |
|
| 1.4435 | 0.9681 | 148 | 1.4401 | |
|
| 1.4317 | 0.9943 | 152 | 1.4401 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
