|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: HuggingFaceTB/SmolLM-135M |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Assignment2-modified-V1 |
|
|
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. --> |
|
|
|
|
|
# Assignment2-modified-V1 |
|
|
|
|
|
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.2164 |
|
|
|
|
|
## 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: 0.0002 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: constant |
|
|
- num_epochs: 2 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 3.1948 | 0.16 | 200 | 3.2495 | |
|
|
| 2.9483 | 0.32 | 400 | 3.1734 | |
|
|
| 2.8639 | 0.48 | 600 | 3.1253 | |
|
|
| 2.7234 | 0.64 | 800 | 3.1154 | |
|
|
| 2.6644 | 0.8 | 1000 | 3.0934 | |
|
|
| 2.6771 | 0.96 | 1200 | 3.0747 | |
|
|
| 1.9795 | 1.12 | 1400 | 3.2253 | |
|
|
| 1.7571 | 1.28 | 1600 | 3.2024 | |
|
|
| 1.7604 | 1.44 | 1800 | 3.2253 | |
|
|
| 1.8268 | 1.6 | 2000 | 3.2242 | |
|
|
| 1.8035 | 1.76 | 2200 | 3.2222 | |
|
|
| 1.7959 | 1.92 | 2400 | 3.2164 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.56.1 |
|
|
- Pytorch 2.8.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.0 |
|
|
|
