metadata
library_name: transformers
license: apache-2.0
base_model: HuggingFaceTB/SmolLM-135M
tags:
- generated_from_trainer
model-index:
- name: distily_smollm_dataset_sweep
results: []
distily_smollm_dataset_sweep
This model is a fine-tuned version of HuggingFaceTB/SmolLM-135M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2261
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: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0 | 0 | 19.2449 |
| 1.1157 | 0.0401 | 5000 | 1.0851 |
| 0.6609 | 0.0802 | 10000 | 0.6537 |
| 0.5549 | 0.1202 | 15000 | 0.5350 |
| 0.4606 | 0.1603 | 20000 | 0.4633 |
| 0.465 | 0.2004 | 25000 | 0.4193 |
| 0.3826 | 0.2405 | 30000 | 0.3880 |
| 0.3807 | 0.2806 | 35000 | 0.3668 |
| 0.3315 | 0.3206 | 40000 | 0.3475 |
| 0.3352 | 0.3607 | 45000 | 0.3333 |
| 0.3222 | 0.4008 | 50000 | 0.3209 |
| 0.2994 | 0.4409 | 55000 | 0.3103 |
| 0.3059 | 0.4810 | 60000 | 0.3016 |
| 0.3154 | 0.5210 | 65000 | 0.2924 |
| 0.2986 | 0.5611 | 70000 | 0.2855 |
| 0.2696 | 0.6012 | 75000 | 0.2785 |
| 0.254 | 0.6413 | 80000 | 0.2726 |
| 0.2561 | 0.6814 | 85000 | 0.2662 |
| 0.2602 | 0.7214 | 90000 | 0.2605 |
| 0.2592 | 0.7615 | 95000 | 0.2558 |
| 0.2417 | 0.8016 | 100000 | 0.2506 |
| 0.23 | 0.8417 | 105000 | 0.2455 |
| 0.2329 | 0.8818 | 110000 | 0.2406 |
| 0.2302 | 0.9218 | 115000 | 0.2360 |
| 0.2722 | 0.9619 | 120000 | 0.2312 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.5.0.dev20240910+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1