|
--- |
|
license: apache-2.0 |
|
base_model: distilroberta-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: distilroberta-base-fineweb-edu-llama3-annotations-2048-vN |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pszemraj/eduscore-regression/runs/8e2uvp5t) |
|
# distilroberta-base-fineweb-edu-llama3-annotations-2048-vN |
|
|
|
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2197 |
|
- Mse: 0.2197 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 90085 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-09 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 1.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mse | |
|
|:-------------:|:------:|:----:|:---------------:|:------:| |
|
| 0.5276 | 0.0288 | 100 | 0.5012 | 0.5012 | |
|
| 0.3307 | 0.0576 | 200 | 0.3467 | 0.3467 | |
|
| 0.2994 | 0.0865 | 300 | 0.2948 | 0.2948 | |
|
| 0.2813 | 0.1153 | 400 | 0.2799 | 0.2799 | |
|
| 0.2707 | 0.1441 | 500 | 0.3017 | 0.3017 | |
|
| 0.2506 | 0.1729 | 600 | 0.2699 | 0.2699 | |
|
| 0.2584 | 0.2018 | 700 | 0.2633 | 0.2633 | |
|
| 0.2603 | 0.2306 | 800 | 0.2434 | 0.2434 | |
|
| 0.2973 | 0.2594 | 900 | 0.2394 | 0.2394 | |
|
| 0.2541 | 0.2882 | 1000 | 0.2356 | 0.2356 | |
|
| 0.2837 | 0.3171 | 1100 | 0.2437 | 0.2437 | |
|
| 0.242 | 0.3459 | 1200 | 0.2379 | 0.2379 | |
|
| 0.2379 | 0.3747 | 1300 | 0.2270 | 0.2270 | |
|
| 0.23 | 0.4035 | 1400 | 0.2357 | 0.2357 | |
|
| 0.2345 | 0.4324 | 1500 | 0.2417 | 0.2417 | |
|
| 0.2574 | 0.4612 | 1600 | 0.2556 | 0.2556 | |
|
| 0.264 | 0.4900 | 1700 | 0.2452 | 0.2452 | |
|
| 0.2596 | 0.5188 | 1800 | 0.2215 | 0.2215 | |
|
| 0.244 | 0.5477 | 1900 | 0.2269 | 0.2269 | |
|
| 0.2225 | 0.5765 | 2000 | 0.2342 | 0.2342 | |
|
| 0.2475 | 0.6053 | 2100 | 0.2403 | 0.2403 | |
|
| 0.253 | 0.6341 | 2200 | 0.2326 | 0.2326 | |
|
| 0.2435 | 0.6630 | 2300 | 0.2161 | 0.2161 | |
|
| 0.2865 | 0.6918 | 2400 | 0.2265 | 0.2265 | |
|
| 0.2351 | 0.7206 | 2500 | 0.2343 | 0.2343 | |
|
| 0.2582 | 0.7494 | 2600 | 0.2342 | 0.2342 | |
|
| 0.2167 | 0.7783 | 2700 | 0.2337 | 0.2337 | |
|
| 0.2495 | 0.8071 | 2800 | 0.2273 | 0.2273 | |
|
| 0.2364 | 0.8359 | 2900 | 0.2298 | 0.2298 | |
|
| 0.2236 | 0.8647 | 3000 | 0.2170 | 0.2170 | |
|
| 0.231 | 0.8936 | 3100 | 0.2234 | 0.2234 | |
|
| 0.2474 | 0.9224 | 3200 | 0.2227 | 0.2227 | |
|
| 0.2333 | 0.9512 | 3300 | 0.2241 | 0.2241 | |
|
| 0.2265 | 0.9800 | 3400 | 0.2197 | 0.2197 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|