metadata
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: distilroberta-base-fineweb-edu-llama3-annotations-2048-vN
results: []
distilroberta-base-fineweb-edu-llama3-annotations-2048-vN
This model is a fine-tuned version of 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