|
--- |
|
base_model: d0rj/rut5-base-summ |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: myspace1 |
|
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. --> |
|
|
|
# myspace1 |
|
|
|
This model is a fine-tuned version of [d0rj/rut5-base-summ](https://huggingface.co/d0rj/rut5-base-summ) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3282 |
|
- Rouge1: 0.242 |
|
- Rouge2: 0.1107 |
|
- Rougel: 0.2373 |
|
- Rougelsum: 0.2351 |
|
- Gen Len: 55.65 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 25 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| No log | 1.0 | 90 | 2.3719 | 0.2088 | 0.0817 | 0.2064 | 0.2072 | 39.99 | |
|
| No log | 2.0 | 180 | 2.3539 | 0.2393 | 0.1057 | 0.2367 | 0.2363 | 42.87 | |
|
| No log | 3.0 | 270 | 2.3378 | 0.2249 | 0.0893 | 0.2194 | 0.2187 | 46.75 | |
|
| No log | 4.0 | 360 | 2.3271 | 0.2263 | 0.0935 | 0.2199 | 0.2195 | 49.99 | |
|
| No log | 5.0 | 450 | 2.3220 | 0.2412 | 0.1001 | 0.2318 | 0.2328 | 53.65 | |
|
| 1.7281 | 6.0 | 540 | 2.3206 | 0.2305 | 0.0978 | 0.2238 | 0.223 | 55.28 | |
|
| 1.7281 | 7.0 | 630 | 2.3194 | 0.2338 | 0.1044 | 0.2276 | 0.2274 | 55.01 | |
|
| 1.7281 | 8.0 | 720 | 2.3197 | 0.2449 | 0.1085 | 0.2383 | 0.237 | 55.42 | |
|
| 1.7281 | 9.0 | 810 | 2.3201 | 0.2526 | 0.1114 | 0.2481 | 0.2455 | 56.34 | |
|
| 1.7281 | 10.0 | 900 | 2.3204 | 0.238 | 0.103 | 0.2331 | 0.2302 | 55.9 | |
|
| 1.7281 | 11.0 | 990 | 2.3214 | 0.2372 | 0.1133 | 0.2334 | 0.231 | 55.46 | |
|
| 1.4551 | 12.0 | 1080 | 2.3220 | 0.2418 | 0.1158 | 0.2361 | 0.2352 | 56.44 | |
|
| 1.4551 | 13.0 | 1170 | 2.3229 | 0.25 | 0.1209 | 0.2454 | 0.2433 | 55.8 | |
|
| 1.4551 | 14.0 | 1260 | 2.3240 | 0.2507 | 0.124 | 0.2465 | 0.2448 | 55.09 | |
|
| 1.4551 | 15.0 | 1350 | 2.3247 | 0.2561 | 0.1247 | 0.2505 | 0.2491 | 54.39 | |
|
| 1.4551 | 16.0 | 1440 | 2.3256 | 0.2452 | 0.1198 | 0.2396 | 0.2379 | 53.75 | |
|
| 1.3726 | 17.0 | 1530 | 2.3258 | 0.2367 | 0.1137 | 0.2305 | 0.2285 | 54.84 | |
|
| 1.3726 | 18.0 | 1620 | 2.3265 | 0.2403 | 0.1159 | 0.2349 | 0.2329 | 54.56 | |
|
| 1.3726 | 19.0 | 1710 | 2.3264 | 0.2381 | 0.1132 | 0.2335 | 0.2303 | 55.01 | |
|
| 1.3726 | 20.0 | 1800 | 2.3270 | 0.2418 | 0.1133 | 0.2371 | 0.2346 | 55.21 | |
|
| 1.3726 | 21.0 | 1890 | 2.3273 | 0.2413 | 0.1133 | 0.2368 | 0.234 | 55.84 | |
|
| 1.3726 | 22.0 | 1980 | 2.3275 | 0.2431 | 0.1137 | 0.2388 | 0.2367 | 55.82 | |
|
| 1.3286 | 23.0 | 2070 | 2.3277 | 0.2424 | 0.1106 | 0.2376 | 0.2354 | 56.05 | |
|
| 1.3286 | 24.0 | 2160 | 2.3280 | 0.242 | 0.1107 | 0.2373 | 0.2351 | 55.87 | |
|
| 1.3286 | 25.0 | 2250 | 2.3282 | 0.242 | 0.1107 | 0.2373 | 0.2351 | 55.65 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
