Edit model card

myspace1

This model is a fine-tuned version of 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
Downloads last month

-

Downloads are not tracked for this model. How to track
Unable to determine this model's library. Check the docs .

Finetuned from