Edit model card

MIDICausalFinetuning4

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0222

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 500

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 1 4.7564
No log 2.0 2 4.2796
No log 3.0 3 3.9949
No log 4.0 4 3.7963
No log 5.0 5 3.6377
No log 6.0 6 3.5060
No log 7.0 7 3.3965
No log 8.0 8 3.2999
No log 9.0 9 3.2098
No log 10.0 10 3.1233
No log 11.0 11 3.0391
No log 12.0 12 2.9529
No log 13.0 13 2.8613
No log 14.0 14 2.7629
No log 15.0 15 2.6630
No log 16.0 16 2.5652
No log 17.0 17 2.4777
No log 18.0 18 2.4026
No log 19.0 19 2.3401
No log 20.0 20 2.2842
No log 21.0 21 2.2316
No log 22.0 22 2.1806
No log 23.0 23 2.1304
No log 24.0 24 2.0802
No log 25.0 25 2.0289
No log 26.0 26 1.9770
No log 27.0 27 1.9237
No log 28.0 28 1.8690
No log 29.0 29 1.8143
No log 30.0 30 1.7591
No log 31.0 31 1.7008
No log 32.0 32 1.6392
No log 33.0 33 1.5777
No log 34.0 34 1.5191
No log 35.0 35 1.4578
No log 36.0 36 1.3959
No log 37.0 37 1.3435
No log 38.0 38 1.2901
No log 39.0 39 1.2289
No log 40.0 40 1.1688
No log 41.0 41 1.1256
No log 42.0 42 1.0843
No log 43.0 43 1.0364
No log 44.0 44 0.9923
No log 45.0 45 0.9577
No log 46.0 46 0.9238
No log 47.0 47 0.8884
No log 48.0 48 0.8536
No log 49.0 49 0.8185
No log 50.0 50 0.7881
No log 51.0 51 0.7595
No log 52.0 52 0.7320
No log 53.0 53 0.7073
No log 54.0 54 0.6851
No log 55.0 55 0.6594
No log 56.0 56 0.6342
No log 57.0 57 0.6123
No log 58.0 58 0.5941
No log 59.0 59 0.5731
No log 60.0 60 0.5497
No log 61.0 61 0.5318
No log 62.0 62 0.5164
No log 63.0 63 0.4998
No log 64.0 64 0.4823
No log 65.0 65 0.4658
No log 66.0 66 0.4524
No log 67.0 67 0.4396
No log 68.0 68 0.4273
No log 69.0 69 0.4139
No log 70.0 70 0.4016
No log 71.0 71 0.3905
No log 72.0 72 0.3796
No log 73.0 73 0.3703
No log 74.0 74 0.3607
No log 75.0 75 0.3503
No log 76.0 76 0.3403
No log 77.0 77 0.3316
No log 78.0 78 0.3226
No log 79.0 79 0.3131
No log 80.0 80 0.3053
No log 81.0 81 0.2981
No log 82.0 82 0.2909
No log 83.0 83 0.2849
No log 84.0 84 0.2810
No log 85.0 85 0.2748
No log 86.0 86 0.2674
No log 87.0 87 0.2595
No log 88.0 88 0.2523
No log 89.0 89 0.2461
No log 90.0 90 0.2407
No log 91.0 91 0.2358
No log 92.0 92 0.2298
No log 93.0 93 0.2245
No log 94.0 94 0.2207
No log 95.0 95 0.2171
No log 96.0 96 0.2133
No log 97.0 97 0.2097
No log 98.0 98 0.2066
No log 99.0 99 0.2025
No log 100.0 100 0.1974
No log 101.0 101 0.1926
No log 102.0 102 0.1886
No log 103.0 103 0.1853
No log 104.0 104 0.1818
No log 105.0 105 0.1788
No log 106.0 106 0.1756
No log 107.0 107 0.1718
No log 108.0 108 0.1680
No log 109.0 109 0.1643
No log 110.0 110 0.1619
No log 111.0 111 0.1594
No log 112.0 112 0.1563
No log 113.0 113 0.1535
No log 114.0 114 0.1506
No log 115.0 115 0.1468
No log 116.0 116 0.1431
No log 117.0 117 0.1401
No log 118.0 118 0.1382
No log 119.0 119 0.1365
No log 120.0 120 0.1345
No log 121.0 121 0.1325
No log 122.0 122 0.1303
No log 123.0 123 0.1277
No log 124.0 124 0.1250
No log 125.0 125 0.1223
No log 126.0 126 0.1189
No log 127.0 127 0.1156
No log 128.0 128 0.1127
No log 129.0 129 0.1102
No log 130.0 130 0.1077
No log 131.0 131 0.1054
No log 132.0 132 0.1038
No log 133.0 133 0.1030
No log 134.0 134 0.1023
No log 135.0 135 0.1007
No log 136.0 136 0.0984
No log 137.0 137 0.0958
No log 138.0 138 0.0938
No log 139.0 139 0.0933
No log 140.0 140 0.0916
No log 141.0 141 0.0892
No log 142.0 142 0.0870
No log 143.0 143 0.0851
No log 144.0 144 0.0835
No log 145.0 145 0.0822
No log 146.0 146 0.0809
No log 147.0 147 0.0805
No log 148.0 148 0.0799
No log 149.0 149 0.0789
No log 150.0 150 0.0770
No log 151.0 151 0.0751
No log 152.0 152 0.0740
No log 153.0 153 0.0737
No log 154.0 154 0.0731
No log 155.0 155 0.0719
No log 156.0 156 0.0702
No log 157.0 157 0.0686
No log 158.0 158 0.0677
No log 159.0 159 0.0674
No log 160.0 160 0.0672
No log 161.0 161 0.0669
No log 162.0 162 0.0663
No log 163.0 163 0.0654
No log 164.0 164 0.0644
No log 165.0 165 0.0634
No log 166.0 166 0.0620
No log 167.0 167 0.0606
No log 168.0 168 0.0595
No log 169.0 169 0.0589
No log 170.0 170 0.0583
No log 171.0 171 0.0578
No log 172.0 172 0.0573
No log 173.0 173 0.0572
No log 174.0 174 0.0574
No log 175.0 175 0.0572
No log 176.0 176 0.0566
No log 177.0 177 0.0556
No log 178.0 178 0.0545
No log 179.0 179 0.0535
No log 180.0 180 0.0529
No log 181.0 181 0.0526
No log 182.0 182 0.0521
No log 183.0 183 0.0515
No log 184.0 184 0.0510
No log 185.0 185 0.0507
No log 186.0 186 0.0507
No log 187.0 187 0.0505
No log 188.0 188 0.0499
No log 189.0 189 0.0492
No log 190.0 190 0.0486
No log 191.0 191 0.0480
No log 192.0 192 0.0476
No log 193.0 193 0.0471
No log 194.0 194 0.0468
No log 195.0 195 0.0464
No log 196.0 196 0.0461
No log 197.0 197 0.0457
No log 198.0 198 0.0453
No log 199.0 199 0.0449
No log 200.0 200 0.0445
No log 201.0 201 0.0442
No log 202.0 202 0.0439
No log 203.0 203 0.0437
No log 204.0 204 0.0434
No log 205.0 205 0.0430
No log 206.0 206 0.0426
No log 207.0 207 0.0423
No log 208.0 208 0.0419
No log 209.0 209 0.0415
No log 210.0 210 0.0412
No log 211.0 211 0.0409
No log 212.0 212 0.0406
No log 213.0 213 0.0403
No log 214.0 214 0.0402
No log 215.0 215 0.0400
No log 216.0 216 0.0398
No log 217.0 217 0.0395
No log 218.0 218 0.0392
No log 219.0 219 0.0389
No log 220.0 220 0.0387
No log 221.0 221 0.0385
No log 222.0 222 0.0384
No log 223.0 223 0.0382
No log 224.0 224 0.0380
No log 225.0 225 0.0376
No log 226.0 226 0.0373
No log 227.0 227 0.0369
No log 228.0 228 0.0366
No log 229.0 229 0.0364
No log 230.0 230 0.0362
No log 231.0 231 0.0361
No log 232.0 232 0.0359
No log 233.0 233 0.0358
No log 234.0 234 0.0357
No log 235.0 235 0.0355
No log 236.0 236 0.0353
No log 237.0 237 0.0351
No log 238.0 238 0.0349
No log 239.0 239 0.0347
No log 240.0 240 0.0346
No log 241.0 241 0.0345
No log 242.0 242 0.0343
No log 243.0 243 0.0341
No log 244.0 244 0.0340
No log 245.0 245 0.0338
No log 246.0 246 0.0337
No log 247.0 247 0.0336
No log 248.0 248 0.0336
No log 249.0 249 0.0335
No log 250.0 250 0.0334
No log 251.0 251 0.0333
No log 252.0 252 0.0331
No log 253.0 253 0.0329
No log 254.0 254 0.0327
No log 255.0 255 0.0324
No log 256.0 256 0.0322
No log 257.0 257 0.0320
No log 258.0 258 0.0319
No log 259.0 259 0.0318
No log 260.0 260 0.0317
No log 261.0 261 0.0316
No log 262.0 262 0.0315
No log 263.0 263 0.0315
No log 264.0 264 0.0314
No log 265.0 265 0.0313
No log 266.0 266 0.0313
No log 267.0 267 0.0311
No log 268.0 268 0.0310
No log 269.0 269 0.0309
No log 270.0 270 0.0307
No log 271.0 271 0.0306
No log 272.0 272 0.0305
No log 273.0 273 0.0303
No log 274.0 274 0.0302
No log 275.0 275 0.0301
No log 276.0 276 0.0300
No log 277.0 277 0.0299
No log 278.0 278 0.0298
No log 279.0 279 0.0298
No log 280.0 280 0.0297
No log 281.0 281 0.0297
No log 282.0 282 0.0296
No log 283.0 283 0.0296
No log 284.0 284 0.0295
No log 285.0 285 0.0294
No log 286.0 286 0.0293
No log 287.0 287 0.0291
No log 288.0 288 0.0290
No log 289.0 289 0.0289
No log 290.0 290 0.0288
No log 291.0 291 0.0287
No log 292.0 292 0.0286
No log 293.0 293 0.0286
No log 294.0 294 0.0285
No log 295.0 295 0.0284
No log 296.0 296 0.0284
No log 297.0 297 0.0283
No log 298.0 298 0.0282
No log 299.0 299 0.0281
No log 300.0 300 0.0281
No log 301.0 301 0.0280
No log 302.0 302 0.0279
No log 303.0 303 0.0278
No log 304.0 304 0.0277
No log 305.0 305 0.0276
No log 306.0 306 0.0276
No log 307.0 307 0.0275
No log 308.0 308 0.0274
No log 309.0 309 0.0274
No log 310.0 310 0.0273
No log 311.0 311 0.0272
No log 312.0 312 0.0272
No log 313.0 313 0.0271
No log 314.0 314 0.0270
No log 315.0 315 0.0270
No log 316.0 316 0.0269
No log 317.0 317 0.0269
No log 318.0 318 0.0268
No log 319.0 319 0.0268
No log 320.0 320 0.0267
No log 321.0 321 0.0267
No log 322.0 322 0.0266
No log 323.0 323 0.0266
No log 324.0 324 0.0265
No log 325.0 325 0.0264
No log 326.0 326 0.0264
No log 327.0 327 0.0263
No log 328.0 328 0.0262
No log 329.0 329 0.0262
No log 330.0 330 0.0261
No log 331.0 331 0.0260
No log 332.0 332 0.0260
No log 333.0 333 0.0259
No log 334.0 334 0.0259
No log 335.0 335 0.0259
No log 336.0 336 0.0258
No log 337.0 337 0.0258
No log 338.0 338 0.0257
No log 339.0 339 0.0256
No log 340.0 340 0.0256
No log 341.0 341 0.0256
No log 342.0 342 0.0255
No log 343.0 343 0.0255
No log 344.0 344 0.0254
No log 345.0 345 0.0254
No log 346.0 346 0.0254
No log 347.0 347 0.0253
No log 348.0 348 0.0253
No log 349.0 349 0.0253
No log 350.0 350 0.0252
No log 351.0 351 0.0252
No log 352.0 352 0.0252
No log 353.0 353 0.0252
No log 354.0 354 0.0251
No log 355.0 355 0.0251
No log 356.0 356 0.0251
No log 357.0 357 0.0250
No log 358.0 358 0.0250
No log 359.0 359 0.0249
No log 360.0 360 0.0249
No log 361.0 361 0.0248
No log 362.0 362 0.0248
No log 363.0 363 0.0247
No log 364.0 364 0.0247
No log 365.0 365 0.0246
No log 366.0 366 0.0246
No log 367.0 367 0.0245
No log 368.0 368 0.0245
No log 369.0 369 0.0244
No log 370.0 370 0.0244
No log 371.0 371 0.0244
No log 372.0 372 0.0243
No log 373.0 373 0.0243
No log 374.0 374 0.0242
No log 375.0 375 0.0242
No log 376.0 376 0.0241
No log 377.0 377 0.0241
No log 378.0 378 0.0241
No log 379.0 379 0.0241
No log 380.0 380 0.0240
No log 381.0 381 0.0240
No log 382.0 382 0.0240
No log 383.0 383 0.0240
No log 384.0 384 0.0239
No log 385.0 385 0.0239
No log 386.0 386 0.0239
No log 387.0 387 0.0238
No log 388.0 388 0.0238
No log 389.0 389 0.0238
No log 390.0 390 0.0238
No log 391.0 391 0.0237
No log 392.0 392 0.0237
No log 393.0 393 0.0237
No log 394.0 394 0.0236
No log 395.0 395 0.0236
No log 396.0 396 0.0235
No log 397.0 397 0.0235
No log 398.0 398 0.0235
No log 399.0 399 0.0235
No log 400.0 400 0.0234
No log 401.0 401 0.0234
No log 402.0 402 0.0234
No log 403.0 403 0.0234
No log 404.0 404 0.0234
No log 405.0 405 0.0233
No log 406.0 406 0.0233
No log 407.0 407 0.0233
No log 408.0 408 0.0233
No log 409.0 409 0.0233
No log 410.0 410 0.0233
No log 411.0 411 0.0232
No log 412.0 412 0.0232
No log 413.0 413 0.0232
No log 414.0 414 0.0232
No log 415.0 415 0.0232
No log 416.0 416 0.0231
No log 417.0 417 0.0231
No log 418.0 418 0.0231
No log 419.0 419 0.0231
No log 420.0 420 0.0231
No log 421.0 421 0.0230
No log 422.0 422 0.0230
No log 423.0 423 0.0230
No log 424.0 424 0.0230
No log 425.0 425 0.0229
No log 426.0 426 0.0229
No log 427.0 427 0.0229
No log 428.0 428 0.0228
No log 429.0 429 0.0228
No log 430.0 430 0.0228
No log 431.0 431 0.0228
No log 432.0 432 0.0228
No log 433.0 433 0.0227
No log 434.0 434 0.0227
No log 435.0 435 0.0227
No log 436.0 436 0.0227
No log 437.0 437 0.0227
No log 438.0 438 0.0227
No log 439.0 439 0.0226
No log 440.0 440 0.0226
No log 441.0 441 0.0226
No log 442.0 442 0.0226
No log 443.0 443 0.0226
No log 444.0 444 0.0226
No log 445.0 445 0.0226
No log 446.0 446 0.0226
No log 447.0 447 0.0225
No log 448.0 448 0.0225
No log 449.0 449 0.0225
No log 450.0 450 0.0225
No log 451.0 451 0.0225
No log 452.0 452 0.0225
No log 453.0 453 0.0225
No log 454.0 454 0.0224
No log 455.0 455 0.0224
No log 456.0 456 0.0224
No log 457.0 457 0.0224
No log 458.0 458 0.0224
No log 459.0 459 0.0224
No log 460.0 460 0.0224
No log 461.0 461 0.0224
No log 462.0 462 0.0223
No log 463.0 463 0.0223
No log 464.0 464 0.0223
No log 465.0 465 0.0223
No log 466.0 466 0.0223
No log 467.0 467 0.0223
No log 468.0 468 0.0223
No log 469.0 469 0.0223
No log 470.0 470 0.0223
No log 471.0 471 0.0223
No log 472.0 472 0.0223
No log 473.0 473 0.0223
No log 474.0 474 0.0223
No log 475.0 475 0.0222
No log 476.0 476 0.0222
No log 477.0 477 0.0222
No log 478.0 478 0.0222
No log 479.0 479 0.0222
No log 480.0 480 0.0222
No log 481.0 481 0.0222
No log 482.0 482 0.0222
No log 483.0 483 0.0222
No log 484.0 484 0.0222
No log 485.0 485 0.0222
No log 486.0 486 0.0222
No log 487.0 487 0.0222
No log 488.0 488 0.0222
No log 489.0 489 0.0222
No log 490.0 490 0.0222
No log 491.0 491 0.0222
No log 492.0 492 0.0222
No log 493.0 493 0.0222
No log 494.0 494 0.0222
No log 495.0 495 0.0222
No log 496.0 496 0.0222
No log 497.0 497 0.0222
No log 498.0 498 0.0222
No log 499.0 499 0.0222
0.3551 500.0 500 0.0222

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
5
Safetensors
Model size
12.1M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.