answerdotai-ModernBERT-large_20250111-224237

This model is a fine-tuned version of answerdotai/ModernBERT-large on an unknown dataset. It achieves the following results on the evaluation set:

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 64
  • total_train_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
5.8618 1.0 4160 0.1579 0.6785 0.9929 0.8061 0.8303 0.7597 0.9835 0.8573 0.8836 0.7958 0.9772 0.8772 0.9028 0.8144 0.9734 0.8868 0.9117 0.8279 0.9710 0.8938 0.9180 0.8403 0.9684 0.8998 0.9234 0.8481 0.9660 0.9032 0.9264 0.8546 0.9641 0.9061 0.9290 0.8602 0.9631 0.9088 0.9313 0.8649 0.9617 0.9107 0.9330 0.8691 0.9604 0.9125 0.9345 0.8721 0.9593 0.9136 0.9355 0.8747 0.9579 0.9144 0.9363 0.8774 0.9571 0.9155 0.9372 0.8802 0.9561 0.9166 0.9382 0.8830 0.9556 0.9179 0.9392 0.8854 0.9552 0.9190 0.9402 0.8873 0.9543 0.9196 0.9407 0.8891 0.9537 0.9202 0.9412 0.8909 0.9534 0.9211 0.9419 0.8926 0.9525 0.9216 0.9424 0.8944 0.9521 0.9224 0.9430 0.8955 0.9513 0.9225 0.9432 0.8965 0.9502 0.9225 0.9433 0.8969 0.9496 0.9225 0.9433 0.8982 0.9484 0.9226 0.9435 0.8993 0.9475 0.9228 0.9437 0.9004 0.9469 0.9230 0.9439 0.9019 0.9467 0.9237 0.9444 0.9034 0.9461 0.9243 0.9449 0.9047 0.9454 0.9246 0.9452 0.9056 0.9450 0.9248 0.9454 0.9065 0.9446 0.9252 0.9457 0.9074 0.9440 0.9254 0.9459 0.9085 0.9438 0.9258 0.9462 0.9093 0.9433 0.9260 0.9464 0.9100 0.9428 0.9261 0.9466 0.9109 0.9423 0.9263 0.9467 0.9118 0.9418 0.9266 0.9470 0.9124 0.9417 0.9268 0.9472 0.9130 0.9412 0.9269 0.9472 0.9140 0.9406 0.9271 0.9474 0.9146 0.9398 0.9271 0.9474 0.9158 0.9396 0.9275 0.9478 0.9170 0.9392 0.9279 0.9482 0.9177 0.9387 0.9281 0.9483 0.9185 0.9383 0.9283 0.9485 0.9193 0.9376 0.9284 0.9486 0.9200 0.9370 0.9284 0.9487 0.9206 0.9367 0.9286 0.9488 0.9214 0.9363 0.9288 0.9490 0.9219 0.9356 0.9287 0.9489 0.9224 0.9352 0.9288 0.9490 0.9228 0.9350 0.9289 0.9491 0.9234 0.9350 0.9292 0.9494 0.9241 0.9345 0.9293 0.9494 0.9250 0.9341 0.9295 0.9497 0.9256 0.9339 0.9298 0.9499 0.9269 0.9336 0.9302 0.9502 0.9273 0.9331 0.9302 0.9502 0.9276 0.9323 0.9299 0.9501 0.9284 0.9318 0.9301 0.9502 0.9290 0.9313 0.9301 0.9503 0.9296 0.9309 0.9303 0.9504 0.9306 0.9307 0.9307 0.9507 0.9320 0.9302 0.9311 0.9511 0.9327 0.9293 0.9310 0.9510 0.9333 0.9288 0.9310 0.9511 0.9340 0.9281 0.9310 0.9511 0.9347 0.9273 0.9310 0.9512 0.9354 0.9263 0.9309 0.9511 0.9364 0.9260 0.9311 0.9513 0.9373 0.9250 0.9311 0.9514 0.9383 0.9242 0.9312 0.9515 0.9392 0.9235 0.9313 0.9516 0.9402 0.9230 0.9315 0.9518 0.9410 0.9218 0.9313 0.9517 0.9421 0.9204 0.9311 0.9516 0.9428 0.9198 0.9312 0.9517 0.9439 0.9192 0.9314 0.9519 0.9448 0.9179 0.9312 0.9518 0.9460 0.9164 0.9310 0.9517 0.9479 0.9152 0.9313 0.9520 0.9493 0.9140 0.9313 0.9521 0.9504 0.9125 0.9311 0.9520 0.9517 0.9101 0.9304 0.9516 0.9529 0.9085 0.9302 0.9515 0.9542 0.9062 0.9296 0.9512 0.9555 0.9041 0.9291 0.9510 0.9566 0.9028 0.9289 0.9509 0.9577 0.9005 0.9282 0.9505 0.9600 0.8975 0.9277 0.9503 0.9620 0.8948 0.9272 0.9501 0.9639 0.89 0.9255 0.9491 0.9662 0.8857 0.9242 0.9484 0.9697 0.8790 0.9221 0.9472 0.9744 0.8685 0.9184 0.9452 0.9794 0.8508 0.9106 0.9406 0.9860 0.8112 0.8901 0.9288
3.574 2.0 8320 0.2679 0.9139 0.9550 0.9340 0.9520 0.9191 0.9520 0.9352 0.9531 0.9225 0.9505 0.9363 0.9540 0.9246 0.9493 0.9368 0.9545 0.9251 0.9479 0.9364 0.9542 0.9262 0.9472 0.9365 0.9544 0.9271 0.9468 0.9368 0.9546 0.9282 0.9463 0.9372 0.9549 0.9284 0.9460 0.9371 0.9549 0.9287 0.9453 0.9369 0.9548 0.9293 0.9449 0.9370 0.9549 0.9298 0.9449 0.9373 0.9550 0.9301 0.9445 0.9372 0.9550 0.9302 0.9440 0.9371 0.9549 0.9304 0.9437 0.9370 0.9549 0.9304 0.9435 0.9369 0.9548 0.9308 0.9434 0.9370 0.9549 0.9312 0.9432 0.9371 0.9550 0.9312 0.9431 0.9371 0.9550 0.9314 0.9429 0.9371 0.9550 0.9316 0.9428 0.9372 0.9551 0.9317 0.9428 0.9372 0.9551 0.9317 0.9423 0.9370 0.9549 0.9319 0.9421 0.9370 0.9550 0.9321 0.9421 0.9371 0.9550 0.9321 0.9420 0.9370 0.9550 0.9324 0.9420 0.9372 0.9551 0.9327 0.9419 0.9373 0.9552 0.9328 0.9418 0.9373 0.9552 0.9329 0.9418 0.9374 0.9553 0.9329 0.9417 0.9373 0.9552 0.9330 0.9415 0.9372 0.9552 0.9333 0.9412 0.9372 0.9552 0.9336 0.9409 0.9372 0.9552 0.9336 0.9409 0.9373 0.9552 0.9337 0.9408 0.9373 0.9552 0.9339 0.9408 0.9373 0.9553 0.9340 0.9407 0.9373 0.9553 0.9343 0.9406 0.9375 0.9554 0.9344 0.9405 0.9374 0.9554 0.9345 0.9404 0.9374 0.9554 0.9345 0.9402 0.9373 0.9553 0.9349 0.94 0.9374 0.9554 0.9353 0.9399 0.9376 0.9555 0.9356 0.9399 0.9378 0.9557 0.9356 0.9395 0.9376 0.9555 0.9357 0.9395 0.9376 0.9556 0.9358 0.9390 0.9374 0.9554 0.9360 0.9388 0.9374 0.9554 0.9360 0.9385 0.9373 0.9554 0.9363 0.9384 0.9374 0.9554 0.9364 0.9384 0.9374 0.9555 0.9366 0.9384 0.9375 0.9555 0.9366 0.9384 0.9375 0.9556 0.9368 0.9383 0.9376 0.9556 0.9370 0.9383 0.9377 0.9557 0.9374 0.9383 0.9379 0.9558 0.9374 0.9382 0.9378 0.9558 0.9374 0.9382 0.9378 0.9558 0.9374 0.9382 0.9378 0.9558 0.9375 0.9382 0.9378 0.9558 0.9376 0.9382 0.9379 0.9558 0.9379 0.9380 0.9379 0.9559 0.9381 0.9379 0.9380 0.9559 0.9381 0.9377 0.9379 0.9559 0.9383 0.9375 0.9379 0.9559 0.9386 0.9375 0.9380 0.9560 0.9387 0.9372 0.9379 0.9559 0.9387 0.9372 0.9379 0.9559 0.9388 0.9370 0.9379 0.9559 0.9389 0.9368 0.9378 0.9559 0.9391 0.9368 0.9380 0.9560 0.9393 0.9364 0.9378 0.9559 0.9393 0.9364 0.9378 0.9559 0.9393 0.9363 0.9378 0.9559 0.9396 0.9361 0.9378 0.9559 0.9398 0.9360 0.9379 0.9560 0.9404 0.9360 0.9382 0.9562 0.9407 0.9359 0.9383 0.9562 0.9409 0.9359 0.9384 0.9563 0.9410 0.9358 0.9384 0.9563 0.9411 0.9357 0.9384 0.9563 0.9413 0.9355 0.9384 0.9563 0.9413 0.9354 0.9383 0.9563 0.9420 0.9354 0.9387 0.9566 0.9423 0.9352 0.9388 0.9566 0.9428 0.9352 0.9390 0.9568 0.9432 0.9350 0.9391 0.9569 0.9438 0.9350 0.9393 0.9571 0.9442 0.9347 0.9394 0.9572 0.9449 0.9339 0.9394 0.9572 0.9454 0.9337 0.9395 0.9573 0.9459 0.9330 0.9394 0.9572 0.9463 0.9321 0.9392 0.9571 0.9469 0.9316 0.9392 0.9571 0.9481 0.9308 0.9394 0.9573 0.9491 0.9295 0.9392 0.9573 0.9501 0.9273 0.9386 0.9569 0.9549 0.9229 0.9387 0.9571
1.7597 2.9995 12477 0.3203 0.9384 0.9372 0.9378 0.9558 0.9411 0.9359 0.9385 0.9564 0.9417 0.9350 0.9384 0.9563 0.9421 0.9349 0.9385 0.9564 0.9429 0.9348 0.9388 0.9567 0.9431 0.9348 0.9389 0.9568 0.9432 0.9347 0.9389 0.9568 0.9437 0.9345 0.9391 0.9569 0.9437 0.9344 0.9390 0.9569 0.9438 0.9343 0.9391 0.9569 0.9439 0.9342 0.9390 0.9569 0.9440 0.9339 0.9389 0.9568 0.9442 0.9337 0.9389 0.9568 0.9444 0.9334 0.9389 0.9568 0.9448 0.9334 0.9391 0.9570 0.9449 0.9334 0.9391 0.9570 0.9450 0.9332 0.9391 0.9570 0.9450 0.9332 0.9391 0.9570 0.9452 0.9330 0.9391 0.9570 0.9454 0.9330 0.9392 0.9571 0.9455 0.9329 0.9392 0.9571 0.9455 0.9328 0.9391 0.9570 0.9455 0.9328 0.9391 0.9570 0.9456 0.9328 0.9391 0.9570 0.9456 0.9328 0.9391 0.9570 0.9457 0.9327 0.9391 0.9570 0.9458 0.9326 0.9392 0.9571 0.9459 0.9326 0.9392 0.9571 0.9460 0.9326 0.9392 0.9571 0.9461 0.9325 0.9392 0.9571 0.9462 0.9325 0.9393 0.9572 0.9462 0.9325 0.9393 0.9572 0.9464 0.9325 0.9394 0.9572 0.9465 0.9324 0.9394 0.9572 0.9464 0.9323 0.9393 0.9572 0.9467 0.9323 0.9394 0.9573 0.9467 0.9323 0.9394 0.9573 0.9467 0.9322 0.9394 0.9573 0.9467 0.9322 0.9394 0.9573 0.9467 0.9321 0.9393 0.9572 0.9467 0.9321 0.9393 0.9572 0.9467 0.9321 0.9393 0.9572 0.9468 0.9320 0.9393 0.9572 0.9470 0.9319 0.9394 0.9573 0.9469 0.9317 0.9393 0.9572 0.9469 0.9317 0.9393 0.9572 0.9469 0.9317 0.9393 0.9572 0.9470 0.9317 0.9393 0.9572 0.9471 0.9316 0.9393 0.9572 0.9471 0.9316 0.9393 0.9572 0.9471 0.9316 0.9393 0.9572 0.9472 0.9316 0.9393 0.9572 0.9473 0.9314 0.9393 0.9572 0.9473 0.9314 0.9393 0.9572 0.9474 0.9314 0.9393 0.9572 0.9474 0.9312 0.9392 0.9572 0.9474 0.9312 0.9392 0.9572 0.9473 0.9310 0.9391 0.9571 0.9473 0.9310 0.9391 0.9571 0.9474 0.9310 0.9392 0.9571 0.9474 0.9310 0.9392 0.9571 0.9475 0.9309 0.9391 0.9571 0.9476 0.9307 0.9391 0.9571 0.9476 0.9306 0.9390 0.9571 0.9477 0.9306 0.9390 0.9571 0.9477 0.9306 0.9390 0.9571 0.9477 0.9304 0.9389 0.9570 0.9478 0.9304 0.9390 0.9570 0.9477 0.9302 0.9389 0.9570 0.9479 0.9302 0.9390 0.9570 0.9479 0.9301 0.9389 0.9570 0.9480 0.9299 0.9389 0.9570 0.9481 0.9299 0.9389 0.9570 0.9481 0.9299 0.9389 0.9570 0.9482 0.9299 0.9390 0.9570 0.9482 0.9299 0.9390 0.9570 0.9483 0.9298 0.9389 0.9570 0.9483 0.9297 0.9389 0.9570 0.9484 0.9297 0.9390 0.9571 0.9485 0.9296 0.9390 0.9571 0.9485 0.9294 0.9389 0.9570 0.9485 0.9294 0.9389 0.9570 0.9486 0.9294 0.9389 0.9570 0.9488 0.9294 0.9390 0.9571 0.9491 0.9293 0.9391 0.9572 0.9495 0.9293 0.9393 0.9573 0.9495 0.9292 0.9392 0.9573 0.9496 0.9292 0.9393 0.9573 0.9497 0.9290 0.9392 0.9573 0.9499 0.9289 0.9393 0.9573 0.9501 0.9287 0.9393 0.9573 0.9503 0.9287 0.9394 0.9574 0.9507 0.9285 0.9395 0.9575 0.9509 0.9283 0.9394 0.9575 0.9512 0.9281 0.9395 0.9575 0.9515 0.9277 0.9395 0.9575 0.9520 0.9270 0.9393 0.9575 0.9525 0.9267 0.9394 0.9575 0.9537 0.9246 0.9389 0.9573

Framework versions

  • Transformers 4.48.0.dev0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
29
Safetensors
Model size
396M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for Kyle1668/answerdotai-ModernBERT-large_20250111-224237

Finetuned
(49)
this model