childes-multilingual-5M-gpt2_lm-model

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

  • Loss: 1.6555
  • Model Preparation Time: 0.0013
  • Perplexity: 5.2355
  • Bpc: 2.3883
  • Spike Seg Type Fscore Entropy: 0.3332
  • Spike Seg Boundary Fscore Entropy: 0.6727
  • Absolute Seg Type Fscore Entropy: 0.3995
  • Absolute Seg Boundary Fscore Entropy: 0.6660
  • Spike Seg Type Fscore Increase in entropy: 0.2810
  • Spike Seg Boundary Fscore Increase in entropy: 0.6403
  • Absolute Seg Type Fscore Increase in entropy: 0.3995
  • Absolute Seg Boundary Fscore Increase in entropy: 0.6829
  • Spike Seg Type Fscore Loss: 0.2547
  • Spike Seg Boundary Fscore Loss: 0.5907
  • Absolute Seg Type Fscore Loss: 0.2617
  • Absolute Seg Boundary Fscore Loss: 0.5870
  • Spike Seg Type Fscore Increase in loss: 0.2604
  • Spike Seg Boundary Fscore Increase in loss: 0.6271
  • Absolute Seg Type Fscore Increase in loss: 0.3425
  • Absolute Seg Boundary Fscore Increase in loss: 0.6148
  • Spike Seg Type Fscore Rank: 0.3266
  • Spike Seg Boundary Fscore Rank: 0.6156
  • Absolute Seg Type Fscore Rank: 0.2731
  • Absolute Seg Boundary Fscore Rank: 0.5804
  • Spike Seg Type Fscore Increase in rank: 0.3286
  • Spike Seg Boundary Fscore Increase in rank: 0.6367
  • Absolute Seg Type Fscore Increase in rank: 0.3916
  • Absolute Seg Boundary Fscore Increase in rank: 0.6459
  • Spike Seg Type Fscore Boundary prediction: 0.2640
  • Spike Seg Boundary Fscore Boundary prediction: 0.6591
  • Absolute Seg Type Fscore Boundary prediction: 0.4087
  • Absolute Seg Boundary Fscore Boundary prediction: 0.6786
  • Spike Seg Type Fscore Increase in boundary prediction: 0.2521
  • Spike Seg Boundary Fscore Increase in boundary prediction: 0.6460
  • Absolute Seg Type Fscore Increase in boundary prediction: 0.3788
  • Absolute Seg Boundary Fscore Increase in boundary prediction: 0.6863
  • Spike Seg Type Fscore Majority vote cutoff: 0.4145
  • Spike Seg Type Fscore Majority vote spike: 0.2634
  • Absolute Seg Type Fscore Majority vote cutoff: 0.4730
  • Absolute Seg Type Fscore Majority vote spike: 0.3846
  • Spike Seg Boundary Fscore Majority vote cutoff: 0.7263
  • Spike Seg Boundary Fscore Majority vote spike: 0.6556
  • Absolute Seg Boundary Fscore Majority vote cutoff: 0.7257
  • Absolute Seg Boundary Fscore Majority vote spike: 0.7086

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: 0.001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 60000
  • training_steps: 200000

Training results

Training Loss Epoch Step Validation Loss Model Preparation Time Perplexity Bpc Spike Seg Type Fscore Entropy Spike Seg Boundary Fscore Entropy Absolute Seg Type Fscore Entropy Absolute Seg Boundary Fscore Entropy Spike Seg Type Fscore Increase in entropy Spike Seg Boundary Fscore Increase in entropy Absolute Seg Type Fscore Increase in entropy Absolute Seg Boundary Fscore Increase in entropy Spike Seg Type Fscore Loss Spike Seg Boundary Fscore Loss Absolute Seg Type Fscore Loss Absolute Seg Boundary Fscore Loss Spike Seg Type Fscore Increase in loss Spike Seg Boundary Fscore Increase in loss Absolute Seg Type Fscore Increase in loss Absolute Seg Boundary Fscore Increase in loss Spike Seg Type Fscore Rank Spike Seg Boundary Fscore Rank Absolute Seg Type Fscore Rank Absolute Seg Boundary Fscore Rank Spike Seg Type Fscore Increase in rank Spike Seg Boundary Fscore Increase in rank Absolute Seg Type Fscore Increase in rank Absolute Seg Boundary Fscore Increase in rank Spike Seg Type Fscore Boundary prediction Spike Seg Boundary Fscore Boundary prediction Absolute Seg Type Fscore Boundary prediction Absolute Seg Boundary Fscore Boundary prediction Spike Seg Type Fscore Increase in boundary prediction Spike Seg Boundary Fscore Increase in boundary prediction Absolute Seg Type Fscore Increase in boundary prediction Absolute Seg Boundary Fscore Increase in boundary prediction Spike Seg Type Fscore Majority vote cutoff Spike Seg Type Fscore Majority vote spike Absolute Seg Type Fscore Majority vote cutoff Absolute Seg Type Fscore Majority vote spike Spike Seg Boundary Fscore Majority vote cutoff Spike Seg Boundary Fscore Majority vote spike Absolute Seg Boundary Fscore Majority vote cutoff Absolute Seg Boundary Fscore Majority vote spike
1.4761 45.3515 20000 1.5296 0.0013 4.6161 2.2067 0.2933 0.6533 0.3764 0.6823 0.2437 0.6296 0.3826 0.6783 0.2627 0.6248 0.2715 0.6075 0.2579 0.6404 0.3646 0.6707 0.3207 0.6292 0.2926 0.5841 0.3191 0.6343 0.3784 0.6506 0.2459 0.6490 0.3313 0.6050 0.2195 0.6348 0.3329 0.6364 0.3773 0.2403 0.4597 0.3700 0.7046 0.6493 0.7398 0.7064
1.3324 90.7029 40000 1.4757 0.0013 4.3740 2.1290 0.3304 0.6852 0.4470 0.7163 0.2676 0.6494 0.4321 0.7014 0.2840 0.6297 0.2792 0.6112 0.2784 0.6536 0.3758 0.6853 0.3470 0.6397 0.2836 0.5838 0.3302 0.6511 0.3965 0.6604 0.2511 0.6597 0.3352 0.6558 0.2345 0.6419 0.0863 0.3805 0.4189 0.2606 0.4828 0.4033 0.7202 0.6602 0.7298 0.7267
1.263 136.0544 60000 1.4784 0.0013 4.3861 2.1329 0.3207 0.6751 0.4275 0.6999 0.2719 0.6483 0.4223 0.6899 0.2763 0.6338 0.2752 0.6014 0.2785 0.6528 0.3770 0.6798 0.3401 0.6308 0.3102 0.5725 0.3417 0.6461 0.3974 0.6600 0.2657 0.6598 0.2714 0.6686 0.2416 0.6441 0.3684 0.6782 0.4071 0.2588 0.4663 0.4118 0.7277 0.6605 0.7610 0.7240
1.1888 181.4059 80000 1.5073 0.0013 4.5144 2.1745 0.3370 0.6769 0.3840 0.6951 0.2663 0.6444 0.4274 0.6987 0.2671 0.6254 0.2660 0.5993 0.2703 0.6389 0.3555 0.6727 0.3440 0.6310 0.3263 0.5892 0.3298 0.6393 0.3903 0.6569 0.2676 0.6655 0.4326 0.6851 0.2449 0.6462 0.3689 0.6849 0.4143 0.2596 0.4759 0.3976 0.7280 0.6618 0.7646 0.7208
1.1401 226.7574 100000 1.5238 0.0013 4.5894 2.1983 0.3344 0.6828 0.4377 0.6887 0.2711 0.6473 0.4270 0.6977 0.2684 0.6173 0.2735 0.5961 0.2744 0.6365 0.3572 0.6661 0.3377 0.6224 0.3051 0.5802 0.3337 0.6383 0.3790 0.6468 0.2686 0.6594 0.3810 0.5867 0.2505 0.6458 0.3485 0.6866 0.4157 0.2553 0.4973 0.3907 0.7224 0.6580 0.7488 0.7171
1.1035 272.1088 120000 1.5710 0.0013 4.8115 2.2665 0.3319 0.6690 0.4017 0.6756 0.2869 0.6469 0.4084 0.6887 0.2560 0.6048 0.2697 0.5921 0.2766 0.6333 0.3519 0.6525 0.3310 0.6193 0.3101 0.5803 0.3286 0.6391 0.3974 0.6524 0.2679 0.6574 0.2611 0.6827 0.2541 0.6448 0.3777 0.6850 0.4218 0.2600 0.4547 0.3892 0.7235 0.6517 0.7486 0.7108
1.0732 317.4603 140000 1.5963 0.0013 4.9347 2.3030 0.3276 0.6665 0.4038 0.6610 0.2714 0.6390 0.3942 0.6810 0.2579 0.6023 0.2643 0.5904 0.2675 0.6285 0.3478 0.6483 0.3271 0.6237 0.3101 0.5817 0.3249 0.6337 0.3866 0.6459 0.2621 0.6527 0.2926 0.6842 0.2462 0.6416 0.3665 0.6823 0.4058 0.2475 0.4579 0.3821 0.7231 0.6523 0.7451 0.7062
1.0485 362.8118 160000 1.6166 0.0013 5.0360 2.3323 0.3348 0.6715 0.3927 0.6747 0.2878 0.6467 0.4025 0.6911 0.2556 0.5968 0.2590 0.5856 0.2668 0.6309 0.3465 0.6374 0.3375 0.6173 0.3081 0.5802 0.3263 0.6358 0.3717 0.6477 0.2698 0.6594 0.2664 0.6875 0.2537 0.6470 0.3871 0.6892 0.4088 0.2645 0.4867 0.3960 0.7259 0.6569 0.7347 0.7088
1.0264 408.1633 180000 1.6407 0.0013 5.1590 2.3671 0.3316 0.6720 0.3952 0.6720 0.2754 0.6424 0.4033 0.6893 0.2590 0.5971 0.2607 0.5865 0.2590 0.6276 0.3442 0.6562 0.3342 0.6176 0.3020 0.5768 0.3258 0.6388 0.3727 0.6448 0.2613 0.6539 0.4009 0.6823 0.2541 0.6432 0.3713 0.6809 0.4032 0.2569 0.4795 0.3866 0.7269 0.6555 0.7511 0.7086
1.009 453.5147 200000 1.6555 0.0013 5.2355 2.3883 0.3332 0.6727 0.3995 0.6660 0.2810 0.6403 0.3995 0.6829 0.2547 0.5907 0.2617 0.5870 0.2604 0.6271 0.3425 0.6148 0.3266 0.6156 0.2731 0.5804 0.3286 0.6367 0.3916 0.6459 0.2640 0.6591 0.4087 0.6786 0.2521 0.6460 0.3788 0.6863 0.4145 0.2634 0.4730 0.3846 0.7263 0.6556 0.7257 0.7086

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.18.0
  • Tokenizers 0.19.1
Downloads last month
70
Safetensors
Model size
4.81M 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.