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: 1.7764
  • Model Preparation Time: 0.0013
  • Perplexity: 5.9087
  • Bpc: 2.5628
  • Spike Seg Type Fscore Entropy: 0.4334
  • Spike Seg Boundary Fscore Entropy: 0.7663
  • Absolute Seg Type Fscore Entropy: 0.3804
  • Absolute Seg Boundary Fscore Entropy: 0.6737
  • Spike Seg Type Fscore Increase in entropy: 0.4311
  • Spike Seg Boundary Fscore Increase in entropy: 0.7744
  • Absolute Seg Type Fscore Increase in entropy: 0.4526
  • Absolute Seg Boundary Fscore Increase in entropy: 0.7708
  • Spike Seg Type Fscore Loss: 0.3207
  • Spike Seg Boundary Fscore Loss: 0.6605
  • Absolute Seg Type Fscore Loss: 0.2997
  • Absolute Seg Boundary Fscore Loss: 0.6265
  • Spike Seg Type Fscore Increase in loss: 0.3666
  • Spike Seg Boundary Fscore Increase in loss: 0.7129
  • Absolute Seg Type Fscore Increase in loss: 0.3948
  • Absolute Seg Boundary Fscore Increase in loss: 0.6974
  • Spike Seg Type Fscore Rank: 0.3706
  • Spike Seg Boundary Fscore Rank: 0.6566
  • Absolute Seg Type Fscore Rank: 0.2953
  • Absolute Seg Boundary Fscore Rank: 0.6023
  • Spike Seg Type Fscore Increase in rank: 0.4030
  • Spike Seg Boundary Fscore Increase in rank: 0.6944
  • Absolute Seg Type Fscore Increase in rank: 0.3984
  • Absolute Seg Boundary Fscore Increase in rank: 0.6831
  • Spike Seg Type Fscore Boundary prediction: 0.4851
  • Spike Seg Boundary Fscore Boundary prediction: 0.8220
  • Absolute Seg Type Fscore Boundary prediction: 0.5671
  • Absolute Seg Boundary Fscore Boundary prediction: 0.8526
  • Spike Seg Type Fscore Increase in boundary prediction: 0.4868
  • Spike Seg Boundary Fscore Increase in boundary prediction: 0.8249
  • Absolute Seg Type Fscore Increase in boundary prediction: 0.3078
  • Absolute Seg Boundary Fscore Increase in boundary prediction: 0.8533
  • Spike Seg Type Fscore Majority vote cutoff: 0.5195
  • Spike Seg Type Fscore Majority vote spike: 0.4437
  • Absolute Seg Type Fscore Majority vote cutoff: 0.4941
  • Absolute Seg Type Fscore Majority vote spike: 0.5013
  • Spike Seg Boundary Fscore Majority vote cutoff: 0.8395
  • Spike Seg Boundary Fscore Majority vote spike: 0.7897
  • Absolute Seg Boundary Fscore Majority vote cutoff: 0.8047
  • Absolute Seg Boundary Fscore Majority vote spike: 0.8009

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
1.4397 45.2489 20000 1.5926 0.0013 4.9168 2.2977 0.4509 0.7872 0.4073 0.6982 0.4412 0.7861 0.4668 0.7946 0.3229 0.6816 0.3149 0.6441 0.3818 0.7352 0.3793 0.7290 0.3717 0.6597 0.3107 0.6016 0.4150 0.7056 0.3993 0.6905 0.4849 0.8247 0.5396 0.8410 0.4850 0.8267 0.5381 0.8429 0.54 0.4457 0.5563 0.5173 0.8435 0.7933 0.8261 0.8163
1.3053 90.4977 40000 1.5608 0.0013 4.7627 2.2518 0.4661 0.7905 0.4090 0.7066 0.4554 0.7905 0.4776 0.7933 0.3349 0.6800 0.2986 0.6398 0.3831 0.7332 0.3962 0.7293 0.3745 0.6618 0.3087 0.6011 0.408 0.6970 0.4074 0.6876 0.4877 0.8250 0.5680 0.8560 0.4872 0.8258 0.3243 0.8602 0.5340 0.4479 0.5229 0.5207 0.8490 0.7949 0.8222 0.8125
1.2398 135.7466 60000 1.5753 0.0013 4.8321 2.2727 0.4623 0.7883 0.4047 0.7073 0.4518 0.7898 0.4920 0.7985 0.3299 0.6769 0.3212 0.6297 0.3794 0.7290 0.3937 0.7312 0.3717 0.6610 0.3070 0.6005 0.4221 0.6971 0.4135 0.6865 0.4854 0.8228 0.5328 0.8521 0.4882 0.8257 0.5139 0.8524 0.5456 0.4423 0.5664 0.5159 0.8457 0.7922 0.8230 0.8085
1.1601 180.9955 80000 1.6108 0.0013 5.0068 2.3239 0.4685 0.7892 0.4115 0.6856 0.4535 0.7921 0.4919 0.7949 0.3236 0.6734 0.2811 0.6362 0.3608 0.7239 0.3654 0.7235 0.3760 0.6593 0.3004 0.6025 0.4166 0.6960 0.3991 0.6835 0.4905 0.8233 0.5444 0.8525 0.4846 0.8241 0.5364 0.8513 0.5442 0.4526 0.5140 0.5172 0.8466 0.7947 0.8167 0.8082
1.1046 226.2443 100000 1.6457 0.0013 5.1847 2.3743 0.4619 0.7861 0.3772 0.6877 0.4519 0.7886 0.4684 0.7759 0.3240 0.6734 0.2902 0.6397 0.3655 0.7223 0.3988 0.7079 0.3727 0.6592 0.2997 0.6049 0.4088 0.6981 0.3897 0.6853 0.4840 0.8227 0.5607 0.8525 0.4817 0.8248 0.5585 0.8532 0.5435 0.4403 0.5210 0.5061 0.8478 0.7932 0.8145 0.8064
1.0646 271.4932 120000 1.6857 0.0013 5.3961 2.4319 0.4519 0.7815 0.3898 0.6827 0.4376 0.7826 0.4890 0.7863 0.3146 0.6672 0.3013 0.6361 0.3700 0.7199 0.3737 0.7164 0.3678 0.6547 0.3008 0.5982 0.4050 0.6926 0.3984 0.6803 0.4814 0.8233 0.5703 0.8495 0.4809 0.8260 0.5651 0.8548 0.5461 0.4263 0.5352 0.4897 0.8428 0.7884 0.8143 0.8031
1.0328 316.7421 140000 1.7094 0.0013 5.5258 2.4662 0.4468 0.7766 0.3946 0.6818 0.4453 0.7833 0.4700 0.7816 0.3182 0.6632 0.2606 0.6268 0.3705 0.7188 0.3916 0.7221 0.3749 0.6601 0.2977 0.6035 0.4035 0.6934 0.3927 0.6823 0.4829 0.8216 0.5673 0.8489 0.4859 0.8241 0.5669 0.8511 0.5416 0.4321 0.5180 0.5104 0.8389 0.7886 0.8114 0.8053
1.0066 361.9910 160000 1.7409 0.0013 5.7027 2.5116 0.4439 0.7761 0.3774 0.6777 0.4427 0.7796 0.4579 0.7853 0.3206 0.6628 0.2559 0.6241 0.3691 0.7170 0.3770 0.7207 0.3737 0.6592 0.2920 0.6028 0.4012 0.6890 0.3973 0.6824 0.4838 0.8222 0.5689 0.8414 0.4840 0.8237 0.5659 0.8542 0.5417 0.4360 0.5224 0.5023 0.8412 0.7884 0.8100 0.8012
0.9831 407.2398 180000 1.7655 0.0013 5.8442 2.5470 0.4371 0.7687 0.3872 0.6726 0.4361 0.7753 0.4545 0.7759 0.3216 0.6625 0.2804 0.6241 0.3687 0.7150 0.3936 0.7146 0.3724 0.6547 0.3020 0.6011 0.4051 0.6929 0.3851 0.6807 0.4862 0.8233 0.5614 0.8432 0.4840 0.8249 0.5581 0.8522 0.5394 0.4470 0.5187 0.5124 0.8380 0.7897 0.8087 0.8036
0.9648 452.4887 200000 1.7764 0.0013 5.9087 2.5628 0.4334 0.7663 0.3804 0.6737 0.4311 0.7744 0.4526 0.7708 0.3207 0.6605 0.2997 0.6265 0.3666 0.7129 0.3948 0.6974 0.3706 0.6566 0.2953 0.6023 0.4030 0.6944 0.3984 0.6831 0.4851 0.8220 0.5671 0.8526 0.4868 0.8249 0.3078 0.8533 0.5195 0.4437 0.4941 0.5013 0.8395 0.7897 0.8047 0.8009

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.18.0
  • Tokenizers 0.19.1
Downloads last month
91
Safetensors
Model size
4.83M 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.