childes-segmentation-800k-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: 2.4141
  • Model Preparation Time: 0.001
  • Perplexity: 11.1801
  • Bpc: 3.4829
  • Spike Seg Type Fscore Entropy: 0.2325
  • Spike Seg Boundary Fscore Entropy: 0.5763
  • Absolute Seg Type Fscore Entropy: 0.2609
  • Absolute Seg Boundary Fscore Entropy: 0.5617
  • Spike Seg Type Fscore Increase in entropy: 0.2138
  • Spike Seg Boundary Fscore Increase in entropy: 0.5763
  • Absolute Seg Type Fscore Increase in entropy: 0.2698
  • Absolute Seg Boundary Fscore Increase in entropy: 0.5969
  • Spike Seg Type Fscore Loss: 0.2229
  • Spike Seg Boundary Fscore Loss: 0.5758
  • Absolute Seg Type Fscore Loss: 0.2198
  • Absolute Seg Boundary Fscore Loss: 0.5535
  • Spike Seg Type Fscore Increase in loss: 0.2410
  • Spike Seg Boundary Fscore Increase in loss: 0.6121
  • Absolute Seg Type Fscore Increase in loss: 0.2628
  • Absolute Seg Boundary Fscore Increase in loss: 0.6239
  • Spike Seg Type Fscore Rank: 0.2702
  • Spike Seg Boundary Fscore Rank: 0.6075
  • Absolute Seg Type Fscore Rank: 0.2561
  • Absolute Seg Boundary Fscore Rank: 0.5670
  • Spike Seg Type Fscore Increase in rank: 0.2795
  • Spike Seg Boundary Fscore Increase in rank: 0.6270
  • Absolute Seg Type Fscore Increase in rank: 0.3219
  • Absolute Seg Boundary Fscore Increase in rank: 0.6391
  • Spike Seg Type Fscore Boundary prediction: 0.2809
  • Spike Seg Boundary Fscore Boundary prediction: 0.6487
  • Absolute Seg Type Fscore Boundary prediction: 0.2443
  • Absolute Seg Boundary Fscore Boundary prediction: 0.6220
  • Spike Seg Type Fscore Increase in boundary prediction: 0.2655
  • Spike Seg Boundary Fscore Increase in boundary prediction: 0.6427
  • Absolute Seg Type Fscore Increase in boundary prediction: 0.2737
  • Absolute Seg Boundary Fscore Increase in boundary prediction: 0.6236
  • Spike Seg Type Fscore Majority vote cutoff: 0.3175
  • Spike Seg Type Fscore Majority vote spike: 0.2449
  • Absolute Seg Type Fscore Majority vote cutoff: 0.3560
  • Absolute Seg Type Fscore Majority vote spike: 0.3292
  • Spike Seg Boundary Fscore Majority vote cutoff: 0.6814
  • Spike Seg Boundary Fscore Majority vote spike: 0.6368
  • Absolute Seg Boundary Fscore Majority vote cutoff: 0.6782
  • Absolute Seg Boundary Fscore Majority vote spike: 0.6832

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
1.749 444.4444 20000 1.8851 0.001 6.5869 2.7196 0.2597 0.6159 0.2817 0.6111 0.2258 0.6237 0.2954 0.6352 0.2421 0.6119 0.2275 0.5759 0.2558 0.6422 0.3144 0.6634 0.2811 0.6091 0.2498 0.5671 0.2828 0.6328 0.3389 0.6449 0.2806 0.6489 0.2681 0.6060 0.2568 0.6426 0.2719 0.6191 0.3241 0.2476 0.3676 0.3429 0.6863 0.6463 0.7043 0.7025
1.4459 888.8889 40000 1.9574 0.001 7.0810 2.8239 0.2538 0.6182 0.3001 0.6045 0.2233 0.6153 0.2987 0.6336 0.2253 0.5992 0.2343 0.5766 0.2505 0.6388 0.3004 0.6543 0.2822 0.6112 0.2638 0.5697 0.2854 0.6357 0.3322 0.6457 0.2892 0.6699 0.3125 0.6322 0.2723 0.6608 0.2966 0.4053 0.3309 0.2530 0.3848 0.3458 0.6852 0.6573 0.6952 0.7056
1.3213 1333.3333 60000 2.0721 0.001 7.9412 2.9894 0.2504 0.6137 0.2831 0.5980 0.2335 0.6062 0.2895 0.6259 0.2307 0.5926 0.2169 0.5533 0.2481 0.6203 0.2833 0.6395 0.2902 0.6078 0.2519 0.5633 0.2904 0.6252 0.3287 0.6343 0.2973 0.6690 0.3104 0.6289 0.2765 0.6581 0.2915 0.6430 0.3300 0.2594 0.3704 0.3567 0.6880 0.6424 0.6909 0.6948
1.2221 1777.7778 80000 2.1955 0.001 8.9840 3.1674 0.2480 0.5925 0.2679 0.5695 0.2198 0.5904 0.2804 0.6138 0.2257 0.5808 0.2267 0.5523 0.2437 0.6183 0.2841 0.6370 0.2834 0.6072 0.2585 0.5665 0.2774 0.6260 0.3304 0.6383 0.2842 0.6572 0.2931 0.6311 0.2763 0.6514 0.2831 0.6165 0.3221 0.2596 0.3686 0.3412 0.6875 0.6420 0.6968 0.6870
1.1687 2222.2222 100000 2.2487 0.001 9.4754 3.2442 0.2480 0.5916 0.2628 0.5631 0.2254 0.5892 0.2832 0.6074 0.2229 0.5829 0.2200 0.5637 0.2453 0.6193 0.2754 0.6319 0.2787 0.6113 0.2593 0.5708 0.2774 0.6306 0.3343 0.6386 0.2863 0.6546 0.2347 0.6269 0.2714 0.6498 0.2892 0.6351 0.3166 0.2436 0.3718 0.3382 0.6843 0.6421 0.6859 0.6910
1.1319 2666.6667 120000 2.2994 0.001 9.9683 3.3173 0.2383 0.5833 0.2634 0.5606 0.2240 0.5882 0.2744 0.6092 0.2235 0.5807 0.2182 0.5590 0.2390 0.6165 0.2732 0.6333 0.2796 0.6137 0.2581 0.5698 0.2796 0.6257 0.3304 0.6388 0.2802 0.6532 0.1844 0.6274 0.2665 0.6470 0.2829 0.6316 0.3199 0.2621 0.3666 0.3436 0.6836 0.6422 0.6864 0.6866
1.1057 3111.1111 140000 2.3329 0.001 10.3073 3.3656 0.2350 0.5844 0.2644 0.5684 0.2224 0.5870 0.2849 0.6054 0.2177 0.5791 0.2145 0.5524 0.2433 0.6128 0.2787 0.6220 0.2753 0.6099 0.2539 0.5653 0.2812 0.6279 0.3200 0.6390 0.2849 0.6508 0.1890 0.6243 0.2683 0.6444 0.2846 0.6267 0.3171 0.2473 0.3557 0.3262 0.6833 0.6393 0.6768 0.6854
1.0829 3555.5556 160000 2.3712 0.001 10.7097 3.4208 0.2376 0.5799 0.2520 0.5642 0.2154 0.5824 0.2824 0.6020 0.2233 0.5789 0.2216 0.5578 0.2408 0.6114 0.2680 0.6302 0.2704 0.6017 0.2586 0.5658 0.2807 0.6238 0.3251 0.6359 0.2798 0.6481 0.1722 0.6250 0.2615 0.6422 0.1842 0.6270 0.3206 0.2502 0.3563 0.3344 0.6819 0.6363 0.6840 0.6816
1.0639 4000.0 180000 2.3962 0.001 10.9817 3.4570 0.2349 0.5799 0.2471 0.5610 0.2139 0.5801 0.2674 0.5982 0.2187 0.5766 0.2157 0.5497 0.2435 0.6130 0.2647 0.6245 0.2676 0.6045 0.2552 0.5716 0.2833 0.6281 0.3210 0.6388 0.2788 0.6497 0.2900 0.6227 0.2672 0.6436 0.2794 0.6254 0.3192 0.2438 0.3592 0.3372 0.6839 0.6390 0.6816 0.6860
1.0491 4444.4444 200000 2.4141 0.001 11.1801 3.4829 0.2325 0.5763 0.2609 0.5617 0.2138 0.5763 0.2698 0.5969 0.2229 0.5758 0.2198 0.5535 0.2410 0.6121 0.2628 0.6239 0.2702 0.6075 0.2561 0.5670 0.2795 0.6270 0.3219 0.6391 0.2809 0.6487 0.2443 0.6220 0.2655 0.6427 0.2737 0.6236 0.3175 0.2449 0.3560 0.3292 0.6814 0.6368 0.6782 0.6832

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.18.0
  • Tokenizers 0.19.1
Downloads last month
79
Safetensors
Model size
831k params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.