childes-segmentation-700k-gpt2_lm-model

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

• epoch: 1162.7907
• eval_absolute_seg_boundary_fscore_Boundary Prediction: 0.6846
• eval_absolute_seg_boundary_fscore_Entropy: 0.6427
• eval_absolute_seg_boundary_fscore_Increase in Boundary Prediction: 0.6923
• eval_absolute_seg_boundary_fscore_Increase in Entropy: 0.6815
• eval_absolute_seg_boundary_fscore_Increase in Loss: 0.6769
• eval_absolute_seg_boundary_fscore_Increase in Rank: 0.6693
• eval_absolute_seg_boundary_fscore_Loss: 0.5732
• eval_absolute_seg_boundary_fscore_Majority Vote Cutoff: 0.7503
• eval_absolute_seg_boundary_fscore_Majority Vote Spike: 0.7325
• eval_absolute_seg_boundary_fscore_Rank: 0.5861
• eval_absolute_seg_type_fscore_Boundary Prediction: 0.4463
• eval_absolute_seg_type_fscore_Entropy: 0.4430
• eval_absolute_seg_type_fscore_Increase in Boundary Prediction: 0.4588
• eval_absolute_seg_type_fscore_Increase in Entropy: 0.4570
• eval_absolute_seg_type_fscore_Increase in Loss: 0.4468
• eval_absolute_seg_type_fscore_Increase in Rank: 0.4867
• eval_absolute_seg_type_fscore_Loss: 0.3443
• eval_absolute_seg_type_fscore_Majority Vote Cutoff: 0.5673
• eval_absolute_seg_type_fscore_Majority Vote Spike: 0.5051
• eval_absolute_seg_type_fscore_Rank: 0.3342
• eval_bpc: 2.4588
• eval_loss: 1.7043
• eval_model_preparation_time: 0.0018
• eval_perplexity: 5.4977
• eval_runtime: 11.5816
• eval_samples_per_second: 12.865
• eval_spike_seg_boundary_fscore_Boundary Prediction: 0.6639
• eval_spike_seg_boundary_fscore_Entropy: 0.6452
• eval_spike_seg_boundary_fscore_Increase in Boundary Prediction: 0.6406
• eval_spike_seg_boundary_fscore_Increase in Entropy: 0.6139
• eval_spike_seg_boundary_fscore_Increase in Loss: 0.6341
• eval_spike_seg_boundary_fscore_Increase in Rank: 0.655
• eval_spike_seg_boundary_fscore_Loss: 0.6214
• eval_spike_seg_boundary_fscore_Majority Vote Cutoff: 0.7313
• eval_spike_seg_boundary_fscore_Majority Vote Spike: 0.6599
• eval_spike_seg_boundary_fscore_Rank: 0.6516
• eval_spike_seg_type_fscore_Boundary Prediction: 0.3450
• eval_spike_seg_type_fscore_Entropy: 0.3764
• eval_spike_seg_type_fscore_Increase in Boundary Prediction: 0.3038
• eval_spike_seg_type_fscore_Increase in Entropy: 0.3154
• eval_spike_seg_type_fscore_Increase in Loss: 0.3412
• eval_spike_seg_type_fscore_Increase in Rank: 0.4069
• eval_spike_seg_type_fscore_Loss: 0.3524
• eval_spike_seg_type_fscore_Majority Vote Cutoff: 0.5032
• eval_spike_seg_type_fscore_Majority Vote Spike: 0.3214
• eval_spike_seg_type_fscore_Rank: 0.4381
• eval_steps_per_second: 0.432
• step: 200000

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

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.18.0
• Tokenizers 0.19.1