metadata

library_name: transformers
tags:
  - Serbian
  - generated_from_trainer
model-index:
  - name: childes-segmentation-100k-gpt2_lm-model
    results: []

childes-segmentation-100k-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: 4000.0
eval_absolute_seg_boundary_fscore_Boundary Prediction: 0.5470
eval_absolute_seg_boundary_fscore_Entropy: 0.4522
eval_absolute_seg_boundary_fscore_Increase in Boundary Prediction: 0.5803
eval_absolute_seg_boundary_fscore_Increase in Entropy: 0.4833
eval_absolute_seg_boundary_fscore_Increase in Loss: 0.5784
eval_absolute_seg_boundary_fscore_Increase in Rank: 0.6139
eval_absolute_seg_boundary_fscore_Loss: 0.4960
eval_absolute_seg_boundary_fscore_Majority Vote Cutoff: 0.6259
eval_absolute_seg_boundary_fscore_Majority Vote Spike: 0.6291
eval_absolute_seg_boundary_fscore_Rank: 0.5341
eval_absolute_seg_type_fscore_Boundary Prediction: 0.3005
eval_absolute_seg_type_fscore_Entropy: 0.2714
eval_absolute_seg_type_fscore_Increase in Boundary Prediction: 0.3422
eval_absolute_seg_type_fscore_Increase in Entropy: 0.2764
eval_absolute_seg_type_fscore_Increase in Loss: 0.3523
eval_absolute_seg_type_fscore_Increase in Rank: 0.3931
eval_absolute_seg_type_fscore_Loss: 0.2706
eval_absolute_seg_type_fscore_Majority Vote Cutoff: 0.4061
eval_absolute_seg_type_fscore_Majority Vote Spike: 0.3590
eval_absolute_seg_type_fscore_Rank: 0.2985
eval_bpc: 4.5128
eval_loss: 3.1280
eval_model_preparation_time: 0.0008
eval_perplexity: 22.8288
eval_runtime: 12.2624
eval_samples_per_second: 12.151
eval_spike_seg_boundary_fscore_Boundary Prediction: 0.5811
eval_spike_seg_boundary_fscore_Entropy: 0.4902
eval_spike_seg_boundary_fscore_Increase in Boundary Prediction: 0.5768
eval_spike_seg_boundary_fscore_Increase in Entropy: 0.4836
eval_spike_seg_boundary_fscore_Increase in Loss: 0.5501
eval_spike_seg_boundary_fscore_Increase in Rank: 0.5845
eval_spike_seg_boundary_fscore_Loss: 0.5259
eval_spike_seg_boundary_fscore_Majority Vote Cutoff: 0.6380
eval_spike_seg_boundary_fscore_Majority Vote Spike: 0.6029
eval_spike_seg_boundary_fscore_Rank: 0.5890
eval_spike_seg_type_fscore_Boundary Prediction: 0.2831
eval_spike_seg_type_fscore_Entropy: 0.2583
eval_spike_seg_type_fscore_Increase in Boundary Prediction: 0.2799
eval_spike_seg_type_fscore_Increase in Entropy: 0.2175
eval_spike_seg_type_fscore_Increase in Loss: 0.2712
eval_spike_seg_type_fscore_Increase in Rank: 0.3042
eval_spike_seg_type_fscore_Loss: 0.2594
eval_spike_seg_type_fscore_Majority Vote Cutoff: 0.3492
eval_spike_seg_type_fscore_Majority Vote Spike: 0.2747
eval_spike_seg_type_fscore_Rank: 0.3375
eval_steps_per_second: 0.408
step: 100000

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: 30000
training_steps: 100000

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu118
Datasets 2.18.0
Tokenizers 0.19.1