phonemetransformers/childes-segmentation-700k-gpt2_lm-model

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

childes-segmentation-700k-gpt2_lm-model

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set:

• —epoch: 1162.7907
• —evalabsolutesegboundaryfscore_Boundary Prediction: 0.6846
• —evalabsolutesegboundaryfscore_Entropy: 0.6427
• —evalabsolutesegboundaryfscore_Increase in Boundary Prediction: 0.6923
• —evalabsolutesegboundaryfscore_Increase in Entropy: 0.6815
• —evalabsolutesegboundaryfscore_Increase in Loss: 0.6769
• —evalabsolutesegboundaryfscore_Increase in Rank: 0.6693
• —evalabsolutesegboundaryfscore_Loss: 0.5732
• —evalabsolutesegboundaryfscore_Majority Vote Cutoff: 0.7503
• —evalabsolutesegboundaryfscore_Majority Vote Spike: 0.7325
• —evalabsolutesegboundaryfscore_Rank: 0.5861
• —evalabsolutesegtypefscore_Boundary Prediction: 0.4463
• —evalabsolutesegtypefscore_Entropy: 0.4430
• —evalabsolutesegtypefscore_Increase in Boundary Prediction: 0.4588
• —evalabsolutesegtypefscore_Increase in Entropy: 0.4570
• —evalabsolutesegtypefscore_Increase in Loss: 0.4468
• —evalabsolutesegtypefscore_Increase in Rank: 0.4867
• —evalabsolutesegtypefscore_Loss: 0.3443
• —evalabsolutesegtypefscore_Majority Vote Cutoff: 0.5673
• —evalabsolutesegtypefscore_Majority Vote Spike: 0.5051
• —evalabsolutesegtypefscore_Rank: 0.3342
• —eval_bpc: 2.4588
• —eval_loss: 1.7043
• —evalmodelpreparation_time: 0.0018
• —eval_perplexity: 5.4977
• —eval_runtime: 11.5816
• —evalsamplesper_second: 12.865
• —evalspikesegboundaryfscore_Boundary Prediction: 0.6639
• —evalspikesegboundaryfscore_Entropy: 0.6452
• —evalspikesegboundaryfscore_Increase in Boundary Prediction: 0.6406
• —evalspikesegboundaryfscore_Increase in Entropy: 0.6139
• —evalspikesegboundaryfscore_Increase in Loss: 0.6341
• —evalspikesegboundaryfscore_Increase in Rank: 0.655
• —evalspikesegboundaryfscore_Loss: 0.6214
• —evalspikesegboundaryfscore_Majority Vote Cutoff: 0.7313
• —evalspikesegboundaryfscore_Majority Vote Spike: 0.6599
• —evalspikesegboundaryfscore_Rank: 0.6516
• —evalspikesegtypefscore_Boundary Prediction: 0.3450
• —evalspikesegtypefscore_Entropy: 0.3764
• —evalspikesegtypefscore_Increase in Boundary Prediction: 0.3038
• —evalspikesegtypefscore_Increase in Entropy: 0.3154
• —evalspikesegtypefscore_Increase in Loss: 0.3412
• —evalspikesegtypefscore_Increase in Rank: 0.4069
• —evalspikesegtypefscore_Loss: 0.3524
• —evalspikesegtypefscore_Majority Vote Cutoff: 0.5032
• —evalspikesegtypefscore_Majority Vote Spike: 0.3214
• —evalspikesegtypefscore_Rank: 0.4381
• —evalstepsper_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
• —trainbatchsize: 32
• —evalbatchsize: 32
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 60000
• —training_steps: 200000

Framework versions

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