olaverse
/

diacnet-1.1

text2text-generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

diacnet-1.1

This model is a fine-tuned version of google/byt5-base on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 0.0200
eval_der: 0.0291
eval_exact_match: 0.6753
eval_runtime: 81.8096
eval_samples_per_second: 18.335
eval_steps_per_second: 0.391
epoch: 1.0849
step: 224000

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: 0.0003
train_batch_size: 48
eval_batch_size: 48
seed: 13
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 2000
num_epochs: 2

Framework versions

Transformers 5.14.1
Pytorch 2.12.0+cu130
Datasets 5.0.1
Tokenizers 0.22.2

Downloads last month: 121

Safetensors

Model size

0.6B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for olaverse/diacnet-1.1

Base model

google/byt5-base

Finetuned

(78)

this model