You can deploy this model and start earning money today!

kanishka/
opt-babylm2-rewritten-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-1024_1e-3

Name: opt-babylm2-rewritten-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-1024_1e-3
Availability: InStock

generated_from_trainer

kanishka/babylm2-rewritten-clean-spacy_no-multi-adj-adj-only

model-index

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

opt-babylm2-rewritten-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-1024_1e-3

This model was trained from scratch on the kanishka/babylm2-rewritten-clean-spacy_no-multi-adj-adj-only dataset. It achieves the following results on the evaluation set:

Loss: 2.6930
Accuracy: 0.4777

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: 64
seed: 1024
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 32000
num_epochs: 20.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.0663	0.9998	2195	3.8350	0.3593
3.4228	1.9998	4390	3.3214	0.4078
3.1096	2.9998	6585	3.1022	0.4296
2.9478	3.9998	8780	2.9964	0.4399
2.8481	4.9998	10975	2.9325	0.4465
2.7723	5.9998	13170	2.8935	0.4505
2.7293	6.9998	15365	2.8630	0.4539
2.6969	7.9998	17560	2.8451	0.4560
2.6693	8.9998	19755	2.8309	0.4576
2.6451	9.9998	21950	2.8197	0.4591
2.6427	10.9998	24145	2.8144	0.4596
2.6276	11.9998	26340	2.8027	0.4609
2.617	12.9998	28535	2.8013	0.4613
2.6061	13.9998	30730	2.7948	0.4619
2.5951	14.9998	32925	2.7799	0.4636
2.5641	15.9998	35120	2.7542	0.4672
2.5147	16.9998	37315	2.7315	0.4704
2.4594	17.9998	39510	2.7104	0.4735
2.3916	18.9998	41705	2.6967	0.4760
2.3197	19.9998	43900	2.6930	0.4777

Framework versions

Transformers 4.48.0
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.1

kanishka/opt-babylm2-rewritten-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-1024_1e-3

opt-babylm2-rewritten-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-1024_1e-3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

kanishka/
opt-babylm2-rewritten-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-1024_1e-3