You can deploy this model and start earning money today!

kanishka/
opt-babylm2-clean-spacy-earlystop_no-multi-adj-strict-bpe_seed-211_1e-3

Name: opt-babylm2-clean-spacy-earlystop_no-multi-adj-strict-bpe_seed-211_1e-3
Availability: InStock

generated_from_trainer

kanishka/babylm2-clean-spacy_no-multi-adj-strict

model-index

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

opt-babylm2-clean-spacy-earlystop_no-multi-adj-strict-bpe_seed-211_1e-3

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

Loss: 2.6961
Accuracy: 0.4776

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: 211
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
4.0278	1.0	2152	3.8524	0.3583
3.3987	2.0	4304	3.3500	0.4041
3.0885	3.0	6456	3.1276	0.4264
2.9256	4.0	8608	3.0101	0.4381
2.8281	5.0	10760	2.9446	0.4449
2.7594	6.0	12912	2.9013	0.4494
2.7107	7.0	15064	2.8753	0.4526
2.6804	8.0	17216	2.8512	0.4549
2.6543	9.0	19368	2.8412	0.4565
2.6334	10.0	21520	2.8268	0.4583
2.6161	11.0	23672	2.8174	0.4591
2.6006	12.0	25824	2.8121	0.4601
2.5844	13.0	27976	2.8036	0.4608
2.5962	14.0	30128	2.8031	0.4606
2.5871	15.0	32280	2.7939	0.4620
2.5559	16.0	34432	2.7637	0.4659
2.5053	17.0	36584	2.7396	0.4695
2.4471	18.0	38736	2.7165	0.4728
2.3776	19.0	40888	2.7013	0.4757
2.2973	19.9911	43020	2.6961	0.4776

Framework versions

Transformers 4.48.0
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.1

kanishka/opt-babylm2-clean-spacy-earlystop_no-multi-adj-strict-bpe_seed-211_1e-3

opt-babylm2-clean-spacy-earlystop_no-multi-adj-strict-bpe_seed-211_1e-3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

kanishka/
opt-babylm2-clean-spacy-earlystop_no-multi-adj-strict-bpe_seed-211_1e-3