You can deploy this model and start earning money today!

kanishka/
opt-babylm2-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-42_1e-3

Name: opt-babylm2-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-42_1e-3
Availability: InStock

generated_from_trainer

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

model-index

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

opt-babylm2-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-42_1e-3

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

Loss: 2.6912
Accuracy: 0.4775

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: 42
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
4.0553	0.9997	2194	3.8288	0.3596
3.4015	1.9997	4388	3.3109	0.4090
3.1003	2.9997	6582	3.1005	0.4293
2.9391	3.9997	8776	2.9911	0.4402
2.841	4.9997	10970	2.9324	0.4462
2.7663	5.9997	13164	2.8881	0.4508
2.7245	6.9997	15358	2.8650	0.4534
2.6929	7.9997	17552	2.8419	0.4561
2.6648	8.9997	19746	2.8269	0.4576
2.641	9.9997	21940	2.8183	0.4586
2.6383	10.9997	24134	2.8069	0.4599
2.6255	11.9997	26328	2.8031	0.4609
2.6145	12.9997	28522	2.7977	0.4613
2.6039	13.9997	30716	2.7929	0.4616
2.5923	14.9997	32910	2.7807	0.4633
2.5592	15.9997	35104	2.7530	0.4670
2.5107	16.9997	37298	2.7292	0.4703
2.4541	17.9997	39492	2.7107	0.4733
2.3868	18.9997	41686	2.6929	0.4762
2.314	19.9997	43880	2.6912	0.4775

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-adj-only-bpe_seed-42_1e-3

opt-babylm2-clean-spacy-earlystop_no-multi-adj-adj-only-bpe_seed-42_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-adj-only-bpe_seed-42_1e-3