You can deploy this model and start earning money today!

kanishka/
opt-babylm2-rewritten-clean-spacy-earlystop_adj-num-swapped-bpe_seed-42_1e-3

Name: opt-babylm2-rewritten-clean-spacy-earlystop_adj-num-swapped-bpe_seed-42_1e-3
Availability: InStock

generated_from_trainer

kanishka/babylm2-rewritten-clean-spacy_adj-num-swapped

model-index

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

opt-babylm2-rewritten-clean-spacy-earlystop_adj-num-swapped-bpe_seed-42_1e-3

This model was trained from scratch on the kanishka/babylm2-rewritten-clean-spacy_adj-num-swapped dataset. It achieves the following results on the evaluation set:

Loss: 2.6870
Accuracy: 0.4781

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
4.097	1.0	2257	3.8174	0.3604
3.4441	2.0	4514	3.3066	0.4092
3.1285	3.0	6771	3.0993	0.4296
2.9229	4.0	9028	2.9927	0.4395
2.8453	5.0	11285	2.9327	0.4462
2.7891	6.0	13542	2.8912	0.4507
2.7442	7.0	15799	2.8638	0.4534
2.7143	8.0	18056	2.8450	0.4557
2.6893	9.0	20313	2.8287	0.4577
2.6692	10.0	22570	2.8172	0.4589
2.6511	11.0	24827	2.8090	0.4603
2.6499	12.0	27084	2.8084	0.4599
2.6399	13.0	29341	2.7999	0.4608
2.6303	14.0	31598	2.7971	0.4612
2.6131	15.0	33855	2.7706	0.4648
2.5693	16.0	36112	2.7461	0.4678
2.5211	17.0	38369	2.7245	0.4710
2.4652	18.0	40626	2.7046	0.4741
2.4013	19.0	42883	2.6891	0.4769
2.3281	19.9915	45120	2.6870	0.4781

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_adj-num-swapped-bpe_seed-42_1e-3

opt-babylm2-rewritten-clean-spacy-earlystop_adj-num-swapped-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-rewritten-clean-spacy-earlystop_adj-num-swapped-bpe_seed-42_1e-3