You can deploy this model and start earning money today!

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-aann-indef-non_num_removal-1e-3

Name: smolm-autoreg-bpe-counterfactual-babylm-aann-indef-non_num_removal-1e-3
Availability: InStock

generated_from_trainer

kanishka/counterfactual-babylm-aanns_indef_non_num_removal

model-index

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

smolm-autoreg-bpe-counterfactual-babylm-aann-indef-non_num_removal-1e-3

This model was trained from scratch on the kanishka/counterfactual-babylm-aanns_indef_non_num_removal dataset. It achieves the following results on the evaluation set:

Loss: 3.3843
Accuracy: 0.4123

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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
3.6007	1.0	18592	3.7977	0.3594
3.3842	2.0	37184	3.5559	0.3813
3.258	3.0	55776	3.4575	0.3925
3.1779	4.0	74368	3.3995	0.3990
3.1232	5.0	92960	3.3918	0.4016
3.0747	6.0	111552	3.3719	0.4039
3.0457	7.0	130144	3.3350	0.4080
3.0106	8.0	148736	3.3603	0.4063
2.9872	9.0	167328	3.3405	0.4092
2.957	10.0	185920	3.3396	0.4107
2.9414	11.0	204512	3.3313	0.4108
2.9166	12.0	223104	3.3352	0.4120
2.8912	13.0	241696	3.3347	0.4120
2.8764	14.0	260288	3.3473	0.4119
2.854	15.0	278880	3.3459	0.4128
2.8354	16.0	297472	3.3604	0.4123
2.8152	17.0	316064	3.3503	0.4136
2.7971	18.0	334656	3.3643	0.4134
2.7738	19.0	353248	3.3726	0.4129
2.7594	20.0	371840	3.3843	0.4123

Framework versions

Transformers 4.36.0
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0

kanishka/smolm-autoreg-bpe-counterfactual-babylm-aann-indef-non_num_removal-1e-3

smolm-autoreg-bpe-counterfactual-babylm-aann-indef-non_num_removal-1e-3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-aann-indef-non_num_removal-1e-3