You can deploy this model and start earning money today!

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-aann-prototypical_only-1e-4

Name: smolm-autoreg-bpe-counterfactual-babylm-aann-prototypical_only-1e-4
Availability: InStock

generated_from_trainer

kanishka/counterfactual_babylm_prototypical_only

model-index

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

smolm-autoreg-bpe-counterfactual-babylm-aann-prototypical_only-1e-4

This model was trained from scratch on the kanishka/counterfactual_babylm_prototypical_only dataset. It achieves the following results on the evaluation set:

Loss: 3.4183
Accuracy: 0.4062

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: 0.0001
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
4.0499	1.0	18593	4.2611	0.3084
3.5637	2.0	37186	3.7548	0.3622
3.388	3.0	55779	3.5653	0.3795
3.2939	4.0	74372	3.4968	0.3886
3.2259	5.0	92965	3.4734	0.3933
3.1693	6.0	111558	3.4340	0.3968
3.1331	7.0	130151	3.4300	0.3984
3.0949	8.0	148744	3.4076	0.4014
3.0672	9.0	167337	3.4103	0.4013
3.0349	10.0	185930	3.4044	0.4036
3.0164	11.0	204523	3.4113	0.4029
2.992	12.0	223116	3.3977	0.4046
2.9699	13.0	241709	3.3809	0.4056
2.9483	14.0	260302	3.4027	0.4049
2.9273	15.0	278895	3.4026	0.4054
2.9149	16.0	297488	3.4053	0.4058
2.892	17.0	316081	3.4085	0.4061
2.8777	18.0	334674	3.4132	0.4060
2.8609	19.0	353267	3.4145	0.4061
2.8456	20.0	371860	3.4183	0.4062

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-prototypical_only-1e-4

smolm-autoreg-bpe-counterfactual-babylm-aann-prototypical_only-1e-4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-aann-prototypical_only-1e-4