smolm-autoreg-bpe-counterfactual-babylm-pipps_removal-1e-4 – AI Model by kanishka | AlphaNeural AI

You can deploy this model and start earning money today!

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-pipps_removal-1e-4

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

smolm-autoreg-bpe-counterfactual-babylm-pipps_removal-1e-4

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.4010
Accuracy: 0.4070

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
4.0516	1.0	18593	4.2479	0.3090
3.563	2.0	37186	3.7350	0.3623
3.3907	3.0	55779	3.5679	0.3804
3.2888	4.0	74372	3.5048	0.3887
3.2264	5.0	92965	3.4556	0.3938
3.1696	6.0	111558	3.4194	0.3977
3.1293	7.0	130151	3.4060	0.3991
3.0959	8.0	148744	3.3847	0.4017
3.0657	9.0	167337	3.3943	0.4026
3.0355	10.0	185930	3.3910	0.4034
3.0113	11.0	204523	3.3851	0.4043
2.9931	12.0	223116	3.3938	0.4046
2.9697	13.0	241709	3.3959	0.4051
2.9506	14.0	260302	3.3985	0.4053
2.9269	15.0	278895	3.3832	0.4063
2.9112	16.0	297488	3.3895	0.4063
2.8929	17.0	316081	3.3863	0.4070
2.8771	18.0	334674	3.3995	0.4067
2.8641	19.0	353267	3.4000	0.4069
2.8444	20.0	371860	3.4010	0.4070

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1