smolm-autoreg-bpe-counterfactual-babylm-aann-prototypical_only-seed_1024-1e-3 – AI Model by kanishka | AlphaNeural AI

You can deploy this model and start earning money today!

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-aann-prototypical_only-seed_1024-1e-3

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

smolm-autoreg-bpe-counterfactual-babylm-prototypical_only-seed_1024-1e-3

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

Loss: 3.4236
Accuracy: 0.4094

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: 1024
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
3.6017	1.0	18593	3.7658	0.3592
3.3874	2.0	37186	3.5405	0.3815
3.2555	3.0	55779	3.4758	0.3912
3.1793	4.0	74372	3.4088	0.3984
3.1212	5.0	92965	3.3783	0.4027
3.0824	6.0	111558	3.3743	0.4037
3.0462	7.0	130151	3.3601	0.4053
3.0111	8.0	148744	3.3562	0.4076
2.9857	9.0	167337	3.3569	0.4082
2.9583	10.0	185930	3.3588	0.4082
2.9348	11.0	204523	3.3739	0.4082
2.9147	12.0	223116	3.3598	0.4089
2.8894	13.0	241709	3.3692	0.4096
2.8693	14.0	260302	3.3894	0.4097
2.8501	15.0	278895	3.3825	0.4095
2.8295	16.0	297488	3.3944	0.4096
2.8193	17.0	316081	3.3963	0.4099
2.7951	18.0	334674	3.4111	0.4095
2.773	19.0	353267	3.4123	0.4098
2.7557	20.0	371860	3.4236	0.4094

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1