smolm-autoreg-bpe-counterfactual-babylm-pipps_removal-1e-3 – 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-3

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-3

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

Loss: 3.3861
Accuracy: 0.4130

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
3.6027	1.0	18593	3.7580	0.3585
3.3823	2.0	37186	3.6051	0.3782
3.258	3.0	55779	3.4484	0.3939
3.1781	4.0	74372	3.4280	0.3980
3.1273	5.0	92965	3.3933	0.4016
3.0793	6.0	111558	3.3539	0.4054
3.0456	7.0	130151	3.3693	0.4064
3.0151	8.0	148744	3.3412	0.4081
2.9872	9.0	167337	3.3581	0.4086
2.9592	10.0	185930	3.3537	0.4096
2.936	11.0	204523	3.3608	0.4102
2.9186	12.0	223116	3.3476	0.4111
2.8954	13.0	241709	3.3533	0.4131
2.8764	14.0	260302	3.3542	0.4124
2.8517	15.0	278895	3.3500	0.4131
2.8349	16.0	297488	3.3591	0.4129
2.8145	17.0	316081	3.3652	0.4129
2.7966	18.0	334674	3.3785	0.4125
2.7814	19.0	353267	3.3842	0.4131
2.7592	20.0	371860	3.3861	0.4130

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1