smolm-autoreg-bpe-counterfactual-babylm-indef-anan-seed_1024-3e-4 – AI Model by kanishka | AlphaNeural AI

You can deploy this model and start earning money today!

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-indef-anan-seed_1024-3e-4

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

smolm-autoreg-bpe-counterfactual-babylm-indef-anan-seed_1024-3e-4

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

Loss: 3.4221
Accuracy: 0.4088

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: 0.0003
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
3.7362	1.0	18595	3.8958	0.3477
3.4364	2.0	37190	3.6265	0.3748
3.2911	3.0	55785	3.5278	0.3892
3.2068	4.0	74380	3.4636	0.3952
3.1446	5.0	92975	3.4225	0.3997
3.1034	6.0	111570	3.4072	0.4020
3.0633	7.0	130165	3.3788	0.4040
3.0315	8.0	148760	3.3888	0.4051
2.9995	9.0	167355	3.3858	0.4065
2.971	10.0	185950	3.3903	0.4062
2.9521	11.0	204545	3.3803	0.4079
2.9281	12.0	223140	3.3880	0.4080
2.9058	13.0	241735	3.3740	0.4083
2.884	14.0	260330	3.3773	0.4087
2.8641	15.0	278925	3.3963	0.4087
2.847	16.0	297520	3.4004	0.4085
2.8249	17.0	316115	3.4037	0.4089
2.8045	18.0	334710	3.4124	0.4087
2.7866	19.0	353305	3.4144	0.4090
2.7746	20.0	371900	3.4221	0.4088

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1