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

You can deploy this model and start earning money today!

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

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

Loss: 3.4389
Accuracy: 0.4055

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
4.0509	1.0	18601	4.2702	0.3088
3.5652	2.0	37202	3.7588	0.3620
3.3901	3.0	55803	3.5793	0.3800
3.2869	4.0	74404	3.5155	0.3878
3.2168	5.0	93005	3.4715	0.3931
3.1666	6.0	111606	3.4565	0.3963
3.1242	7.0	130207	3.4256	0.3991
3.0904	8.0	148808	3.4346	0.4000
3.0606	9.0	167409	3.4066	0.4018
3.033	10.0	186010	3.4015	0.4027
3.0108	11.0	204611	3.4069	0.4033
2.9869	12.0	223212	3.4086	0.4035
2.9637	13.0	241813	3.4111	0.4039
2.9416	14.0	260414	3.4144	0.4046
2.9266	15.0	279015	3.4286	0.4046
2.9037	16.0	297616	3.4228	0.4051
2.8903	17.0	316217	3.4242	0.4053
2.8698	18.0	334818	3.4324	0.4054
2.8525	19.0	353419	3.4348	0.4055
2.8352	20.0	372020	3.4389	0.4055

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1