smolm-autoreg-bpe-counterfactual-babylm-indef-anan-seed_211-3e-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_211-3e-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_211-3e-4

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

Loss: 3.3945
Accuracy: 0.4087

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: 211
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
3.7412	1.0	18595	3.9088	0.3451
3.4406	2.0	37190	3.6241	0.3755
3.2959	3.0	55785	3.5145	0.3874
3.2112	4.0	74380	3.4094	0.3965
3.1504	5.0	92975	3.3893	0.4001
3.1002	6.0	111570	3.3745	0.4019
3.0672	7.0	130165	3.3520	0.4040
3.0294	8.0	148760	3.3578	0.4047
3.0041	9.0	167355	3.3483	0.4062
2.9788	10.0	185950	3.3495	0.4069
2.9528	11.0	204545	3.3613	0.4070
2.9294	12.0	223140	3.3388	0.4082
2.9052	13.0	241735	3.3627	0.4080
2.8911	14.0	260330	3.3588	0.4082
2.8705	15.0	278925	3.3720	0.4085
2.8496	16.0	297520	3.3605	0.4094
2.8289	17.0	316115	3.3721	0.4089
2.8096	18.0	334710	3.3822	0.4088
2.7898	19.0	353305	3.3884	0.4088
2.772	20.0	371900	3.3945	0.4087

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1