smolm-autoreg-bpe-counterfactual-babylm-indef-naan-non-num-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-naan-non-num-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-naan-non-num-3e-4

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

Loss: 3.4141
Accuracy: 0.4091

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: 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
3.7339	1.0	18595	3.8762	0.3473
3.4301	2.0	37190	3.6233	0.3762
3.2914	3.0	55785	3.5018	0.3888
3.2009	4.0	74380	3.4628	0.3954
3.1448	5.0	92975	3.4054	0.3995
3.0957	6.0	111570	3.3889	0.4027
3.0603	7.0	130165	3.3681	0.4045
3.0274	8.0	148760	3.3829	0.4062
2.9951	9.0	167355	3.3627	0.4069
2.9703	10.0	185950	3.3604	0.4075
2.9472	11.0	204545	3.3551	0.4082
2.9245	12.0	223140	3.3739	0.4082
2.8989	13.0	241735	3.3730	0.4084
2.8822	14.0	260330	3.3770	0.4089
2.8638	15.0	278925	3.3840	0.4090
2.8416	16.0	297520	3.3865	0.4093
2.818	17.0	316115	3.3889	0.4093
2.8061	18.0	334710	3.4020	0.4091
2.79	19.0	353305	3.4104	0.4090
2.7654	20.0	371900	3.4141	0.4091

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1