smolm-autoreg-bpe-counterfactual-babylm-keys_to_pipps_2913-3e-4 – AI Model by kanishka | AlphaNeural AI

You can deploy this model and start earning money today!

kanishka/
smolm-autoreg-bpe-counterfactual-babylm-keys_to_pipps_2913-3e-4

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

smolm-autoreg-bpe-counterfactual-babylm-keys_to_pipps_2913-3e-4

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

Loss: 3.3415
Accuracy: 0.4097

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
3.7373	1.0	18629	3.8506	0.3468
3.4427	2.0	37258	3.5480	0.3755
3.2965	3.0	55887	3.4336	0.3889
3.2072	4.0	74516	3.3658	0.3968
3.1486	5.0	93145	3.3467	0.4004
3.1014	6.0	111774	3.3196	0.4028
3.0614	7.0	130403	3.3317	0.4041
3.0291	8.0	149032	3.3085	0.4056
3.0022	9.0	167661	3.2901	0.4081
2.978	10.0	186290	3.2869	0.4087
2.9473	11.0	204919	3.3076	0.4083
2.9317	12.0	223548	3.3017	0.4090
2.9087	13.0	242177	3.2993	0.4088
2.8854	14.0	260806	3.3109	0.4096
2.8647	15.0	279435	3.3189	0.4091
2.8436	16.0	298064	3.3179	0.4100
2.828	17.0	316693	3.3213	0.4103
2.8085	18.0	335322	3.3345	0.4096
2.7947	19.0	353951	3.3383	0.4099
2.7703	20.0	372580	3.3415	0.4097

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.14.1