opt-babylm2-20-epochs_seed-42_1e-3 – AI Model by kanishka | AlphaNeural AI

You can deploy this model and start earning money today!

kanishka/
opt-babylm2-20-epochs_seed-42_1e-3

like

0

text-generation

generated_from_trainer

kanishka/babylm2-sentence-tokenized

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

opt-babylm2-20-epochs_seed-42_1e-3

This model was trained from scratch on the kanishka/babylm2-sentence-tokenized dataset. It achieves the following results on the evaluation set:

Loss: 2.4862
Accuracy: 0.5211

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: 0.001
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
2.7114	1.0	21397	2.8283	0.4749
2.5228	2.0	42794	2.6497	0.4950
2.423	3.0	64191	2.5691	0.5045
2.3641	4.0	85588	2.5271	0.5096
2.3077	5.0	106985	2.5005	0.5130
2.2752	6.0	128382	2.4888	0.5148
2.2395	7.0	149779	2.4765	0.5168
2.2179	8.0	171176	2.4709	0.5178
2.1916	9.0	192573	2.4651	0.5187
2.1646	10.0	213970	2.4652	0.5193
2.1449	11.0	235367	2.4641	0.5199
2.1298	12.0	256764	2.4656	0.5203
2.1054	13.0	278161	2.4637	0.5206
2.0971	14.0	299558	2.4668	0.5207
2.0723	15.0	320955	2.4676	0.5209
2.0582	16.0	342352	2.4699	0.5211
2.0422	17.0	363749	2.4730	0.5212
2.0302	18.0	385146	2.4786	0.5212
2.0135	19.0	406543	2.4823	0.5211
1.99	20.0	427940	2.4862	0.5211

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0