experiment-distill-tree-babylm2024-58M-seq-1 – AI Model by aakarsh-nair | AlphaNeural AI

You can deploy this model and start earning money today!

aakarsh-nair/
experiment-distill-tree-babylm2024-58M-seq-1

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

experiment-distill-tree-babylm2024-58M-seq-1

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 5.1943

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: 0.00025
train_batch_size: 64
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 200
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
8.53	1.0	2065	8.9592
6.5636	2.0	4130	6.9316
6.0134	3.0	6195	6.3153
5.718	4.0	8260	5.9170
5.3728	5.0	10325	5.7022
5.2975	6.0	12390	5.4895
5.0661	7.0	14455	5.3451
5.0005	8.0	16520	5.2530
4.88	9.0	18585	5.2067
4.9478	10.0	20650	5.1943

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Tokenizers 0.19.1