You can deploy this model and start earning money today!

contemmcm/
e4282864d74884ad524c5f2bbc20c511

Name: e4282864d74884ad524c5f2bbc20c511
Rating: 2.5 (9 reviews)

generated_from_trainer

distilbert/distilgpt2

finetune

apache-2.0

endpoints_compatible

Views

No views yet

e4282864d74884ad524c5f2bbc20c511

This model is a fine-tuned version of distilbert/distilgpt2 on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

Loss: 1.0704
Data Size: 1.0
Epoch Runtime: 123.4001
Accuracy: 0.6715
F1 Macro: 0.5966

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	3.6910	0	8.7986	0.3846	0.1129
No log	1	1973	1.4796	0.0078	9.6313	0.3644	0.2284
0.0336	2	3946	1.3123	0.0156	9.9926	0.4676	0.2923
1.1586	3	5919	1.0647	0.0312	11.4152	0.5557	0.3842
0.989	4	7892	0.9020	0.0625	13.7673	0.6247	0.5125
0.896	5	9865	0.8748	0.125	19.7605	0.6383	0.5078
0.8432	6	11838	0.8329	0.25	29.3461	0.6562	0.5508
0.8345	7	13811	0.7730	0.5	64.3705	0.6770	0.5906
0.7499	8.0	15784	0.7578	1.0	122.2699	0.6807	0.6057
0.6719	9.0	17757	0.7483	1.0	124.6216	0.6942	0.6103
0.5793	10.0	19730	0.7811	1.0	123.4201	0.6885	0.6234
0.5128	11.0	21703	0.8755	1.0	124.3051	0.6815	0.5926
0.4561	12.0	23676	0.9241	1.0	124.8142	0.6797	0.6087
0.3815	13.0	25649	1.0704	1.0	123.4001	0.6715	0.5966

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/e4282864d74884ad524c5f2bbc20c511

e4282864d74884ad524c5f2bbc20c511

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
e4282864d74884ad524c5f2bbc20c511