You can deploy this model and start earning money today!

MayaAyman/
cube_model

generated_from_trainer

mistralai/Mistral-7B-Instruct-v0.3

adapter

apache-2.0

Views

No views yet

cube_model

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the cube_finetune_train dataset. It achieves the following results on the evaluation set:

Loss: 0.0914

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.2884	0.3064	100	0.2831
0.2081	0.6128	200	0.2174
0.203	0.9192	300	0.1819
0.0861	1.2237	400	0.1533
0.0984	1.5301	500	0.1360
0.0555	1.8365	600	0.1078
0.0345	2.1409	700	0.0984
0.0103	2.4473	800	0.0934
0.0133	2.7537	900	0.0924

Framework versions

PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.7.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1

MayaAyman/cube_model

cube_model

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

MayaAyman/
cube_model