You can deploy this model and start earning money today!

sahil-theloops/
Mistral_7B_Instruct_V02

Name: Mistral_7B_Instruct_V02
Availability: InStock

peft

safetensors

generated_from_trainer

mistralai/Mistral-7B-Instruct-v0.2

adapter

apache-2.0

Views

No views yet

Mistral_7B_Instruct_V02

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3369

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: 2.5e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3241	0.14	200	0.3797
0.3135	0.28	400	0.3664
0.3343	0.43	600	0.3595
0.3664	0.57	800	0.3544
0.2947	0.71	1000	0.3510
0.3098	0.85	1200	0.3483
0.3488	1.0	1400	0.3454
0.2957	1.14	1600	0.3447
0.2821	1.28	1800	0.3430
0.2814	1.42	2000	0.3410
0.2756	1.56	2200	0.3392
0.2769	1.71	2400	0.3379
0.2946	1.85	2600	0.3364
0.2933	1.99	2800	0.3349
0.2529	2.13	3000	0.3383
0.2781	2.28	3200	0.3377
0.2561	2.42	3400	0.3387
0.2467	2.56	3600	0.3377
0.2758	2.7	3800	0.3375
0.221	2.84	4000	0.3370
0.2579	2.99	4200	0.3369

Framework versions

PEFT 0.10.1.dev0
Transformers 4.38.2
Pytorch 2.2.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

sahil-theloops/Mistral_7B_Instruct_V02

Mistral_7B_Instruct_V02

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sahil-theloops/
Mistral_7B_Instruct_V02