Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Mistral_Sparse_refined_web_graceful_reg_90p_2024-03-15 – AI Model by thrunlab | AlphaNeural AI
You can deploy this model and start earning money today!
thrunlab
/
Mistral_Sparse_refined_web_graceful_reg_90p_2024-03-15
like
0
transformers
safetensors
sparse_mistral
text-generation
generated_from_trainer
custom_code
mistralai/Mistral-7B-v0.1
finetune
apache-2.0
autotrain_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Mistral_Sparse_refined_web_graceful_reg_90p_2024-03-15
This model is a fine-tuned version of
mistralai/Mistral-7B-v0.1
on the None dataset. It achieves the following results on the evaluation set:
Loss: 3.2280
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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 0
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 32
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 200
Training results
Training Loss
Epoch
Step
Validation Loss
3.6976
0.01
25
2.3994
3.6502
0.02
50
2.3851
3.6737
0.02
75
2.3872
3.5871
0.03
100
2.4521
3.5615
0.04
125
2.4990
3.4322
0.05
150
2.5199
3.3361
0.06
175
2.5204
3.3823
0.06
200
2.5230
Framework versions
Transformers 4.37.2
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0
