Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
rcgrpo_sft_qwen – AI Model by JZSAWYER | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
JZSAWYER
/
rcgrpo_sft_qwen
like
0
transformers
tensorboard
safetensors
qwen2
text-generation
llama-factory
full
generated_from_trainer
conversational
Qwen/Qwen2.5-7B
finetune
other
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
sft
This model is a fine-tuned version of
/inspire/hdd/project/chemicalreaction/dijixiu-CZXS25220051/models/Qwen2.5-7B-Instruct
on the bfcl_sft_aligned_train dataset. It achieves the following results on the evaluation set:
Loss: 0.0021
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: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 16
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 5.0
Training results
Training Loss
Epoch
Step
Validation Loss
0.0736
1.1111
50
0.0216
0.0623
2.2222
100
0.0078
0.0011
3.3333
150
0.0024
0.0512
4.4444
200
0.0021
Framework versions
Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.0.0
Tokenizers 0.22.1
