This model is a fine-tuned version of Qwen/Qwen2.5-7B on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset. It achieves the following results on the evaluation set:

Loss: 0.6196

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-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 512
total_eval_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6364	0.9983	438	0.6270
0.6003	1.9994	877	0.6200
0.5853	2.9960	1314	0.6196

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.0.2
Tokenizers 0.20.3

RichardErkhov/mlfoundations-dev_-_hp_ablations_qwen_scheduler_cosine_warmup0.10_minlr1e-6-4bits

Original model description:

hp_ablations_qwen_scheduler_cosine_warmup0.10_minlr1e-6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_hp_ablations_qwen_scheduler_cosine_warmup0.10_minlr1e-6-4bits