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: 0.6213

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: 4
total_train_batch_size: 256
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: constant
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 1738
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6134	0.9994	877	0.6224
0.5823	2.0	1755	0.6175
0.5443	2.9983	2631	0.6213

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.0.2
Tokenizers 0.20.3

RichardErkhov/mlfoundations-dev_-_hp_ablations_qwen_bsz256-4bits

Original model description:

hp_ablations_qwen_bsz256

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_hp_ablations_qwen_bsz256-4bits