Configuration Parsing Warning:Config file config.json cannot be fetched (too big)

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

MATH_training_split_distill_small_teacher_1_8

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the MATH_training_split_distill_small_teacher dataset. It achieves the following results on the evaluation set:

Loss: 0.1733

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: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.1616	0.1781	100	0.1824
0.2029	0.3561	200	0.1828
0.1222	0.5342	300	0.1802
0.2275	0.7122	400	0.1738
0.1335	0.8903	500	0.1700
0.0572	1.0677	600	0.1817
0.0715	1.2457	700	0.1810
0.0629	1.4238	800	0.1786
0.0649	1.6018	900	0.1747
0.0555	1.7799	1000	0.1735
0.0646	1.9579	1100	0.1731

Framework versions

Transformers 4.49.0
Pytorch 2.7.0+cu126
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 2

Safetensors

Model size

0.5B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jojo2joker/MATH_training_split_distill_small_teacher_1_8

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(900)

this model