This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the t1_25k_v2_tag5_fixed_hermes dataset. It achieves the following results on the evaluation set:

Loss: 0.2461

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 4
total_eval_batch_size: 4
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: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.2842	0.0704	100	0.3212
0.3355	0.1408	200	0.2992
0.3257	0.2113	300	0.2843
0.2655	0.2817	400	0.2745
0.2419	0.3521	500	0.2684
0.2525	0.4225	600	0.2662
0.2335	0.4930	700	0.2633
0.2557	0.5634	800	0.2573
0.2337	0.6338	900	0.2527
0.2606	0.7042	1000	0.2506
0.2466	0.7746	1100	0.2478
0.2473	0.8451	1200	0.2464
0.2356	0.9155	1300	0.2462
0.2559	0.9859	1400	0.2459

Framework versions

Transformers 4.46.1
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.20.3

lemonhat/Qwen2.5-7B-Instruct-t1_25k_v2_tag5_fixed_hermes

t1_25k_v2_tag5_fixed_hermes

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

lemonhat/
Qwen2.5-7B-Instruct-t1_25k_v2_tag5_fixed_hermes