You can deploy this model and start earning money today!

mmustafa2194/
qwen2.5-1.5b-instruct-genai-v0.3

Name: qwen2.5-1.5b-instruct-genai-v0.3
Availability: InStock

generated_from_trainer

Qwen/Qwen2.5-1.5B-Instruct

adapter

apache-2.0

Views

No views yet

qwen2.5-1.5b-instruct-genai-v0.3

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the finetune_train_genai dataset. It achieves the following results on the evaluation set:

Loss: 0.3775

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6244	0.0631	100	0.5972
0.5988	0.1262	200	0.5624
0.6001	0.1893	300	0.5406
0.5796	0.2524	400	0.5348
0.7508	0.3155	500	0.5257
0.5659	0.3785	600	0.5133
0.6705	0.4416	700	0.5039
0.5055	0.5047	800	0.4919
0.5966	0.5678	900	0.4746
0.4532	0.6309	1000	0.4562
0.4135	0.6940	1100	0.4538
0.4829	0.7571	1200	0.4550
0.5239	0.8202	1300	0.4459
0.4102	0.8833	1400	0.4290
0.4438	0.9464	1500	0.4284
0.235	1.0095	1600	0.4214
0.2285	1.0726	1700	0.4299
0.2863	1.1356	1800	0.4208
0.2773	1.1987	1900	0.4151
0.2836	1.2618	2000	0.4151
0.2273	1.3249	2100	0.4081
0.165	1.3880	2200	0.4117
0.1348	1.4511	2300	0.3972
0.2274	1.5142	2400	0.3912
0.2932	1.5773	2500	0.3868
0.1665	1.6404	2600	0.3827
0.2626	1.7035	2700	0.3723
0.2172	1.7666	2800	0.3725
0.1786	1.8297	2900	0.3705
0.1864	1.8927	3000	0.3705
0.1776	1.9558	3100	0.3597
0.0557	2.0189	3200	0.3742
0.0762	2.0820	3300	0.3806
0.0754	2.1451	3400	0.3838
0.0822	2.2082	3500	0.3838
0.0434	2.2713	3600	0.3858
0.0498	2.3344	3700	0.3880
0.0844	2.3975	3800	0.3813
0.1364	2.4606	3900	0.3813
0.0669	2.5237	4000	0.3819
0.0521	2.5868	4100	0.3820
0.058	2.6498	4200	0.3800
0.0568	2.7129	4300	0.3781
0.0743	2.7760	4400	0.3780
0.0653	2.8391	4500	0.3783
0.0657	2.9022	4600	0.3775
0.0856	2.9653	4700	0.3774

Framework versions

PEFT 0.15.2
Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.1

mmustafa2194/qwen2.5-1.5b-instruct-genai-v0.3

qwen2.5-1.5b-instruct-genai-v0.3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mmustafa2194/
qwen2.5-1.5b-instruct-genai-v0.3