Qwen3-1.7B-Base-hatebr-ep80

g-assismoraes/Qwen3-1.7B-Base-hatebr-ep80

Qwen3-1.7B-Base-hatebr-ep80 is a text generation model from g-assismoraes. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Parameters

1.7B

3.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors3.4 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: qwen3
Access: Public
Created: Aug 15, 2025
Updated: Aug 15, 2025
SHA: e97267d0

Try a prompt

Base models

Qwen/Qwen3-1.7B-Base

Model card

From the Hugging Face model README

Qwen3-1.7B-Base-hatebr-ep80

This model is a fine-tuned version of Qwen/Qwen3-1.7B-Base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0837

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
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: linear
num_epochs: 80

Training results

Training Loss	Epoch	Step	Validation Loss
0.6012	1.0	1120	0.5427
0.5277	2.0	2240	0.5396
0.4539	3.0	3360	0.5515
0.42	4.0	4480	0.5748
0.3919	5.0	5600	0.5983
0.3442	6.0	6720	0.6389
0.2954	7.0	7840	0.6887
0.2787	8.0	8960	0.7277
0.2221	9.0	10080	0.7553
0.2263	10.0	11200	0.7934
0.1929	11.0	12320	0.8283
0.1738	12.0	13440	0.8329
0.1554	13.0	14560	0.8702
0.1448	14.0	15680	0.8827
0.1434	15.0	16800	0.9032
0.1353	16.0	17920	0.9135
0.1209	17.0	19040	0.9276
0.1201	18.0	20160	0.9439
0.1055	19.0	21280	0.9485
0.1074	20.0	22400	0.9715
0.1052	21.0	23520	0.9795
0.1025	22.0	24640	0.9904
0.1024	23.0	25760	1.0023
0.0936	24.0	26880	1.0158
0.0986	25.0	28000	1.0115
0.0949	26.0	29120	1.0335
0.0928	27.0	30240	1.0243
0.0907	28.0	31360	1.0330
0.0901	29.0	32480	1.0350
0.0875	30.0	33600	1.0363
0.0881	31.0	34720	1.0379
0.0879	32.0	35840	1.0541
0.0865	33.0	36960	1.0439
0.0873	34.0	38080	1.0561
0.0857	35.0	39200	1.0557
0.0837	36.0	40320	1.0559
0.0834	37.0	41440	1.0628
0.0836	38.0	42560	1.0556
0.0852	39.0	43680	1.0684
0.0851	40.0	44800	1.0764
0.0816	41.0	45920	1.0675
0.0831	42.0	47040	1.0793
0.0839	43.0	48160	1.0692
0.0816	44.0	49280	1.0792
0.0839	45.0	50400	1.0766
0.0828	46.0	51520	1.0736
0.0827	47.0	52640	1.0749
0.0812	48.0	53760	1.0769
0.0804	49.0	54880	1.0785
0.0817	50.0	56000	1.0783
0.0804	51.0	57120	1.0737
0.08	52.0	58240	1.0739
0.0818	53.0	59360	1.0783
0.0822	54.0	60480	1.0779
0.0813	55.0	61600	1.0813
0.0808	56.0	62720	1.0807
0.0816	57.0	63840	1.0797
0.0815	58.0	64960	1.0863
0.0807	59.0	66080	1.0821
0.0814	60.0	67200	1.0826
0.0803	61.0	68320	1.0786
0.0819	62.0	69440	1.0812
0.0805	63.0	70560	1.0828
0.0826	64.0	71680	1.0808
0.0788	65.0	72800	1.0852
0.08	66.0	73920	1.0848
0.0805	67.0	75040	1.0850
0.0793	68.0	76160	1.0800
0.0798	69.0	77280	1.0826
0.0804	70.0	78400	1.0839
0.0814	71.0	79520	1.0826
0.0798	72.0	80640	1.0851
0.0797	73.0	81760	1.0851
0.081	74.0	82880	1.0845
0.0814	75.0	84000	1.0844
0.0813	76.0	85120	1.0851
0.0812	77.0	86240	1.0837
0.0813	78.0	87360	1.0809
0.0794	79.0	88480	1.0808
0.0793	80.0	89600	1.0837

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Task: Text Generation
Library: transformers
Type: qwen3
License: apache-2.0
Created: Aug 15, 2025
Updated: Aug 15, 2025