ernie-4-5-0.3B-finance-sft

mhtccc/ernie-4-5-0.3B-finance-sft

ernie-4-5-0.3B-finance-sft is a text generation model from mhtccc. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.

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

Downloads · 30 days

496

50% of all-time downloads

All-time downloads

988

Public

Parameters

359M

1.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.4 GB · 99%

At a glance

Task: Text Generation
Library: transformers
License: other
Model type: ernie4_5
Access: Public
Created: Dec 22, 2025
Updated: Dec 22, 2025
SHA: e5374485

Try a prompt

Base models

baidu/ERNIE-4.5-0.3B-PT

Model card

From the Hugging Face model README

finance-sentiment

This model is a fine-tuned version of D:/code/LLaMA-Factory/0.my_code/process/ernie-sentiment-init on the finance_sentiment dataset. It achieves the following results on the evaluation set:

Loss: 0.4226

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-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: cosine
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 50
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.5518	0.1	250	0.5404
0.6025	0.2	500	0.5480
0.6125	0.3	750	0.5375
0.5424	0.4	1000	0.5382
0.5393	0.5	1250	0.5357
0.5091	0.6	1500	0.5414
0.5425	0.7	1750	0.5335
0.4942	0.8	2000	0.5646
0.5687	0.9	2250	0.5381
0.5462	1.0	2500	0.5609
0.5048	1.1	2750	0.4820
0.5025	1.2	3000	0.4848
0.4823	1.3	3250	0.4895
0.4914	1.4	3500	0.4482
0.4051	1.5	3750	0.4579
0.3931	1.6	4000	0.4225
0.3865	1.7	4250	0.4917
0.625	1.8	4500	0.4107
0.3882	1.9	4750	0.4676
0.2762	2.0	5000	0.4387
0.4132	2.1	5250	0.4282
0.527	2.2	5500	0.4122
0.4196	2.3	5750	0.3563
0.3263	2.4	6000	0.3680
0.354	2.5	6250	0.3632
0.4371	2.6	6500	0.3458
0.3613	2.7	6750	0.3582
0.3223	2.8	7000	0.3965
0.4591	2.9	7250	0.3279
0.4607	3.0	7500	0.3537
0.1142	3.1	7750	0.3854
0.4335	3.2	8000	0.3537
0.4776	3.3	8250	0.4166
0.3446	3.4	8500	0.3924
0.0918	3.5	8750	0.4337
0.3786	3.6	9000	0.4035
0.3945	3.7	9250	0.3965
0.1989	3.8	9500	0.4014
0.3032	3.9	9750	0.3335
0.2882	4.0	10000	0.3608
0.3639	4.1	10250	0.4448
0.283	4.2	10500	0.4376
0.2759	4.3	10750	0.4415
0.4924	4.4	11000	0.4275
0.3681	4.5	11250	0.4300
0.2862	4.6	11500	0.4283
0.2423	4.7	11750	0.4243
0.0904	4.8	12000	0.4217
0.2766	4.9	12250	0.4226
0.3408	5.0	12500	0.4226

Framework versions

Transformers 4.57.3
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Task: Text Generation
Library: transformers
Type: ernie4_5
License: other
Created: Dec 22, 2025
Updated: Dec 22, 2025