README.md

metadata

license: apache-2.0
base_model: IDEA-CCNL/Erlangshen-Longformer-110M
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: >-
      Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-f1-5
    results: []

Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-f1-5

This model is a fine-tuned version of IDEA-CCNL/Erlangshen-Longformer-110M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9559
• F1: 0.6667

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	34	3.1360	0.6111
No log	2.0	68	1.5706	0.7586
No log	3.0	102	1.2619	0.7692
No log	4.0	136	2.7414	0.625
No log	5.0	170	1.7157	0.6667
No log	6.0	204	2.2175	0.6667
No log	7.0	238	2.0533	0.6667
No log	8.0	272	2.2478	0.7333
No log	9.0	306	1.8182	0.64
No log	10.0	340	1.9559	0.6667

Framework versions

• Transformers 4.34.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1