README.md

metadata

library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: bert-reg-biencoder-mae
    results: []

bert-reg-biencoder-mae

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2340
• Mse: 0.0819
• Mae: 0.2335
• Pearson Corr: 0.2475
• Spearman Corr: 0.1329
• Cosine Sim: 0.9022

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	Pearson Corr	Spearman Corr	Cosine Sim
0.2846	1.0	21	0.2617	0.1153	0.2610	0.1327	0.0936	0.9053
0.2728	2.0	42	0.2310	0.0886	0.2304	0.0188	0.0316	0.8994
0.2511	3.0	63	0.2282	0.0847	0.2276	0.1716	0.1111	0.9058
0.2253	4.0	84	0.2333	0.0864	0.2329	0.1906	0.1191	0.9041
0.1993	5.0	105	0.2329	0.0822	0.2325	0.2303	0.1246	0.9016
0.1844	6.0	126	0.2357	0.0828	0.2352	0.2284	0.1254	0.9018
0.165	7.0	147	0.2340	0.0819	0.2335	0.2475	0.1329	0.9022

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0