patchtst-exchange-rate

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

• Loss: 0.0002
• Model Preparation Time: 0.0008
• Mae: 0.0096
• Mse: 0.0002
• Rmse: 0.0156

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: 0.0005
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Mae	Mse	Rmse
0.0005	1.0	55	0.0003	0.0008	0.0114	0.0003	0.0183
0.0003	2.0	110	0.0005	0.0008	0.0128	0.0005	0.0215
0.0004	3.0	165	0.0003	0.0008	0.0110	0.0003	0.0181
0.0004	4.0	220	0.0003	0.0008	0.0108	0.0003	0.0179
0.0003	5.0	275	0.0004	0.0008	0.0129	0.0004	0.0204
0.0004	6.0	330	0.0005	0.0008	0.0129	0.0005	0.0213
0.0003	7.0	385	0.0004	0.0008	0.0116	0.0004	0.0195
0.0003	8.0	440	0.0003	0.0008	0.0111	0.0003	0.0184
0.0005	9.0	495	0.0004	0.0008	0.0127	0.0004	0.0205
0.0003	10.0	550	0.0003	0.0008	0.0110	0.0003	0.0184
0.0004	11.0	605	0.0004	0.0008	0.0114	0.0004	0.0189
0.0004	12.0	660	0.0004	0.0008	0.0119	0.0004	0.0196
0.0004	13.0	715	0.0003	0.0008	0.0111	0.0003	0.0184
0.0003	14.0	770	0.0004	0.0008	0.0114	0.0004	0.0188
0.0004	15.0	825	0.0004	0.0008	0.0118	0.0004	0.0195
0.0004	16.0	880	0.0005	0.0008	0.0131	0.0005	0.0217
0.0003	17.0	935	0.0004	0.0008	0.0116	0.0004	0.0192
0.0003	18.0	990	0.0004	0.0008	0.0115	0.0004	0.0190
0.0003	19.0	1045	0.0004	0.0008	0.0117	0.0004	0.0192

Framework versions

• Transformers 5.12.1
• Pytorch 2.12.1+cu130
• Datasets 5.0.0
• Tokenizers 0.22.2

Generated by ML Intern

This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.

• Try ML Intern: https://smolagents-ml-intern.hf.space
• Source code: https://github.com/huggingface/ml-intern

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'lvizcaya/patchtst-exchange-rate'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

For non-causal architectures, replace AutoModelForCausalLM with the appropriate AutoModel class.