clinton254
commited on
Commit
•
e861e51
1
Parent(s):
bab64db
patchtst
Browse files- README.md +45 -0
- config.json +50 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: patch_tst
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# patch_tst
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
|
16 |
+
## Model description
|
17 |
+
|
18 |
+
More information needed
|
19 |
+
|
20 |
+
## Intended uses & limitations
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Training and evaluation data
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training procedure
|
29 |
+
|
30 |
+
### Training hyperparameters
|
31 |
+
|
32 |
+
The following hyperparameters were used during training:
|
33 |
+
- learning_rate: 5e-05
|
34 |
+
- train_batch_size: 64
|
35 |
+
- eval_batch_size: 64
|
36 |
+
- seed: 42
|
37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
+
- lr_scheduler_type: linear
|
39 |
+
- num_epochs: 3.0
|
40 |
+
|
41 |
+
### Framework versions
|
42 |
+
|
43 |
+
- Transformers 4.37.2
|
44 |
+
- Pytorch 2.1.0+cu121
|
45 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"PatchTSTForClassification"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bias": true,
|
8 |
+
"channel_attention": false,
|
9 |
+
"channel_consistent_masking": false,
|
10 |
+
"context_length": 512,
|
11 |
+
"d_model": 128,
|
12 |
+
"distribution_output": "student_t",
|
13 |
+
"do_mask_input": null,
|
14 |
+
"dropout": 0.0,
|
15 |
+
"ff_dropout": 0.0,
|
16 |
+
"ffn_dim": 512,
|
17 |
+
"head_dropout": 0.0,
|
18 |
+
"init_std": 0.02,
|
19 |
+
"loss": "mse",
|
20 |
+
"mask_type": "random",
|
21 |
+
"mask_value": 0,
|
22 |
+
"model_type": "patchtst",
|
23 |
+
"norm_eps": 1e-05,
|
24 |
+
"norm_type": "batchnorm",
|
25 |
+
"num_attention_heads": 4,
|
26 |
+
"num_forecast_mask_patches": [
|
27 |
+
2
|
28 |
+
],
|
29 |
+
"num_hidden_layers": 3,
|
30 |
+
"num_input_channels": 3,
|
31 |
+
"num_parallel_samples": 100,
|
32 |
+
"num_targets": 4,
|
33 |
+
"output_range": null,
|
34 |
+
"patch_length": 16,
|
35 |
+
"patch_stride": 16,
|
36 |
+
"path_dropout": 0.0,
|
37 |
+
"pooling_type": "mean",
|
38 |
+
"positional_dropout": 0.0,
|
39 |
+
"positional_encoding_type": "sincos",
|
40 |
+
"pre_norm": true,
|
41 |
+
"prediction_length": 24,
|
42 |
+
"random_mask_ratio": 0.5,
|
43 |
+
"scaling": "std",
|
44 |
+
"share_embedding": true,
|
45 |
+
"share_projection": true,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.37.2",
|
48 |
+
"unmasked_channel_indices": null,
|
49 |
+
"use_cls_token": false
|
50 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9e064010e4dce528ea8f9872d47e4e656678161bfb8f8badd18c7714cfe7389
|
3 |
+
size 2424760
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ec3fdd153d581522ea8cf49aee2a84115a856a209ff707637ba80cc73061627
|
3 |
+
size 4664
|