Commit
•
923211e
1
Parent(s):
c85b1e1
patch_tst_pretrain
Browse files- README.md +63 -0
- config.json +50 -0
- model.safetensors +3 -0
- tmp-checkpoint-25/config.json +50 -0
- tmp-checkpoint-25/model.safetensors +3 -0
- tmp-checkpoint-25/optimizer.pt +3 -0
- tmp-checkpoint-25/rng_state.pth +3 -0
- tmp-checkpoint-25/scheduler.pt +3 -0
- tmp-checkpoint-25/training_args.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: pretraining
|
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 |
+
# pretraining
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.9934
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 64
|
37 |
+
- eval_batch_size: 64
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 10
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| 0.9973 | 1.0 | 13 | 0.9918 |
|
48 |
+
| 0.9964 | 2.0 | 26 | 0.9961 |
|
49 |
+
| 0.9966 | 3.0 | 39 | 0.9974 |
|
50 |
+
| 0.996 | 4.0 | 52 | 0.9960 |
|
51 |
+
| 0.996 | 5.0 | 65 | 1.0023 |
|
52 |
+
| 0.9966 | 6.0 | 78 | 0.9973 |
|
53 |
+
| 0.9953 | 7.0 | 91 | 0.9934 |
|
54 |
+
| 0.9972 | 8.0 | 104 | 0.9954 |
|
55 |
+
| 1.0003 | 9.0 | 117 | 0.9965 |
|
56 |
+
| 0.9975 | 10.0 | 130 | 0.9989 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.37.2
|
62 |
+
- Pytorch 2.1.0+cu121
|
63 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"PatchTSTForPretraining"
|
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": true,
|
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": 1,
|
33 |
+
"output_range": null,
|
34 |
+
"patch_length": 12,
|
35 |
+
"patch_stride": 12,
|
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": 0.4,
|
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": true
|
50 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5c7547d66ff83211723568b1909c57f6589c713edd0f1b1cc9f43ee08a5bdb9
|
3 |
+
size 2429008
|
tmp-checkpoint-25/config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"PatchTSTForPretraining"
|
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": true,
|
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": 1,
|
33 |
+
"output_range": null,
|
34 |
+
"patch_length": 12,
|
35 |
+
"patch_stride": 12,
|
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": 0.4,
|
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": true
|
50 |
+
}
|
tmp-checkpoint-25/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e184177214a7efbe31f5e610065eb83aab8ab83af03fffd13378da464e31925a
|
3 |
+
size 2429008
|
tmp-checkpoint-25/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dba83a1696bed2a71a0dca6f071e5ed4e44347e2955b23d8012b926333b0096f
|
3 |
+
size 4828154
|
tmp-checkpoint-25/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f503e9554d56e2b3980363d8454cf281906ac6dded7092d888a589add5ca0c05
|
3 |
+
size 13990
|
tmp-checkpoint-25/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a88033ff558bbf1f6d35e78a8cac7072ac70b7e0a99f6084b6059e1f3f821c9
|
3 |
+
size 1064
|
tmp-checkpoint-25/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0afc52d619c2552ba4ba0c12efe06043525a95f3996e697935edccfd91de3d7
|
3 |
+
size 4664
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a3f6d77a63b4ebdde338ed2df8486bc41ab85b843bf6d3d592a8d8710e643a7
|
3 |
+
size 4664
|