namctin/patchtst-etth1-regression

README.md

@@ -0,0 +1,64 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: patchtst_etth1_regression
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# patchtst_etth1_regression
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7280
+
+## 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: 5e-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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.1517        | 1.0   | 1017  | 0.3056          |
+| 0.1163        | 2.0   | 2034  | 0.2771          |
+| 0.0919        | 3.0   | 3051  | 0.2450          |
+| 0.0764        | 4.0   | 4068  | 0.2216          |
+| 0.0653        | 5.0   | 5085  | 0.2528          |
+| 0.0577        | 6.0   | 6102  | 0.2189          |
+| 0.0498        | 7.0   | 7119  | 0.2526          |
+| 0.0456        | 8.0   | 8136  | 0.2565          |
+| 0.0408        | 9.0   | 9153  | 0.2603          |
+| 0.0369        | 10.0  | 10170 | 0.2523          |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.0.1
+- Datasets 2.14.4
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "./model/patchtst_etth1_pretrain",
+  "activation_function": "gelu",
+  "architectures": [
+    "PatchTSTForRegression"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "channel_attention": false,
+  "channel_consistent_masking": false,
+  "context_length": 512,
+  "d_model": 128,
+  "distribution_output": "student_t",
+  "dropout": 0.2,
+  "ff_dropout": 0.0,
+  "ffn_dim": 512,
+  "head_dropout": 0.2,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_input": null,
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 16,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 6,
+  "num_parallel_samples": 100,
+  "num_target": 1,
+  "num_targets": 1,
+  "output_range": null,
+  "patch_length": 12,
+  "patch_stride": 12,
+  "path_dropout": 0.0,
+  "pooling_type": "mean",
+  "positional_dropout": 0.0,
+  "positional_encoding_type": "sincos",
+  "pre_norm": true,
+  "prediction_length": 24,
+  "random_mask_ratio": 0.5,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "unmasked_channel_indices": null,
+  "use_cls_token": false
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2023-11-27T10:20:35,84b1faab-2e88-4aed-8f1d-c0e01a705153,codecarbon,107.79222440719604,0.0007052480902419897,0.003350730343009218,United States,USA,new york,N,,

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.36.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9462a98715f1f7f69b95bc821e64f9344be77334d04994406e59d07ec7eab1
+size 2424756

runs/Nov27_10-14-41_cccxc536/events.out.tfevents.1701098092.cccxc536.1088024.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2346ce8d8c5c5ea68c62497f3315a3239745e387127e9c0b8efb8df5f8235026
+size 4954

runs/Nov27_10-16-29_cccxc536/events.out.tfevents.1701098191.cccxc536.1088024.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2039001b417c7375eb278459069a680192c45f92c5c7fd276cba35facc3b376
+size 5336

runs/Nov27_10-18-39_cccxc536/events.out.tfevents.1701098327.cccxc536.1088024.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f7daa9f0dbfb0b966b9e48c357a5a173f3530d1e121805e4eb6ce42391dd83
+size 9672

runs/Nov27_10-18-39_cccxc536/events.out.tfevents.1701098436.cccxc536.1088024.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d2c3b841d5606f4eb8da949600357cb341b2a1af7ccf5c09121ea49b73f0c9
+size 359

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af5c32b665c5eb5a8eb7731d012d1a1945a0db5c07498f8cf739b30b6c81d9f
+size 4283