namctin/test_patchtst_pretrain_etth1

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: patchtst_etth1_pretrain
+  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_pretrain
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## 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
+
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.0.1
+- Datasets 2.14.4
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,49 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "PatchTSTForPretraining"
+  ],
+  "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": true,
+  "mask_type": "forecast",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 16,
+  "num_forecast_mask_patches": 5,
+  "num_hidden_layers": 3,
+  "num_input_channels": 7,
+  "num_parallel_samples": 100,
+  "num_targets": 1,
+  "output_range": null,
+  "patch_length": 12,
+  "patch_stride": 12,
+  "path_dropout": 0.0,
+  "pooling_type": null,
+  "positional_dropout": 0.0,
+  "positional_encoding_type": "sincos",
+  "pre_norm": true,
+  "prediction_length": 24,
+  "random_mask_ratio": 0.5,
+  "scaling": "std",
+  "seed_number": null,
+  "share_embedding": true,
+  "share_projection": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "unmasked_channel_indices": null,
+  "use_cls_token": true
+}

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
+2023-11-21T14:17:38,5883e64f-5ee3-4ec1-b417-e32ec5a62382,codecarbon,91.5881712436676,0.000654747073756541,0.00311079309166191,United States,USA,new york,N,,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac3d606577625150561539791f3eae87058ea8ccfa67c45cb22205657b81103
+size 2429008

runs/Nov21_14-03-34_cccxc568/events.out.tfevents.1700593419.cccxc568.2107647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1dc6ccbc391a12794830777728f96675b8b413080fd2b394b653f56e81dd946
+size 4848

runs/Nov21_14-04-55_cccxc568/events.out.tfevents.1700593496.cccxc568.2107647.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275242b0d6148d50d376e055515452def61659f662cd9bbbf06a7559c594ff37
+size 5228

runs/Nov21_14-16-05_cccxc568/events.out.tfevents.1700594167.cccxc568.2107647.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318e672d5077591fdc25c651eb8578a1dbefb430ed8b5ff8313e38b85cdeecbd
+size 6851

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022d316bcac15fbda5a7be60a62435612b7b53a2986397d5272730ebc109c719
+size 4219