patch_tst_pretrain

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: pretraining
+  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. -->
+
+# pretraining
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9934
+
+## 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: 64
+- eval_batch_size: 64
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9973        | 1.0   | 13   | 0.9918          |
+| 0.9964        | 2.0   | 26   | 0.9961          |
+| 0.9966        | 3.0   | 39   | 0.9974          |
+| 0.996         | 4.0   | 52   | 0.9960          |
+| 0.996         | 5.0   | 65   | 1.0023          |
+| 0.9966        | 6.0   | 78   | 0.9973          |
+| 0.9953        | 7.0   | 91   | 0.9934          |
+| 0.9972        | 8.0   | 104  | 0.9954          |
+| 1.0003        | 9.0   | 117  | 0.9965          |
+| 0.9975        | 10.0  | 130  | 0.9989          |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,50 @@
+{
+  "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",
+  "do_mask_input": true,
+  "dropout": 0.0,
+  "ff_dropout": 0.0,
+  "ffn_dim": 512,
+  "head_dropout": 0.0,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 4,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 3,
+  "num_parallel_samples": 100,
+  "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": 0.4,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "unmasked_channel_indices": null,
+  "use_cls_token": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c7547d66ff83211723568b1909c57f6589c713edd0f1b1cc9f43ee08a5bdb9
+size 2429008

tmp-checkpoint-25/config.json

@@ -0,0 +1,50 @@
+{
+  "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",
+  "do_mask_input": true,
+  "dropout": 0.0,
+  "ff_dropout": 0.0,
+  "ffn_dim": 512,
+  "head_dropout": 0.0,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 4,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 3,
+  "num_parallel_samples": 100,
+  "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": 0.4,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "unmasked_channel_indices": null,
+  "use_cls_token": true
+}

tmp-checkpoint-25/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e184177214a7efbe31f5e610065eb83aab8ab83af03fffd13378da464e31925a
+size 2429008

tmp-checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba83a1696bed2a71a0dca6f071e5ed4e44347e2955b23d8012b926333b0096f
+size 4828154

tmp-checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f503e9554d56e2b3980363d8454cf281906ac6dded7092d888a589add5ca0c05
+size 13990

tmp-checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a88033ff558bbf1f6d35e78a8cac7072ac70b7e0a99f6084b6059e1f3f821c9
+size 1064

tmp-checkpoint-25/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0afc52d619c2552ba4ba0c12efe06043525a95f3996e697935edccfd91de3d7
+size 4664

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3f6d77a63b4ebdde338ed2df8486bc41ab85b843bf6d3d592a8d8710e643a7
+size 4664