End of training

README.md

@@ -0,0 +1,96 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: output
+  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. -->
+
+# output
+
+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: 0.1301
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.2376        | 1.0   | 557   | 0.1378          |
+| 0.1626        | 2.0   | 1114  | 0.1266          |
+| 0.1515        | 3.0   | 1671  | 0.1213          |
+| 0.146         | 4.0   | 2228  | 0.1188          |
+| 0.1425        | 5.0   | 2785  | 0.1166          |
+| 0.14          | 6.0   | 3342  | 0.1161          |
+| 0.138         | 7.0   | 3899  | 0.1144          |
+| 0.1365        | 8.0   | 4456  | 0.1141          |
+| 0.1351        | 9.0   | 5013  | 0.1138          |
+| 0.134         | 10.0  | 5570  | 0.1137          |
+| 0.1329        | 11.0  | 6127  | 0.1124          |
+| 0.132         | 12.0  | 6684  | 0.1122          |
+| 0.1312        | 13.0  | 7241  | 0.1118          |
+| 0.1305        | 14.0  | 7798  | 0.1119          |
+| 0.1299        | 15.0  | 8355  | 0.1118          |
+| 0.1294        | 16.0  | 8912  | 0.1112          |
+| 0.129         | 17.0  | 9469  | 0.1112          |
+| 0.1285        | 18.0  | 10026 | 0.1116          |
+| 0.1282        | 19.0  | 10583 | 0.1105          |
+| 0.1276        | 20.0  | 11140 | 0.1103          |
+| 0.1273        | 21.0  | 11697 | 0.1106          |
+| 0.1269        | 22.0  | 12254 | 0.1103          |
+| 0.1267        | 23.0  | 12811 | 0.1103          |
+| 0.1263        | 24.0  | 13368 | 0.1098          |
+| 0.126         | 25.0  | 13925 | 0.1098          |
+| 0.1257        | 26.0  | 14482 | 0.1098          |
+| 0.1253        | 27.0  | 15039 | 0.1101          |
+| 0.125         | 28.0  | 15596 | 0.1104          |
+| 0.1247        | 29.0  | 16153 | 0.1102          |
+| 0.1245        | 30.0  | 16710 | 0.1093          |
+| 0.1241        | 31.0  | 17267 | 0.1112          |
+| 0.124         | 32.0  | 17824 | 0.1092          |
+| 0.1237        | 33.0  | 18381 | 0.1097          |
+| 0.1235        | 34.0  | 18938 | 0.1094          |
+| 0.1233        | 35.0  | 19495 | 0.1097          |
+| 0.1229        | 36.0  | 20052 | 0.1101          |
+| 0.1227        | 37.0  | 20609 | 0.1107          |
+| 0.1226        | 38.0  | 21166 | 0.1094          |
+| 0.1224        | 39.0  | 21723 | 0.1094          |
+| 0.1221        | 40.0  | 22280 | 0.1102          |
+| 0.122         | 41.0  | 22837 | 0.1109          |
+| 0.1218        | 42.0  | 23394 | 0.1101          |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,50 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "PatchTSTForPrediction"
+  ],
+  "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": null,
+  "dropout": 0.2,
+  "ff_dropout": 0.0,
+  "ffn_dim": 256,
+  "head_dropout": 0.2,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "layernorm",
+  "num_attention_heads": 16,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 321,
+  "num_parallel_samples": 100,
+  "num_targets": 1,
+  "output_range": null,
+  "patch_length": 16,
+  "patch_stride": 16,
+  "path_dropout": 0.0,
+  "pooling_type": null,
+  "positional_dropout": 0.0,
+  "positional_encoding_type": "sincos",
+  "pre_norm": true,
+  "prediction_length": 96,
+  "random_mask_ratio": 0.4,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "unmasked_channel_indices": null,
+  "use_cls_token": false
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b38ee1b11f68d169808801a1206614b29dde131cd3eec8ae27be0cbcc17a650
+size 3193880

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833e677e01c9e34fd1c0b1eb0b9f6a068add2c06a803351f201fa173ab21e465
+size 4792