time series foundation model

README.md

@@ -0,0 +1,109 @@
+---
+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: 0.1542
+
+## 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: 0.001
+- 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: 100
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.2823        | 1.0   | 384   | 0.1897          |
+| 0.2134        | 2.0   | 768   | 0.1762          |
+| 0.1961        | 3.0   | 1152  | 0.1714          |
+| 0.1855        | 4.0   | 1536  | 0.1693          |
+| 0.1777        | 5.0   | 1920  | 0.1738          |
+| 0.1713        | 6.0   | 2304  | 0.1674          |
+| 0.1664        | 7.0   | 2688  | 0.1681          |
+| 0.1613        | 8.0   | 3072  | 0.1733          |
+| 0.1578        | 9.0   | 3456  | 0.1698          |
+| 0.1542        | 10.0  | 3840  | 0.1622          |
+| 0.1505        | 11.0  | 4224  | 0.1666          |
+| 0.1475        | 12.0  | 4608  | 0.1655          |
+| 0.1451        | 13.0  | 4992  | 0.1651          |
+| 0.1426        | 14.0  | 5376  | 0.1646          |
+| 0.1409        | 15.0  | 5760  | 0.1618          |
+| 0.1385        | 16.0  | 6144  | 0.1617          |
+| 0.1366        | 17.0  | 6528  | 0.1591          |
+| 0.1347        | 18.0  | 6912  | 0.1628          |
+| 0.1325        | 19.0  | 7296  | 0.1598          |
+| 0.1313        | 20.0  | 7680  | 0.1606          |
+| 0.1295        | 21.0  | 8064  | 0.1573          |
+| 0.1285        | 22.0  | 8448  | 0.1587          |
+| 0.1276        | 23.0  | 8832  | 0.1639          |
+| 0.1258        | 24.0  | 9216  | 0.1608          |
+| 0.1244        | 25.0  | 9600  | 0.1599          |
+| 0.1234        | 26.0  | 9984  | 0.1584          |
+| 0.1225        | 27.0  | 10368 | 0.1604          |
+| 0.1214        | 28.0  | 10752 | 0.1570          |
+| 0.1207        | 29.0  | 11136 | 0.1575          |
+| 0.1195        | 30.0  | 11520 | 0.1563          |
+| 0.1186        | 31.0  | 11904 | 0.1602          |
+| 0.1177        | 32.0  | 12288 | 0.1595          |
+| 0.1167        | 33.0  | 12672 | 0.1582          |
+| 0.1159        | 34.0  | 13056 | 0.1556          |
+| 0.1149        | 35.0  | 13440 | 0.1564          |
+| 0.114         | 36.0  | 13824 | 0.1567          |
+| 0.1132        | 37.0  | 14208 | 0.1551          |
+| 0.1125        | 38.0  | 14592 | 0.1560          |
+| 0.1113        | 39.0  | 14976 | 0.1537          |
+| 0.1114        | 40.0  | 15360 | 0.1518          |
+| 0.1103        | 41.0  | 15744 | 0.1585          |
+| 0.1098        | 42.0  | 16128 | 0.1552          |
+| 0.1094        | 43.0  | 16512 | 0.1533          |
+| 0.1087        | 44.0  | 16896 | 0.1542          |
+| 0.1081        | 45.0  | 17280 | 0.1505          |
+| 0.1085        | 46.0  | 17664 | 0.1535          |
+| 0.1075        | 47.0  | 18048 | 0.1526          |
+| 0.1069        | 48.0  | 18432 | 0.1521          |
+| 0.1067        | 49.0  | 18816 | 0.1532          |
+| 0.1063        | 50.0  | 19200 | 0.1522          |
+| 0.1056        | 51.0  | 19584 | 0.1522          |
+| 0.1048        | 52.0  | 19968 | 0.1538          |
+| 0.1048        | 53.0  | 20352 | 0.1534          |
+| 0.1051        | 54.0  | 20736 | 0.1519          |
+| 0.1045        | 55.0  | 21120 | 0.1542          |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "PatchTSMixerForPrediction"
+  ],
+  "channel_consistent_masking": true,
+  "context_length": 336,
+  "d_model": 16,
+  "distribution_output": "student_t",
+  "dropout": 0.2,
+  "expansion_factor": 2,
+  "gated_attn": true,
+  "head_aggregation": "max_pool",
+  "head_dropout": 0.2,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "masked_loss": true,
+  "mode": "common_channel",
+  "model_type": "patchtsmixer",
+  "norm_eps": 1e-05,
+  "norm_mlp": "LayerNorm",
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_input_channels": 5,
+  "num_layers": 8,
+  "num_parallel_samples": 100,
+  "num_patches": 42,
+  "num_targets": 3,
+  "output_range": null,
+  "patch_last": true,
+  "patch_length": 8,
+  "patch_stride": 8,
+  "positional_encoding_type": "sincos",
+  "post_init": false,
+  "prediction_channel_indices": null,
+  "prediction_length": 24,
+  "random_mask_ratio": 0.5,
+  "scaling": "std",
+  "self_attn": false,
+  "self_attn_heads": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "unmasked_channel_indices": null,
+  "use_positional_encoding": false
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766cbfc72ba5977581332849849ab68c83e73d1af16de5b1dcec5914699e29f5
+size 415592

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e020b16425ffb87111456e7cacf5a0c4c58202d0204f4e43729cc6170830d253
+size 4728