End of training

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: ibm/TTM
+tags:
+- generated_from_trainer
+model-index:
+- name: fewshot_10
+  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. -->
+
+# fewshot_10
+
+This model is a fine-tuned version of [ibm/TTM](https://huggingface.co/ibm/TTM) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0405
+
+## 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: 512
+- eval_batch_size: 512
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1341        | 1.0   | 48   | 0.0386          |
+| 0.1293        | 2.0   | 96   | 0.0383          |
+| 0.1268        | 3.0   | 144  | 0.0382          |
+| 0.1245        | 4.0   | 192  | 0.0382          |
+| 0.1218        | 5.0   | 240  | 0.0383          |
+| 0.1188        | 6.0   | 288  | 0.0389          |
+| 0.1159        | 7.0   | 336  | 0.0395          |
+| 0.1124        | 8.0   | 384  | 0.0399          |
+| 0.1088        | 9.0   | 432  | 0.0402          |
+| 0.105         | 10.0  | 480  | 0.0405          |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "ibm/TTM",
+  "adaptive_patching_levels": 3,
+  "architectures": [
+    "TinyTimeMixerForPrediction"
+  ],
+  "context_length": 1024,
+  "d_model": 192,
+  "d_model_scale": 3,
+  "decoder_adaptive_patching_levels": 0,
+  "decoder_d_model": 128,
+  "decoder_d_model_scale": 2,
+  "decoder_mode": "common_channel",
+  "decoder_num_layers": 2,
+  "decoder_raw_residual": false,
+  "dropout": 0.2,
+  "expansion_factor": 2,
+  "frequency_token_vocab_size": 5,
+  "gated_attn": true,
+  "head_dropout": 0.2,
+  "init_processing": true,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mode": "common_channel",
+  "model_type": "tinytimemixer",
+  "norm_eps": 1e-05,
+  "norm_mlp": "LayerNorm",
+  "num_input_channels": 1,
+  "num_layers": 2,
+  "num_patches": 16,
+  "patch_last": true,
+  "patch_length": 64,
+  "patch_stride": 64,
+  "positional_encoding_type": "sincos",
+  "post_init": false,
+  "prediction_channel_indices": null,
+  "prediction_filter_length": null,
+  "prediction_length": 96,
+  "resolution_prefix_tuning": false,
+  "scaling": "std",
+  "self_attn": false,
+  "self_attn_heads": 1,
+  "stride_ratio": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_decoder": true,
+  "use_positional_encoding": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa22459b56fa87cf69e94b7d280c97582a76096d3a4658e1331d2a5c54d3379a
+size 3804872

runs/May30_18-03-06_one/events.out.tfevents.1717059786.one.682896.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe3c6f3f63706cd6dc3d3c349d83990b76b7ac9af6ba21ed137f6cf8c8f8e7d
+size 12932

runs/May30_18-03-06_one/events.out.tfevents.1717060072.one.682896.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb88f2d0463ec79835120cb246057e289fe1b3b00dde250225ef50956cff31d
+size 359

runs/May30_18-39-39_one/events.out.tfevents.1717061980.one.682896.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330a9d06583aca1e0fdf7235c99b7eb40d5c8f2af779a7d648660bb40f876606
+size 10522

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672ffb824bcbf81435d9c4bc302b7f87aa44e25357c55d24606e67c9b82340f7
+size 5048