End of training

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: rlcc-new-aroma-upsample_replacement-aspect_classifier
+  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. -->
+
+# rlcc-new-aroma-upsample_replacement-aspect_classifier
+
+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: 1.5190
+- Accuracy: 0.4549
+- F1 Macro: 0.4173
+- Precision Macro: 0.4299
+- Recall Macro: 0.4139
+- F1 Micro: 0.4549
+- Precision Micro: 0.4549
+- Recall Micro: 0.4549
+- Total Tf: [116, 139, 371, 139]
+
+## 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: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 40
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | F1 Micro | Precision Micro | Recall Micro | Total Tf             |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------------------:|
+| 1.1063        | 1.0   | 41   | 1.1152          | 0.2588   | 0.1736   | 0.3440          | 0.3490       | 0.2588   | 0.2588          | 0.2588       | [66, 189, 321, 189]  |
+| 1.0222        | 2.0   | 82   | 1.1515          | 0.2980   | 0.2990   | 0.3347          | 0.3179       | 0.2980   | 0.2980          | 0.2980       | [76, 179, 331, 179]  |
+| 0.8089        | 3.0   | 123  | 1.1543          | 0.4      | 0.3963   | 0.3976          | 0.4065       | 0.4000   | 0.4             | 0.4          | [102, 153, 357, 153] |
+| 0.6457        | 4.0   | 164  | 1.1887          | 0.4549   | 0.4204   | 0.4207          | 0.4293       | 0.4549   | 0.4549          | 0.4549       | [116, 139, 371, 139] |
+| 0.4898        | 5.0   | 205  | 1.2712          | 0.4471   | 0.4351   | 0.4419          | 0.4361       | 0.4471   | 0.4471          | 0.4471       | [114, 141, 369, 141] |
+| 0.3316        | 6.0   | 246  | 1.4476          | 0.4471   | 0.4220   | 0.4353          | 0.4177       | 0.4471   | 0.4471          | 0.4471       | [114, 141, 369, 141] |
+| 0.2647        | 7.0   | 287  | 1.5190          | 0.4549   | 0.4173   | 0.4299          | 0.4139       | 0.4549   | 0.4549          | 0.4549       | [116, 139, 371, 139] |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,10 @@
+{
+  "architectures": [
+    "BERTModel"
+  ],
+  "class_weight": null,
+  "model_type": "bert",
+  "num_classes": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99323a5081e15414e58f01188fc9d3c3479c0c3a6b349f24f177632bf7490998
+size 437963716

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54de6b45f56e7b625922fcf751e1f33ae61fdde2add2fbc8e1a28020e974f873
+size 5368