End of training

README.md

@@ -0,0 +1,87 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/mit-b5
+tags:
+- generated_from_trainer
+model-index:
+- name: segformer-b5-finetuned-ce-head-batch3
+  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. -->
+
+# segformer-b5-finetuned-ce-head-batch3
+
+This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0484
+- Mean Iou: 0.7855
+- Mean Accuracy: 0.8702
+- Overall Accuracy: 0.9817
+- Accuracy Bg: 0.9901
+- Accuracy Head: 0.7502
+- Iou Bg: 0.9813
+- Iou Head: 0.5898
+
+## 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: 7e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- 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
+- num_epochs: 70
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bg | Accuracy Head | Iou Bg | Iou Head |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------:|:-------------:|:------:|:--------:|
+| 0.0876        | 2.9412  | 100  | 0.1714          | 0.5435   | 0.5758        | 0.9405           | 0.9958      | 0.1558        | 0.9399 | 0.1470   |
+| 0.0951        | 5.8824  | 200  | 0.1202          | 0.6651   | 0.7254        | 0.9511           | 0.9845      | 0.4663        | 0.9495 | 0.3806   |
+| 0.1451        | 8.8235  | 300  | 0.1209          | 0.6300   | 0.6751        | 0.9494           | 0.9893      | 0.3609        | 0.9482 | 0.3118   |
+| 0.063         | 11.7647 | 400  | 0.1074          | 0.7226   | 0.8202        | 0.9558           | 0.9758      | 0.6646        | 0.9539 | 0.4914   |
+| 0.0953        | 14.7059 | 500  | 0.1201          | 0.7233   | 0.8482        | 0.9499           | 0.9660      | 0.7303        | 0.9472 | 0.4994   |
+| 0.0207        | 17.6471 | 600  | 0.0978          | 0.7365   | 0.8236        | 0.9595           | 0.9796      | 0.6677        | 0.9577 | 0.5152   |
+| 0.0661        | 20.5882 | 700  | 0.0953          | 0.7259   | 0.8130        | 0.9571           | 0.9788      | 0.6473        | 0.9552 | 0.4965   |
+| 0.0529        | 23.5294 | 800  | 0.1145          | 0.6774   | 0.7373        | 0.9540           | 0.9854      | 0.4891        | 0.9525 | 0.4022   |
+| 0.0848        | 26.4706 | 900  | 0.0920          | 0.7487   | 0.8337        | 0.9618           | 0.9808      | 0.6866        | 0.9600 | 0.5375   |
+| 0.0083        | 29.4118 | 1000 | 0.0885          | 0.7336   | 0.8120        | 0.9611           | 0.9824      | 0.6417        | 0.9594 | 0.5078   |
+| 0.0279        | 32.3529 | 1100 | 0.0913          | 0.7459   | 0.8473        | 0.9603           | 0.9767      | 0.7180        | 0.9584 | 0.5334   |
+| 0.0392        | 35.2941 | 1200 | 0.0829          | 0.7682   | 0.8687        | 0.9645           | 0.9783      | 0.7591        | 0.9627 | 0.5737   |
+| 0.0761        | 38.2353 | 1300 | 0.0840          | 0.7557   | 0.8481        | 0.9618           | 0.9789      | 0.7174        | 0.9599 | 0.5516   |
+| 0.0111        | 41.1765 | 1400 | 0.0998          | 0.7424   | 0.8462        | 0.9580           | 0.9749      | 0.7174        | 0.9560 | 0.5288   |
+| 0.0175        | 44.1176 | 1500 | 0.0872          | 0.7665   | 0.8729        | 0.9642           | 0.9771      | 0.7687        | 0.9624 | 0.5705   |
+| 0.0599        | 47.0588 | 1600 | 0.1016          | 0.7394   | 0.8313        | 0.9596           | 0.9785      | 0.6842        | 0.9577 | 0.5212   |
+| 0.0329        | 50.0    | 1700 | 0.0978          | 0.7421   | 0.8439        | 0.9587           | 0.9758      | 0.7120        | 0.9567 | 0.5275   |
+| 0.0344        | 52.9412 | 1800 | 0.1044          | 0.7500   | 0.8598        | 0.9590           | 0.9739      | 0.7456        | 0.9569 | 0.5432   |
+| 0.0372        | 55.8824 | 1900 | 0.1060          | 0.7207   | 0.7969        | 0.9596           | 0.9825      | 0.6113        | 0.9580 | 0.4835   |
+| 0.015         | 58.8235 | 2000 | 0.1043          | 0.7427   | 0.8451        | 0.9585           | 0.9755      | 0.7146        | 0.9564 | 0.5291   |
+| 0.0558        | 61.7647 | 2100 | 0.1009          | 0.7574   | 0.8694        | 0.9608           | 0.9743      | 0.7645        | 0.9587 | 0.5561   |
+| 0.0074        | 64.7059 | 2200 | 0.1108          | 0.7282   | 0.8279        | 0.9554           | 0.9749      | 0.6810        | 0.9533 | 0.5032   |
+| 0.0186        | 67.6471 | 2300 | 0.1162          | 0.7290   | 0.8447        | 0.9543           | 0.9707      | 0.7187        | 0.9520 | 0.5060   |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "nvidia/mit-b5",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 768,
+  "depths": [
+    3,
+    6,
+    40,
+    3
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "id2label": {
+    "0": "bg",
+    "1": "head"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "bg": 0,
+    "head": 1
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd036d193e3e74ea52148d55213806360118223e416e5a8c362695a8c4f8e6a
+size 338528440

runs/Jan16_14-49-34_administrator-Precision-3591/events.out.tfevents.1737035375.administrator-Precision-3591.1140174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c39f88338597cd592219856b6788992bf1136cf7a44ceea4d1f9574166a949f
+size 522644

runs/Jan16_14-49-34_administrator-Precision-3591/events.out.tfevents.1737037309.administrator-Precision-3591.1140174.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6c4734b52fd7879ae4283a560a39289c5f93337a2c270551523e149e90322f
+size 742

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72fca7a25c568c40a3a8620db11e22b84704619b8d5498fba300a32963e0fdf5
+size 5304