End of training

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/mit-b5
+tags:
+- generated_from_trainer
+model-index:
+- name: segformer-b5-finetuned-ce-head-batch2
+  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-batch2
+
+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: 0.0642
+- Mean Iou: 0.7275
+- Mean Accuracy: 0.7749
+- Overall Accuracy: 0.9755
+- Accuracy Bg: 0.9932
+- Accuracy Head: 0.5565
+- Iou Bg: 0.9749
+- Iou Head: 0.4800
+
+## 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: 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: 50
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bg | Accuracy Head | Iou Bg | Iou Head |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------:|:-------------:|:------:|:--------:|
+| 0.0924        | 2.9412  | 100  | 0.1445          | 0.5230   | 0.5477        | 0.9551           | 0.9953      | 0.1001        | 0.9549 | 0.0911   |
+| 0.038         | 5.8824  | 200  | 0.1100          | 0.6241   | 0.6601        | 0.9624           | 0.9931      | 0.3270        | 0.9618 | 0.2864   |
+| 0.2087        | 8.8235  | 300  | 0.0979          | 0.6317   | 0.6714        | 0.9637           | 0.9922      | 0.3506        | 0.9631 | 0.3003   |
+| 0.0562        | 11.7647 | 400  | 0.0911          | 0.6638   | 0.7059        | 0.9657           | 0.9923      | 0.4195        | 0.9651 | 0.3625   |
+| 0.0168        | 14.7059 | 500  | 0.0847          | 0.7076   | 0.7652        | 0.9702           | 0.9902      | 0.5403        | 0.9695 | 0.4457   |
+| 0.0361        | 17.6471 | 600  | 0.0887          | 0.6908   | 0.7392        | 0.9692           | 0.9917      | 0.4867        | 0.9685 | 0.4131   |
+| 0.0594        | 20.5882 | 700  | 0.0848          | 0.6898   | 0.7275        | 0.9704           | 0.9942      | 0.4608        | 0.9698 | 0.4098   |
+| 0.1344        | 23.5294 | 800  | 0.0868          | 0.6944   | 0.7533        | 0.9686           | 0.9894      | 0.5172        | 0.9679 | 0.4209   |
+| 0.0662        | 26.4706 | 900  | 0.0781          | 0.7395   | 0.8269        | 0.9710           | 0.9852      | 0.6686        | 0.9701 | 0.5088   |
+| 0.0178        | 29.4118 | 1000 | 0.0778          | 0.7290   | 0.7982        | 0.9717           | 0.9885      | 0.6079        | 0.9709 | 0.4870   |
+| 0.0092        | 32.3529 | 1100 | 0.0789          | 0.7424   | 0.8153        | 0.9729           | 0.9882      | 0.6424        | 0.9721 | 0.5128   |
+| 0.0684        | 35.2941 | 1200 | 0.0822          | 0.7163   | 0.7700        | 0.9717           | 0.9913      | 0.5487        | 0.9710 | 0.4615   |
+| 0.0969        | 38.2353 | 1300 | 0.0794          | 0.7225   | 0.7807        | 0.9711           | 0.9903      | 0.5711        | 0.9704 | 0.4746   |
+| 0.0224        | 41.1765 | 1400 | 0.0874          | 0.7026   | 0.7476        | 0.9699           | 0.9926      | 0.5026        | 0.9692 | 0.4360   |
+| 0.0549        | 44.1176 | 1500 | 0.0754          | 0.7357   | 0.7990        | 0.9730           | 0.9899      | 0.6082        | 0.9722 | 0.4991   |
+| 0.0728        | 47.0588 | 1600 | 0.0807          | 0.7120   | 0.7582        | 0.9711           | 0.9926      | 0.5238        | 0.9703 | 0.4536   |
+| 0.105         | 50.0    | 1700 | 0.0806          | 0.7059   | 0.7603        | 0.9703           | 0.9908      | 0.5298        | 0.9696 | 0.4422   |
+
+
+### 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 sha256:3f9c085511f195107eb1e5f5776fd4b5d0f6e53d1a85b234fc6549b5916664fe
+size 338528440

runs/Jan16_12-00-58_administrator-Precision-3591/events.out.tfevents.1737025260.administrator-Precision-3591.1090796.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9337c2f8c42579521d2bebc165fd1b9be675ee93923ea993eb36fb061227ec3
+size 11295

runs/Jan16_12-03-34_administrator-Precision-3591/events.out.tfevents.1737025415.administrator-Precision-3591.1092176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ea7d7b505339cf3f95b1ad323f3d6f42d34969b2003b5f2ab723e29c6febc2
+size 375240

runs/Jan16_12-03-34_administrator-Precision-3591/events.out.tfevents.1737026746.administrator-Precision-3591.1092176.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bbb383cc19893a2020531c8840690e06310c4764325e24874f0eb194e3e6c1
+size 742

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a80d7d69b1aa4758858027bc74618d9a4b766300c0a1205935a514639ee95fa
+size 5304