best_model.pt

README.md

@@ -0,0 +1,48 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## 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: 8
+- eval_batch_size: 8
+- 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: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1
+- Datasets 2.21.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "UNETForSegmentation"
+  ],
+  "attention_type": "sdpa",
+  "dim": 224,
+  "dual_obj": false,
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "img_size": 512,
+  "intermediate_size": 1024,
+  "is_causal": false,
+  "k": 2,
+  "max_position_embeddings": 4096,
+  "model_type": "Unet",
+  "moe": false,
+  "n_filts": 3,
+  "num_attention_heads": 8,
+  "num_channels": 3,
+  "num_classes": 2,
+  "num_experts": 8,
+  "num_hidden_layers": 6,
+  "num_layers": 2,
+  "output_router_logits": true,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "router_aux_loss_coef": 0.01,
+  "t": 2,
+  "topk": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cff34c07c75dbc8c2df95f57982d42954672b5ed1299a32decc3a31500ac774
+size 1240512

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f930ba8bf59e0bb0d795407b6406bfed5f8e33e057ceaeb28c46fa61dfd721c2
+size 5240