End of training

README.md

@@ -0,0 +1,47 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: paper-cutting
+  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. -->
+
+# paper-cutting
+
+This model was trained from scratch 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: 6e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.0
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "/kaggle/working/paper-cutting-outputs/checkpoint-640",
+  "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": "N/A",
+    "1": "content"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "N/A": 0,
+    "content": 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": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a53e408066dd599cddd3abc4b3400ca14dca2e26468c844df49960bede7bec
+size 338528440

runs/Oct30_07-26-21_0229da561a22/events.out.tfevents.1730273185.0229da561a22.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46e1f7d573682e1fd7e5ad0590e1b54aa6ba15d7d498ec86f81ae2d11cdf22f
+size 5413

runs/Oct30_07-26-58_0229da561a22/events.out.tfevents.1730273219.0229da561a22.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2d93620cc6b1fc8cfa8e1745b444fe6b3ff55882d7c02149874c43a5c7cc35
+size 5413

runs/Oct30_07-27-22_0229da561a22/events.out.tfevents.1730273244.0229da561a22.30.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6dbd170256af4e5676d9206c60bced6b3a4b793aa8427514a460eb4cd6dc7e
+size 159155

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c771328ea0df92b83c2f7e9ee318c1a10515ccdf40845810f5de88e4727e0624
+size 5240