initial commit

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.9617271835132484,
+    "eval_loss": 0.11346353590488434,
+    "eval_runtime": 12.3823,
+    "eval_samples_per_second": 80.761,
+    "eval_steps_per_second": 10.095,
+    "train_loss": 0.20243481533847807,
+    "train_runtime": 2207.1281,
+    "train_samples_per_second": 24.466,
+    "train_steps_per_second": 0.765
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "diffusion-detection",
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_indices": [
+    3,
+    5,
+    7,
+    11
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "problem_type": "single_label_classification",
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_mask_token": true,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": false,
+  "use_shared_relative_position_bias": true,
+  "vocab_size": 8192
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.9617271835132484,
+    "eval_loss": 0.11346353590488434,
+    "eval_runtime": 12.3823,
+    "eval_samples_per_second": 80.761,
+    "eval_steps_per_second": 10.095
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "BeitFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "BeitImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca49ae14f393414cabd82707f498157a8a793e8cdedae766e6169edd54203b0
+size 343051797

runs/Jun22_13-42-13_DESKTOP-3GG4RF1/1687434133.5090237/events.out.tfevents.1687434133.DESKTOP-3GG4RF1.16212.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d721d083565a790497d15f5ab3c97b32121d3984efdbc2b36c005e401ff0340c
+size 5881

runs/Jun22_13-42-13_DESKTOP-3GG4RF1/events.out.tfevents.1687434133.DESKTOP-3GG4RF1.16212.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c7e3567a2459ed732b97813dc4b97788e530a795db2709e2c1c324cee6e031
+size 16291

runs/Jun22_13-42-13_DESKTOP-3GG4RF1/events.out.tfevents.1687436353.DESKTOP-3GG4RF1.16212.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35470df45ae1beb212aa0412e0b643e18947d6b952d809d239daf861b54e9c49
+size 357

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.20243481533847807,
+    "train_runtime": 2207.1281,
+    "train_samples_per_second": 24.466,
+    "train_steps_per_second": 0.765
+}

trainer_state.json

@@ -0,0 +1,352 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 0.7526,
+      "step": 1
+    },
+    {
+      "epoch": 0.09,
+      "eval_f1": 0.7867768595041322,
+      "eval_loss": 0.501287043094635,
+      "eval_runtime": 111.669,
+      "eval_samples_per_second": 8.955,
+      "eval_steps_per_second": 1.119,
+      "step": 48
+    },
+    {
+      "epoch": 0.17,
+      "eval_f1": 0.731527093596059,
+      "eval_loss": 0.45942792296409607,
+      "eval_runtime": 14.4836,
+      "eval_samples_per_second": 69.044,
+      "eval_steps_per_second": 8.63,
+      "step": 96
+    },
+    {
+      "epoch": 0.26,
+      "eval_f1": 0.768503937007874,
+      "eval_loss": 0.6004758477210999,
+      "eval_runtime": 13.7722,
+      "eval_samples_per_second": 72.61,
+      "eval_steps_per_second": 9.076,
+      "step": 144
+    },
+    {
+      "epoch": 0.34,
+      "eval_f1": 0.8773784355179703,
+      "eval_loss": 0.293561190366745,
+      "eval_runtime": 16.0256,
+      "eval_samples_per_second": 62.4,
+      "eval_steps_per_second": 7.8,
+      "step": 192
+    },
+    {
+      "epoch": 0.43,
+      "eval_f1": 0.8644444444444445,
+      "eval_loss": 0.3103949725627899,
+      "eval_runtime": 13.1537,
+      "eval_samples_per_second": 76.024,
+      "eval_steps_per_second": 9.503,
+      "step": 240
+    },
+    {
+      "epoch": 0.51,
+      "eval_f1": 0.903353057199211,
+      "eval_loss": 0.2314113825559616,
+      "eval_runtime": 13.9609,
+      "eval_samples_per_second": 71.629,
+      "eval_steps_per_second": 8.954,
+      "step": 288
+    },
+    {
+      "epoch": 0.6,
+      "eval_f1": 0.904950495049505,
+      "eval_loss": 0.23260511457920074,
+      "eval_runtime": 10.3047,
+      "eval_samples_per_second": 97.043,
+      "eval_steps_per_second": 12.13,
+      "step": 336
+    },
+    {
+      "epoch": 0.68,
+      "eval_f1": 0.8210526315789474,
+      "eval_loss": 0.39369526505470276,
+      "eval_runtime": 13.155,
+      "eval_samples_per_second": 76.017,
+      "eval_steps_per_second": 9.502,
+      "step": 384
+    },
+    {
+      "epoch": 0.77,
+      "eval_f1": 0.9147609147609148,
+      "eval_loss": 0.20550310611724854,
+      "eval_runtime": 45.6928,
+      "eval_samples_per_second": 21.885,
+      "eval_steps_per_second": 2.736,
+      "step": 432
+    },
+    {
+      "epoch": 0.85,
+      "eval_f1": 0.8367816091954022,
+      "eval_loss": 0.3017582893371582,
+      "eval_runtime": 22.6976,
+      "eval_samples_per_second": 44.057,
+      "eval_steps_per_second": 5.507,
+      "step": 480
+    },
+    {
+      "epoch": 0.94,
+      "eval_f1": 0.9271653543307087,
+      "eval_loss": 0.19784249365329742,
+      "eval_runtime": 12.076,
+      "eval_samples_per_second": 82.809,
+      "eval_steps_per_second": 10.351,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "eval_f1": 0.9368104312938816,
+      "eval_loss": 0.17989766597747803,
+      "eval_runtime": 49.8486,
+      "eval_samples_per_second": 20.061,
+      "eval_steps_per_second": 2.508,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "eval_f1": 0.895424836601307,
+      "eval_loss": 0.23422278463840485,
+      "eval_runtime": 11.6376,
+      "eval_samples_per_second": 85.928,
+      "eval_steps_per_second": 10.741,
+      "step": 624
+    },
+    {
+      "epoch": 1.19,
+      "eval_f1": 0.9256360078277887,
+      "eval_loss": 0.22150222957134247,
+      "eval_runtime": 11.4494,
+      "eval_samples_per_second": 87.341,
+      "eval_steps_per_second": 10.918,
+      "step": 672
+    },
+    {
+      "epoch": 1.28,
+      "eval_f1": 0.9051724137931034,
+      "eval_loss": 0.22654065489768982,
+      "eval_runtime": 11.6176,
+      "eval_samples_per_second": 86.076,
+      "eval_steps_per_second": 10.76,
+      "step": 720
+    },
+    {
+      "epoch": 1.36,
+      "eval_f1": 0.9389389389389389,
+      "eval_loss": 0.1583857387304306,
+      "eval_runtime": 15.3861,
+      "eval_samples_per_second": 64.994,
+      "eval_steps_per_second": 8.124,
+      "step": 768
+    },
+    {
+      "epoch": 1.45,
+      "eval_f1": 0.921487603305785,
+      "eval_loss": 0.22388193011283875,
+      "eval_runtime": 14.1559,
+      "eval_samples_per_second": 70.642,
+      "eval_steps_per_second": 8.83,
+      "step": 816
+    },
+    {
+      "epoch": 1.53,
+      "eval_f1": 0.9282868525896415,
+      "eval_loss": 0.1805724799633026,
+      "eval_runtime": 11.7527,
+      "eval_samples_per_second": 85.087,
+      "eval_steps_per_second": 10.636,
+      "step": 864
+    },
+    {
+      "epoch": 1.62,
+      "eval_f1": 0.8998899889988998,
+      "eval_loss": 0.22186490893363953,
+      "eval_runtime": 11.5055,
+      "eval_samples_per_second": 86.915,
+      "eval_steps_per_second": 10.864,
+      "step": 912
+    },
+    {
+      "epoch": 1.71,
+      "eval_f1": 0.9466263846928499,
+      "eval_loss": 0.15720757842063904,
+      "eval_runtime": 11.3153,
+      "eval_samples_per_second": 88.376,
+      "eval_steps_per_second": 11.047,
+      "step": 960
+    },
+    {
+      "epoch": 1.79,
+      "eval_f1": 0.9457523029682703,
+      "eval_loss": 0.15362103283405304,
+      "eval_runtime": 11.6626,
+      "eval_samples_per_second": 85.744,
+      "eval_steps_per_second": 10.718,
+      "step": 1008
+    },
+    {
+      "epoch": 1.88,
+      "eval_f1": 0.9403714565004888,
+      "eval_loss": 0.15603256225585938,
+      "eval_runtime": 11.4304,
+      "eval_samples_per_second": 87.486,
+      "eval_steps_per_second": 10.936,
+      "step": 1056
+    },
+    {
+      "epoch": 1.96,
+      "eval_f1": 0.9567901234567902,
+      "eval_loss": 0.13539032638072968,
+      "eval_runtime": 11.6426,
+      "eval_samples_per_second": 85.891,
+      "eval_steps_per_second": 10.736,
+      "step": 1104
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.714031971580817e-05,
+      "loss": 0.2638,
+      "step": 1125
+    },
+    {
+      "epoch": 2.05,
+      "eval_f1": 0.9402390438247011,
+      "eval_loss": 0.2028977870941162,
+      "eval_runtime": 11.4905,
+      "eval_samples_per_second": 87.029,
+      "eval_steps_per_second": 10.879,
+      "step": 1152
+    },
+    {
+      "epoch": 2.13,
+      "eval_f1": 0.9477911646586347,
+      "eval_loss": 0.158633291721344,
+      "eval_runtime": 11.6696,
+      "eval_samples_per_second": 85.693,
+      "eval_steps_per_second": 10.712,
+      "step": 1200
+    },
+    {
+      "epoch": 2.22,
+      "eval_f1": 0.9363920750782065,
+      "eval_loss": 0.16604219377040863,
+      "eval_runtime": 11.6366,
+      "eval_samples_per_second": 85.936,
+      "eval_steps_per_second": 10.742,
+      "step": 1248
+    },
+    {
+      "epoch": 2.3,
+      "eval_f1": 0.946611909650924,
+      "eval_loss": 0.16741609573364258,
+      "eval_runtime": 11.5595,
+      "eval_samples_per_second": 86.509,
+      "eval_steps_per_second": 10.814,
+      "step": 1296
+    },
+    {
+      "epoch": 2.39,
+      "eval_f1": 0.9566094853683148,
+      "eval_loss": 0.15039804577827454,
+      "eval_runtime": 11.5775,
+      "eval_samples_per_second": 86.374,
+      "eval_steps_per_second": 10.797,
+      "step": 1344
+    },
+    {
+      "epoch": 2.47,
+      "eval_f1": 0.9386892177589852,
+      "eval_loss": 0.1896335780620575,
+      "eval_runtime": 11.4785,
+      "eval_samples_per_second": 87.12,
+      "eval_steps_per_second": 10.89,
+      "step": 1392
+    },
+    {
+      "epoch": 2.56,
+      "eval_f1": 0.9516129032258065,
+      "eval_loss": 0.1552370935678482,
+      "eval_runtime": 11.6346,
+      "eval_samples_per_second": 85.951,
+      "eval_steps_per_second": 10.744,
+      "step": 1440
+    },
+    {
+      "epoch": 2.64,
+      "eval_f1": 0.9494949494949494,
+      "eval_loss": 0.17198829352855682,
+      "eval_runtime": 11.4094,
+      "eval_samples_per_second": 87.647,
+      "eval_steps_per_second": 10.956,
+      "step": 1488
+    },
+    {
+      "epoch": 2.73,
+      "eval_f1": 0.9596774193548386,
+      "eval_loss": 0.14362381398677826,
+      "eval_runtime": 13.3792,
+      "eval_samples_per_second": 74.743,
+      "eval_steps_per_second": 9.343,
+      "step": 1536
+    },
+    {
+      "epoch": 2.81,
+      "eval_f1": 0.9530469530469531,
+      "eval_loss": 0.15035580098628998,
+      "eval_runtime": 12.9698,
+      "eval_samples_per_second": 77.102,
+      "eval_steps_per_second": 9.638,
+      "step": 1584
+    },
+    {
+      "epoch": 2.9,
+      "eval_f1": 0.9538461538461538,
+      "eval_loss": 0.1516994833946228,
+      "eval_runtime": 11.9429,
+      "eval_samples_per_second": 83.732,
+      "eval_steps_per_second": 10.466,
+      "step": 1632
+    },
+    {
+      "epoch": 2.98,
+      "eval_f1": 0.9538461538461538,
+      "eval_loss": 0.15105971693992615,
+      "eval_runtime": 13.9387,
+      "eval_samples_per_second": 71.743,
+      "eval_steps_per_second": 8.968,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0,
+      "step": 1689,
+      "total_flos": 4.178103906557952e+18,
+      "train_loss": 0.20243481533847807,
+      "train_runtime": 2207.1281,
+      "train_samples_per_second": 24.466,
+      "train_steps_per_second": 0.765
+    }
+  ],
+  "max_steps": 1689,
+  "num_train_epochs": 3,
+  "total_flos": 4.178103906557952e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a641abce807644e204c8c82075dd05c499575409b8d42ac15dc0273ce115f69
+size 3887