Training in progress, epoch 4, checkpoint

checkpoint-428/config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "microsoft/conditional-detr-resnet-50",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "ConditionalDetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 2,
+  "cls_loss_coefficient": 2,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "Coverall",
+    "1": "Face_Shield",
+    "2": "Gloves",
+    "3": "Goggles",
+    "4": "Mask"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Coverall": 0,
+    "Face_Shield": 1,
+    "Gloves": 2,
+    "Goggles": 3,
+    "Mask": 4
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "conditional_detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 300,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2f56f3200f892aed58460b8feffb7c6059ade19b73f86ae4c58c72cec7fc33
+size 174079796

checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5aba889ca31c8a056d7ce11b7900c10f52b5a72bb781289bff32e24161caa2
+size 345687577

checkpoint-428/preprocessor_config.json

@@ -0,0 +1,47 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "annotations",
+    "return_segmentation_masks",
+    "masks_path",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "do_convert_annotations",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "pad_size",
+    "format",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": false,
+  "do_rescale": true,
+  "do_resize": false,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConditionalDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a456936ba2bc9398550d77a4643e0370b286007573cc73fa1928238d019acc87
+size 13990

checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f996f952c685f2fb6e9fc74f1b64d0db503447a168442b4ef12dc0894f87c1
+size 1064

checkpoint-428/trainer_state.json

@@ -0,0 +1,273 @@
+{
+  "best_metric": 0.0149,
+  "best_model_checkpoint": "test_detr_finetuned_cppe5/checkpoint-428",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 107,
+      "train_loss": 3.0001344680786133,
+      "train_map": 0.0047,
+      "train_map_50": 0.0176,
+      "train_map_75": 0.0014,
+      "train_map_Coverall": 0.0232,
+      "train_map_Face_Shield": 0.0,
+      "train_map_Gloves": 0.0001,
+      "train_map_Goggles": 0.0,
+      "train_map_Mask": 0.0004,
+      "train_map_large": 0.0049,
+      "train_map_medium": 0.0002,
+      "train_map_small": 0.0016,
+      "train_mar_1": 0.0108,
+      "train_mar_10": 0.0458,
+      "train_mar_100": 0.0837,
+      "train_mar_100_Coverall": 0.3473,
+      "train_mar_100_Face_Shield": 0.0,
+      "train_mar_100_Gloves": 0.0145,
+      "train_mar_100_Goggles": 0.0,
+      "train_mar_100_Mask": 0.0567,
+      "train_mar_large": 0.0731,
+      "train_mar_medium": 0.0246,
+      "train_mar_small": 0.0013,
+      "train_runtime": 83.8338,
+      "train_samples_per_second": 10.139,
+      "train_steps_per_second": 1.276
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.0698611736297607,
+      "eval_map": 0.0038,
+      "eval_map_50": 0.0126,
+      "eval_map_75": 0.0008,
+      "eval_map_Coverall": 0.0183,
+      "eval_map_Face_Shield": 0.0,
+      "eval_map_Gloves": 0.0002,
+      "eval_map_Goggles": 0.0,
+      "eval_map_Mask": 0.0004,
+      "eval_map_large": 0.0044,
+      "eval_map_medium": 0.0002,
+      "eval_map_small": 0.0022,
+      "eval_mar_1": 0.0063,
+      "eval_mar_10": 0.0308,
+      "eval_mar_100": 0.0561,
+      "eval_mar_100_Coverall": 0.2185,
+      "eval_mar_100_Face_Shield": 0.0,
+      "eval_mar_100_Gloves": 0.0156,
+      "eval_mar_100_Goggles": 0.0,
+      "eval_mar_100_Mask": 0.0462,
+      "eval_mar_large": 0.05,
+      "eval_mar_medium": 0.0266,
+      "eval_mar_small": 0.0022,
+      "eval_runtime": 43.5223,
+      "eval_samples_per_second": 3.447,
+      "eval_steps_per_second": 0.437,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "step": 214,
+      "train_loss": 2.964989423751831,
+      "train_map": 0.0073,
+      "train_map_50": 0.0272,
+      "train_map_75": 0.0018,
+      "train_map_Coverall": 0.0358,
+      "train_map_Face_Shield": 0.0,
+      "train_map_Gloves": 0.0002,
+      "train_map_Goggles": 0.0,
+      "train_map_Mask": 0.0005,
+      "train_map_large": 0.0075,
+      "train_map_medium": 0.0002,
+      "train_map_small": 0.0018,
+      "train_mar_1": 0.0107,
+      "train_mar_10": 0.045,
+      "train_mar_100": 0.0775,
+      "train_mar_100_Coverall": 0.2974,
+      "train_mar_100_Face_Shield": 0.0,
+      "train_mar_100_Gloves": 0.0302,
+      "train_mar_100_Goggles": 0.0,
+      "train_mar_100_Mask": 0.06,
+      "train_mar_large": 0.0627,
+      "train_mar_medium": 0.0311,
+      "train_mar_small": 0.0012,
+      "train_runtime": 86.7545,
+      "train_samples_per_second": 9.798,
+      "train_steps_per_second": 1.233
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.0518693923950195,
+      "eval_map": 0.0042,
+      "eval_map_50": 0.0172,
+      "eval_map_75": 0.0009,
+      "eval_map_Coverall": 0.0203,
+      "eval_map_Face_Shield": 0.0,
+      "eval_map_Gloves": 0.0003,
+      "eval_map_Goggles": 0.0,
+      "eval_map_Mask": 0.0004,
+      "eval_map_large": 0.0046,
+      "eval_map_medium": 0.0003,
+      "eval_map_small": 0.0005,
+      "eval_mar_1": 0.0064,
+      "eval_mar_10": 0.0308,
+      "eval_mar_100": 0.0561,
+      "eval_mar_100_Coverall": 0.2045,
+      "eval_mar_100_Face_Shield": 0.0,
+      "eval_mar_100_Gloves": 0.0339,
+      "eval_mar_100_Goggles": 0.0,
+      "eval_mar_100_Mask": 0.0422,
+      "eval_mar_large": 0.0468,
+      "eval_mar_medium": 0.0333,
+      "eval_mar_small": 0.0004,
+      "eval_runtime": 41.1994,
+      "eval_samples_per_second": 3.641,
+      "eval_steps_per_second": 0.461,
+      "step": 214
+    },
+    {
+      "epoch": 3.0,
+      "step": 321,
+      "train_loss": 2.9912493228912354,
+      "train_map": 0.0034,
+      "train_map_50": 0.0129,
+      "train_map_75": 0.0014,
+      "train_map_Coverall": 0.0166,
+      "train_map_Face_Shield": 0.0003,
+      "train_map_Gloves": 0.0,
+      "train_map_Goggles": 0.0,
+      "train_map_Mask": 0.0003,
+      "train_map_large": 0.0039,
+      "train_map_medium": 0.0001,
+      "train_map_small": 0.0028,
+      "train_mar_1": 0.0112,
+      "train_mar_10": 0.0458,
+      "train_mar_100": 0.0675,
+      "train_mar_100_Coverall": 0.2772,
+      "train_mar_100_Face_Shield": 0.004,
+      "train_mar_100_Gloves": 0.014,
+      "train_mar_100_Goggles": 0.0,
+      "train_mar_100_Mask": 0.0425,
+      "train_mar_large": 0.0589,
+      "train_mar_medium": 0.02,
+      "train_mar_small": 0.0021,
+      "train_runtime": 80.1813,
+      "train_samples_per_second": 10.601,
+      "train_steps_per_second": 1.334
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.0276060104370117,
+      "eval_map": 0.0029,
+      "eval_map_50": 0.0113,
+      "eval_map_75": 0.0007,
+      "eval_map_Coverall": 0.0137,
+      "eval_map_Face_Shield": 0.0003,
+      "eval_map_Gloves": 0.0,
+      "eval_map_Goggles": 0.0,
+      "eval_map_Mask": 0.0003,
+      "eval_map_large": 0.0031,
+      "eval_map_medium": 0.0002,
+      "eval_map_small": 0.001,
+      "eval_mar_1": 0.0057,
+      "eval_mar_10": 0.0326,
+      "eval_mar_100": 0.0506,
+      "eval_mar_100_Coverall": 0.2108,
+      "eval_mar_100_Face_Shield": 0.0063,
+      "eval_mar_100_Gloves": 0.0058,
+      "eval_mar_100_Goggles": 0.0,
+      "eval_mar_100_Mask": 0.0302,
+      "eval_mar_large": 0.0482,
+      "eval_mar_medium": 0.0184,
+      "eval_mar_small": 0.0009,
+      "eval_runtime": 49.8337,
+      "eval_samples_per_second": 3.01,
+      "eval_steps_per_second": 0.381,
+      "step": 321
+    },
+    {
+      "epoch": 4.0,
+      "step": 428,
+      "train_loss": 2.774980068206787,
+      "train_map": 0.0215,
+      "train_map_50": 0.0526,
+      "train_map_75": 0.0145,
+      "train_map_Coverall": 0.1068,
+      "train_map_Face_Shield": 0.0003,
+      "train_map_Gloves": 0.0001,
+      "train_map_Goggles": 0.0,
+      "train_map_Mask": 0.0003,
+      "train_map_large": 0.0226,
+      "train_map_medium": 0.0001,
+      "train_map_small": 0.0025,
+      "train_mar_1": 0.0295,
+      "train_mar_10": 0.08,
+      "train_mar_100": 0.106,
+      "train_mar_100_Coverall": 0.431,
+      "train_mar_100_Face_Shield": 0.0397,
+      "train_mar_100_Gloves": 0.0193,
+      "train_mar_100_Goggles": 0.0,
+      "train_mar_100_Mask": 0.0401,
+      "train_mar_large": 0.1015,
+      "train_mar_medium": 0.0255,
+      "train_mar_small": 0.005,
+      "train_runtime": 75.8168,
+      "train_samples_per_second": 11.211,
+      "train_steps_per_second": 1.411
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.858452558517456,
+      "eval_map": 0.0149,
+      "eval_map_50": 0.0389,
+      "eval_map_75": 0.0106,
+      "eval_map_Coverall": 0.0739,
+      "eval_map_Face_Shield": 0.0001,
+      "eval_map_Gloves": 0.0,
+      "eval_map_Goggles": 0.0,
+      "eval_map_Mask": 0.0005,
+      "eval_map_large": 0.0169,
+      "eval_map_medium": 0.0001,
+      "eval_map_small": 0.003,
+      "eval_mar_1": 0.018,
+      "eval_mar_10": 0.051,
+      "eval_mar_100": 0.0751,
+      "eval_mar_100_Coverall": 0.3243,
+      "eval_mar_100_Face_Shield": 0.0063,
+      "eval_mar_100_Gloves": 0.0098,
+      "eval_mar_100_Goggles": 0.0,
+      "eval_mar_100_Mask": 0.0351,
+      "eval_mar_large": 0.0756,
+      "eval_mar_medium": 0.0173,
+      "eval_mar_small": 0.0055,
+      "eval_runtime": 39.8886,
+      "eval_samples_per_second": 3.76,
+      "eval_steps_per_second": 0.476,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.1082572925952e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb5b1b016fe6c9e411ad0aa21f5650b9f5bdfae6d91c31b103f2e514cbab6ff
+size 5176