Training in progress, epoch 1, checkpoint

checkpoint-107/config.json

@@ -1,69 +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
-}
+{
+  "_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": "4.42.4",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

checkpoint-107/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9168531ddb45f2298b113658889ff631837a10e765f70e7be10501b45790389f
+oid sha256:e0e73b52bd487fe68f9122ef8b954c6bc5b4e68351aaa78a20de44f8b42d1693
 size 174079796

checkpoint-107/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f904da31bb13fab078840fd330dda9a05a05233afad745d9949d03e066d92bc
-size 345687577
+oid sha256:93d99a373e4f0a6a9bdc55bb77fa36619ec34f8e95385249c63aedc7abc5e956
+size 345697817

checkpoint-107/preprocessor_config.json

@@ -1,47 +1,26 @@
-{
-  "_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
-  }
-}
+{
+  "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-107/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c767058bdd3f68dbc6cf97068b5ee58b195ea3718101c65bbe94691b1c73fd6
-size 13990
+oid sha256:c96e01c4478ce452b19c3ac871fcae8ffc9ff5adff345b47347e9222ef89609e
+size 14244

checkpoint-107/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7ac9164f06041a8f4e435beb14854468bf87c43057245430ab822edd10eed0
+oid sha256:8c71b99b3bd76330e6a5aae2cdf3df1f34ce8d9f90031a6793ce1e0abac2e6f7
 size 1064

checkpoint-107/trainer_state.json

@@ -1,93 +1,93 @@
-{
-  "best_metric": 0.0001,
-  "best_model_checkpoint": "test_detr_finetuned_cppe5/checkpoint-107",
-  "epoch": 1.0,
-  "eval_steps": 500,
-  "global_step": 107,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "step": 107,
-      "train_loss": 3.2706406116485596,
-      "train_map": 0.0002,
-      "train_map_50": 0.0006,
-      "train_map_75": 0.0001,
-      "train_map_Coverall": 0.0007,
-      "train_map_Face_Shield": 0.0,
-      "train_map_Gloves": 0.0001,
-      "train_map_Goggles": 0.0,
-      "train_map_Mask": 0.0,
-      "train_map_large": 0.0003,
-      "train_map_medium": 0.0,
-      "train_map_small": 0.0,
-      "train_mar_1": 0.003,
-      "train_mar_10": 0.0087,
-      "train_mar_100": 0.0266,
-      "train_mar_100_Coverall": 0.0956,
-      "train_mar_100_Face_Shield": 0.0006,
-      "train_mar_100_Gloves": 0.034,
-      "train_mar_100_Goggles": 0.0013,
-      "train_mar_100_Mask": 0.0016,
-      "train_mar_large": 0.0244,
-      "train_mar_medium": 0.0105,
-      "train_mar_small": 0.002,
-      "train_runtime": 75.6338,
-      "train_samples_per_second": 11.238,
-      "train_steps_per_second": 1.415
-    },
-    {
-      "epoch": 1.0,
-      "eval_loss": 3.281048059463501,
-      "eval_map": 0.0001,
-      "eval_map_50": 0.0005,
-      "eval_map_75": 0.0,
-      "eval_map_Coverall": 0.0005,
-      "eval_map_Face_Shield": 0.0,
-      "eval_map_Gloves": 0.0001,
-      "eval_map_Goggles": 0.0,
-      "eval_map_Mask": 0.0,
-      "eval_map_large": 0.0002,
-      "eval_map_medium": 0.0001,
-      "eval_map_small": 0.0001,
-      "eval_mar_1": 0.002,
-      "eval_mar_10": 0.0057,
-      "eval_mar_100": 0.0185,
-      "eval_mar_100_Coverall": 0.0676,
-      "eval_mar_100_Face_Shield": 0.0,
-      "eval_mar_100_Gloves": 0.0246,
-      "eval_mar_100_Goggles": 0.0,
-      "eval_mar_100_Mask": 0.0004,
-      "eval_mar_large": 0.0155,
-      "eval_mar_medium": 0.0078,
-      "eval_mar_small": 0.0027,
-      "eval_runtime": 41.9051,
-      "eval_samples_per_second": 3.58,
-      "eval_steps_per_second": 0.453,
-      "step": 107
-    }
-  ],
-  "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": 1.5270643231488e+17,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}
+{
+  "best_metric": 0.0229,
+  "best_model_checkpoint": "test_detr_finetuned_cppe5\\checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 107,
+      "train_loss": 2.4489498138427734,
+      "train_map": 0.0345,
+      "train_map_50": 0.0655,
+      "train_map_75": 0.0342,
+      "train_map_Coverall": 0.1469,
+      "train_map_Face_Shield": 0.0001,
+      "train_map_Gloves": 0.0053,
+      "train_map_Goggles": 0.0,
+      "train_map_Mask": 0.0204,
+      "train_map_large": 0.0326,
+      "train_map_medium": 0.0085,
+      "train_map_small": 0.0026,
+      "train_mar_1": 0.0855,
+      "train_mar_10": 0.1663,
+      "train_mar_100": 0.2076,
+      "train_mar_100_Coverall": 0.5511,
+      "train_mar_100_Face_Shield": 0.0052,
+      "train_mar_100_Gloves": 0.2184,
+      "train_mar_100_Goggles": 0.0097,
+      "train_mar_100_Mask": 0.2535,
+      "train_mar_large": 0.3274,
+      "train_mar_medium": 0.1339,
+      "train_mar_small": 0.0219,
+      "train_runtime": 29.1905,
+      "train_samples_per_second": 29.119,
+      "train_steps_per_second": 3.666
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5123209953308105,
+      "eval_map": 0.0229,
+      "eval_map_50": 0.0502,
+      "eval_map_75": 0.0195,
+      "eval_map_Coverall": 0.0993,
+      "eval_map_Face_Shield": 0.0003,
+      "eval_map_Gloves": 0.0038,
+      "eval_map_Goggles": 0.0002,
+      "eval_map_Mask": 0.0109,
+      "eval_map_large": 0.0247,
+      "eval_map_medium": 0.0069,
+      "eval_map_small": 0.0024,
+      "eval_mar_1": 0.061,
+      "eval_mar_10": 0.1307,
+      "eval_mar_100": 0.1723,
+      "eval_mar_100_Coverall": 0.4779,
+      "eval_mar_100_Face_Shield": 0.0152,
+      "eval_mar_100_Gloves": 0.1562,
+      "eval_mar_100_Goggles": 0.0185,
+      "eval_mar_100_Mask": 0.1938,
+      "eval_mar_large": 0.3415,
+      "eval_mar_medium": 0.1271,
+      "eval_mar_small": 0.0166,
+      "eval_runtime": 11.5313,
+      "eval_samples_per_second": 13.008,
+      "eval_steps_per_second": 1.648,
+      "step": 107
+    }
+  ],
+  "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": 1.5270643231488e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-107/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ab6612c795f2330a136ddf97d7c6e0ba7798175cc9cae994cc3f067700c650
-size 5176
+oid sha256:0fec926f50e96773b99e04d57819f5ac08d83a45048d26a31f3b9c2098e2492b
+size 5112