Training in progress, step 3500, checkpoint

checkpoint-3500/config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "facebook/detr-resnet-50-dc5",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ],
+    "output_stride": 16
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "segment"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "segment": 0
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 500,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48e052484e831ea28b36791cfd0fbc6bacdfbf9921ef17bc560c84902d49f8b
+size 166904424

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f47860b768cea8db2150d45ad3414dd40d5a7009e75567c59a2034410f1a060
+size 331310970

checkpoint-3500/preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetrImageProcessor",
+  "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-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c6aa0cdf9c851d309bb8c1368458c8d564486bb03a06a184ab4211c5c053a1
+size 14180

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09842fe56e19e92e42c6844bd853b4b0e5bb35c841ee01ff36affa1ae636d17
+size 1064

checkpoint-3500/trainer_state.json

@@ -0,0 +1,278 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 53.84615384615385,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 134.7136688232422,
+      "learning_rate": 9.981600000000001e-06,
+      "loss": 5.6198,
+      "step": 100
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 115.98611450195312,
+      "learning_rate": 9.961600000000001e-06,
+      "loss": 3.5959,
+      "step": 200
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 114.23514556884766,
+      "learning_rate": 9.941600000000002e-06,
+      "loss": 3.3845,
+      "step": 300
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 140.5648193359375,
+      "learning_rate": 9.921600000000002e-06,
+      "loss": 3.1494,
+      "step": 400
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 117.4485855102539,
+      "learning_rate": 9.901600000000002e-06,
+      "loss": 3.0773,
+      "step": 500
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 389.71490478515625,
+      "learning_rate": 9.8816e-06,
+      "loss": 3.2116,
+      "step": 600
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 107.11251831054688,
+      "learning_rate": 9.8616e-06,
+      "loss": 3.0471,
+      "step": 700
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 85.49571228027344,
+      "learning_rate": 9.8416e-06,
+      "loss": 3.0201,
+      "step": 800
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 121.62274932861328,
+      "learning_rate": 9.821600000000001e-06,
+      "loss": 2.9355,
+      "step": 900
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 64.66451263427734,
+      "learning_rate": 9.801600000000001e-06,
+      "loss": 2.9637,
+      "step": 1000
+    },
+    {
+      "epoch": 16.923076923076923,
+      "grad_norm": 182.4657440185547,
+      "learning_rate": 9.781600000000001e-06,
+      "loss": 2.9819,
+      "step": 1100
+    },
+    {
+      "epoch": 18.46153846153846,
+      "grad_norm": 97.80529022216797,
+      "learning_rate": 9.761600000000002e-06,
+      "loss": 2.9486,
+      "step": 1200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 220.0562744140625,
+      "learning_rate": 9.741600000000002e-06,
+      "loss": 2.8608,
+      "step": 1300
+    },
+    {
+      "epoch": 21.53846153846154,
+      "grad_norm": 95.53397369384766,
+      "learning_rate": 9.7216e-06,
+      "loss": 2.8322,
+      "step": 1400
+    },
+    {
+      "epoch": 23.076923076923077,
+      "grad_norm": 67.54853057861328,
+      "learning_rate": 9.7016e-06,
+      "loss": 2.9429,
+      "step": 1500
+    },
+    {
+      "epoch": 24.615384615384617,
+      "grad_norm": 214.53131103515625,
+      "learning_rate": 9.6816e-06,
+      "loss": 2.7927,
+      "step": 1600
+    },
+    {
+      "epoch": 26.153846153846153,
+      "grad_norm": 293.3318786621094,
+      "learning_rate": 9.6616e-06,
+      "loss": 2.7665,
+      "step": 1700
+    },
+    {
+      "epoch": 27.692307692307693,
+      "grad_norm": 216.3682861328125,
+      "learning_rate": 9.641600000000001e-06,
+      "loss": 2.8309,
+      "step": 1800
+    },
+    {
+      "epoch": 29.23076923076923,
+      "grad_norm": 168.0605010986328,
+      "learning_rate": 9.621600000000001e-06,
+      "loss": 2.8433,
+      "step": 1900
+    },
+    {
+      "epoch": 30.76923076923077,
+      "grad_norm": 103.49143981933594,
+      "learning_rate": 9.601600000000001e-06,
+      "loss": 2.7606,
+      "step": 2000
+    },
+    {
+      "epoch": 32.30769230769231,
+      "grad_norm": 116.6761474609375,
+      "learning_rate": 9.581600000000002e-06,
+      "loss": 2.6595,
+      "step": 2100
+    },
+    {
+      "epoch": 33.84615384615385,
+      "grad_norm": 176.0087432861328,
+      "learning_rate": 9.5616e-06,
+      "loss": 2.632,
+      "step": 2200
+    },
+    {
+      "epoch": 35.38461538461539,
+      "grad_norm": 120.39679718017578,
+      "learning_rate": 9.5416e-06,
+      "loss": 2.5941,
+      "step": 2300
+    },
+    {
+      "epoch": 36.92307692307692,
+      "grad_norm": 100.69256591796875,
+      "learning_rate": 9.5216e-06,
+      "loss": 2.6007,
+      "step": 2400
+    },
+    {
+      "epoch": 38.46153846153846,
+      "grad_norm": 254.54440307617188,
+      "learning_rate": 9.5016e-06,
+      "loss": 2.5548,
+      "step": 2500
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 113.618896484375,
+      "learning_rate": 9.4816e-06,
+      "loss": 2.5157,
+      "step": 2600
+    },
+    {
+      "epoch": 41.53846153846154,
+      "grad_norm": 825.5616455078125,
+      "learning_rate": 9.461600000000001e-06,
+      "loss": 2.4832,
+      "step": 2700
+    },
+    {
+      "epoch": 43.07692307692308,
+      "grad_norm": 58.83940505981445,
+      "learning_rate": 9.441600000000001e-06,
+      "loss": 2.4393,
+      "step": 2800
+    },
+    {
+      "epoch": 44.61538461538461,
+      "grad_norm": 89.66182708740234,
+      "learning_rate": 9.421600000000001e-06,
+      "loss": 2.4381,
+      "step": 2900
+    },
+    {
+      "epoch": 46.15384615384615,
+      "grad_norm": 242.81410217285156,
+      "learning_rate": 9.4016e-06,
+      "loss": 2.3978,
+      "step": 3000
+    },
+    {
+      "epoch": 47.69230769230769,
+      "grad_norm": 70.43364715576172,
+      "learning_rate": 9.3816e-06,
+      "loss": 2.3782,
+      "step": 3100
+    },
+    {
+      "epoch": 49.23076923076923,
+      "grad_norm": 244.31356811523438,
+      "learning_rate": 9.3616e-06,
+      "loss": 2.3319,
+      "step": 3200
+    },
+    {
+      "epoch": 50.76923076923077,
+      "grad_norm": 59.848697662353516,
+      "learning_rate": 9.3416e-06,
+      "loss": 2.3205,
+      "step": 3300
+    },
+    {
+      "epoch": 52.30769230769231,
+      "grad_norm": 109.26374053955078,
+      "learning_rate": 9.3216e-06,
+      "loss": 2.2943,
+      "step": 3400
+    },
+    {
+      "epoch": 53.84615384615385,
+      "grad_norm": 307.2849426269531,
+      "learning_rate": 9.301600000000001e-06,
+      "loss": 2.2913,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 770,
+  "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": 1.337851081728e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee77453dae7076acf919eb7bcd8ccb5a082573a80b4f2c85a6a7d7ad1edcbedf
+size 5240