Training in progress, step 1000, checkpoint

checkpoint-1000/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-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde2cc4b4097eabb2b9500ae10ef5fc9244c4627ff6738f98206de70f73456b0
+size 166904424

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406683056b4dc35f29a87f9b7043bc326fbe5e7b023eda534b29d3fe78a86693
+size 331310970

checkpoint-1000/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-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4faccc6623814d573a2dc03d5a19ddc8b0c2a9978c2b1eae8f5429bb300e64ee
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db8d7316462a1d5f9d059f8ee96aa24ff6454325292befc63cba12bb8c45522
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.384615384615385,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 47.11796188354492,
+      "learning_rate": 9.990900000000001e-06,
+      "loss": 3.6644,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 2.4919605255126953,
+      "eval_runtime": 12.5517,
+      "eval_samples_per_second": 10.437,
+      "eval_steps_per_second": 1.354,
+      "step": 100
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 31.28130531311035,
+      "learning_rate": 9.980900000000001e-06,
+      "loss": 2.2347,
+      "step": 200
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 2.156316041946411,
+      "eval_runtime": 11.1792,
+      "eval_samples_per_second": 11.718,
+      "eval_steps_per_second": 1.521,
+      "step": 200
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 39.616390228271484,
+      "learning_rate": 9.970900000000001e-06,
+      "loss": 2.0254,
+      "step": 300
+    },
+    {
+      "epoch": 4.615384615384615,
+      "eval_loss": 2.024153709411621,
+      "eval_runtime": 11.1934,
+      "eval_samples_per_second": 11.703,
+      "eval_steps_per_second": 1.519,
+      "step": 300
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 28.285825729370117,
+      "learning_rate": 9.960900000000001e-06,
+      "loss": 1.9361,
+      "step": 400
+    },
+    {
+      "epoch": 6.153846153846154,
+      "eval_loss": 1.9094743728637695,
+      "eval_runtime": 11.3855,
+      "eval_samples_per_second": 11.506,
+      "eval_steps_per_second": 1.493,
+      "step": 400
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 34.14302062988281,
+      "learning_rate": 9.950900000000002e-06,
+      "loss": 1.8531,
+      "step": 500
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "eval_loss": 1.8729331493377686,
+      "eval_runtime": 11.2935,
+      "eval_samples_per_second": 11.6,
+      "eval_steps_per_second": 1.505,
+      "step": 500
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 39.09531784057617,
+      "learning_rate": 9.940900000000002e-06,
+      "loss": 1.7669,
+      "step": 600
+    },
+    {
+      "epoch": 9.23076923076923,
+      "eval_loss": 1.831756830215454,
+      "eval_runtime": 11.0535,
+      "eval_samples_per_second": 11.851,
+      "eval_steps_per_second": 1.538,
+      "step": 600
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 93.24444580078125,
+      "learning_rate": 9.930900000000002e-06,
+      "loss": 1.7518,
+      "step": 700
+    },
+    {
+      "epoch": 10.76923076923077,
+      "eval_loss": 1.7832175493240356,
+      "eval_runtime": 11.1684,
+      "eval_samples_per_second": 11.729,
+      "eval_steps_per_second": 1.522,
+      "step": 700
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 32.21013641357422,
+      "learning_rate": 9.920900000000002e-06,
+      "loss": 1.7149,
+      "step": 800
+    },
+    {
+      "epoch": 12.307692307692308,
+      "eval_loss": 1.7581098079681396,
+      "eval_runtime": 11.101,
+      "eval_samples_per_second": 11.801,
+      "eval_steps_per_second": 1.531,
+      "step": 800
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 59.90657043457031,
+      "learning_rate": 9.9109e-06,
+      "loss": 1.6734,
+      "step": 900
+    },
+    {
+      "epoch": 13.846153846153847,
+      "eval_loss": 1.7163844108581543,
+      "eval_runtime": 11.1167,
+      "eval_samples_per_second": 11.784,
+      "eval_steps_per_second": 1.529,
+      "step": 900
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 20.61592674255371,
+      "learning_rate": 9.9009e-06,
+      "loss": 1.6612,
+      "step": 1000
+    },
+    {
+      "epoch": 15.384615384615385,
+      "eval_loss": 1.6949567794799805,
+      "eval_runtime": 11.0663,
+      "eval_samples_per_second": 11.838,
+      "eval_steps_per_second": 1.536,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1539,
+  "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": 3.82243166208e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad9d755c74ae76083891287d009fdddb96b730c67f38d8947352435e2637ed7
+size 5304