Training in progress, step 500, checkpoint

checkpoint-500/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-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3475764e33afce6c1d0d588001ac3aad82d196719613de1cb00393b973bc856
+size 166904424

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d444bf90d3a22fbbe43a4e6614d84ea4a7c61b8305f8787e27ba7c5daa9bc0a8
+size 331310970

checkpoint-500/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-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b80bf123249cf61490c6349d13940d5a6060e742ed74a272e2b7f69241f53c
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba3a836ce50b6e54aefa6df882f5ca2cb3a16e344d4bb0a7302b9bc0f8d2daf
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.6923076923076925,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 97.95333099365234,
+      "learning_rate": 4.9978e-05,
+      "loss": 5.4721,
+      "step": 50
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 5.876021385192871,
+      "eval_runtime": 12.8977,
+      "eval_samples_per_second": 10.157,
+      "eval_steps_per_second": 1.318,
+      "step": 50
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 104.74186706542969,
+      "learning_rate": 4.99535e-05,
+      "loss": 3.089,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 5.774240970611572,
+      "eval_runtime": 11.4924,
+      "eval_samples_per_second": 11.399,
+      "eval_steps_per_second": 1.479,
+      "step": 100
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 41.090965270996094,
+      "learning_rate": 4.99285e-05,
+      "loss": 2.764,
+      "step": 150
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "eval_loss": 5.597934722900391,
+      "eval_runtime": 11.4654,
+      "eval_samples_per_second": 11.426,
+      "eval_steps_per_second": 1.483,
+      "step": 150
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 73.45726776123047,
+      "learning_rate": 4.99035e-05,
+      "loss": 2.5945,
+      "step": 200
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 5.421833515167236,
+      "eval_runtime": 11.5159,
+      "eval_samples_per_second": 11.376,
+      "eval_steps_per_second": 1.476,
+      "step": 200
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 71.80171203613281,
+      "learning_rate": 4.98785e-05,
+      "loss": 2.6367,
+      "step": 250
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "eval_loss": 5.8073201179504395,
+      "eval_runtime": 11.5047,
+      "eval_samples_per_second": 11.387,
+      "eval_steps_per_second": 1.478,
+      "step": 250
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 43.557945251464844,
+      "learning_rate": 4.98535e-05,
+      "loss": 2.5105,
+      "step": 300
+    },
+    {
+      "epoch": 4.615384615384615,
+      "eval_loss": 4.3725128173828125,
+      "eval_runtime": 11.497,
+      "eval_samples_per_second": 11.394,
+      "eval_steps_per_second": 1.479,
+      "step": 300
+    },
+    {
+      "epoch": 5.384615384615385,
+      "grad_norm": 108.88764953613281,
+      "learning_rate": 4.98285e-05,
+      "loss": 2.5468,
+      "step": 350
+    },
+    {
+      "epoch": 5.384615384615385,
+      "eval_loss": 5.673581123352051,
+      "eval_runtime": 11.5715,
+      "eval_samples_per_second": 11.321,
+      "eval_steps_per_second": 1.469,
+      "step": 350
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 83.45320129394531,
+      "learning_rate": 4.9803500000000005e-05,
+      "loss": 2.4749,
+      "step": 400
+    },
+    {
+      "epoch": 6.153846153846154,
+      "eval_loss": 5.851593971252441,
+      "eval_runtime": 11.522,
+      "eval_samples_per_second": 11.37,
+      "eval_steps_per_second": 1.475,
+      "step": 400
+    },
+    {
+      "epoch": 6.923076923076923,
+      "grad_norm": 68.41734313964844,
+      "learning_rate": 4.97785e-05,
+      "loss": 2.3658,
+      "step": 450
+    },
+    {
+      "epoch": 6.923076923076923,
+      "eval_loss": 5.2119598388671875,
+      "eval_runtime": 11.4672,
+      "eval_samples_per_second": 11.424,
+      "eval_steps_per_second": 1.482,
+      "step": 450
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 102.76841735839844,
+      "learning_rate": 4.9753500000000004e-05,
+      "loss": 2.5853,
+      "step": 500
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "eval_loss": 4.767831325531006,
+      "eval_runtime": 11.4763,
+      "eval_samples_per_second": 11.415,
+      "eval_steps_per_second": 1.481,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "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": 1.91121583104e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b1b85fea4c8b1c2a7be60102809409971174bcdf130b87ba93f7312e8b78a2e
+size 5240