Training in progress, step 200, checkpoint

checkpoint-200/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-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515786a161b4385d2da1d54608d35e81407843853e2b447f895262ea40a98312
+size 166904424

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed74102f166e18234a1a2a248909beccd49f600ef1b180ec65e9b2dbaffee0c
+size 331310970

checkpoint-200/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-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3e45d2c249ec1934dbd0c84fd93ec3bfe90c25b4b762c1859537142001630f
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24d7363df794c93474e47821850fea727afaf413b68591328a2c4b628c01d3c
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.076923076923077,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 222.5110626220703,
+      "learning_rate": 7.950000000000002e-06,
+      "loss": 6.9812,
+      "step": 50
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 7.659696102142334,
+      "eval_runtime": 13.2341,
+      "eval_samples_per_second": 9.899,
+      "eval_steps_per_second": 1.285,
+      "step": 50
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 354.31988525390625,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 5.1829,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 7.435208320617676,
+      "eval_runtime": 12.0118,
+      "eval_samples_per_second": 10.906,
+      "eval_steps_per_second": 1.415,
+      "step": 100
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 373.4967346191406,
+      "learning_rate": 3e-06,
+      "loss": 4.5311,
+      "step": 150
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "eval_loss": 7.100094318389893,
+      "eval_runtime": 11.9696,
+      "eval_samples_per_second": 10.944,
+      "eval_steps_per_second": 1.42,
+      "step": 150
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 195.70413208007812,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.9432,
+      "step": 200
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 6.598204612731934,
+      "eval_runtime": 12.1096,
+      "eval_samples_per_second": 10.818,
+      "eval_steps_per_second": 1.404,
+      "step": 200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.64486332416e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f303e3ee81f8b8015f27409a0898409742db082edc3d8148768e6ede7d4c3429
+size 5240