Training in progress, step 400, checkpoint

checkpoint-400/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": "4.44.1",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be31652cebd9e6cac6c2c7e6d8ebc29c10c3151608118515c0ae91c2a3e43603
+size 166904424

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b35d247bcf741bb4f781719234ff514665c4bb0e0bc7378dabdbf522dfe774
+size 331310970

checkpoint-400/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-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd6f77552e756d83b55e3331e0aa88480527d18255123d54e2b6ebff9e576e1
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe7bd9572fe84072887a8faccbf74b762ee4ab0c431a9750888d768c19d3cbe
+size 1064

checkpoint-400/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.938271604938271,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 62.88630294799805,
+      "learning_rate": 9.916000000000001e-06,
+      "loss": 6.6856,
+      "step": 50
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 387.6339111328125,
+      "learning_rate": 9.818000000000002e-06,
+      "loss": 5.5869,
+      "step": 100
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 245.18975830078125,
+      "learning_rate": 9.718e-06,
+      "loss": 5.159,
+      "step": 150
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 330.3158264160156,
+      "learning_rate": 9.618e-06,
+      "loss": 4.0494,
+      "step": 200
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 138.14215087890625,
+      "learning_rate": 9.518000000000001e-06,
+      "loss": 3.6313,
+      "step": 250
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 166.69479370117188,
+      "learning_rate": 9.418e-06,
+      "loss": 3.3391,
+      "step": 300
+    },
+    {
+      "epoch": 4.320987654320987,
+      "grad_norm": 107.54407501220703,
+      "learning_rate": 9.318e-06,
+      "loss": 3.3295,
+      "step": 350
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 293.8923034667969,
+      "learning_rate": 9.218e-06,
+      "loss": 3.0956,
+      "step": 400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 62,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.528972664832e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dae0b4d732b15d565b589748a29a09a17e2ddd7d7ab9df017470bce43888a34
+size 5240