Training in progress, step 150, checkpoint

checkpoint-150/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": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.1",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

checkpoint-150/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc239be78411bf8dc8b2487bf5f4486e957ccc0ef997823b87024fe51162dd6
+size 166494824

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ec13ca5dd9be0b88cd6ce394d09af7a7128b5f95e3af2df97d69edc7f0a359
+size 330491770

checkpoint-150/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-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e11da36761ad1cb5e9dde9beea7fbfc28e235b3975ee72ba4e2feda9693b7f
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8212a57c74bbfcd624ed71f2d4bb6e26593a9ca2883b2b97200c02246004c817
+size 1064

checkpoint-150/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8518518518518519,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 69.9074478149414,
+      "learning_rate": 9.952e-06,
+      "loss": 4.4273,
+      "step": 30
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 96.12484741210938,
+      "learning_rate": 9.892000000000001e-06,
+      "loss": 2.6895,
+      "step": 60
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 43.14171600341797,
+      "learning_rate": 9.832e-06,
+      "loss": 2.4001,
+      "step": 90
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 41.42817306518555,
+      "learning_rate": 9.772e-06,
+      "loss": 2.0886,
+      "step": 120
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 41.4298095703125,
+      "learning_rate": 9.712e-06,
+      "loss": 1.9545,
+      "step": 150
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 62,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.73364749312e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f15598e86df495b8b90a7a9a5888880b2567bb4b0491fa29b9018cf021aa752
+size 5240