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 sha256:4c4fa456da07595dba2ff94c18f5eba0d4e38991b13e04dc0a9831f5f649935f
+size 166904424

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593adddff4fc1e782e93e97c66d053f40b1687ea80dc4fa9dd5a83e0e9586ebf
+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 sha256:0345832bd9c8697d0a8e6f99c1c682ea0ee27fe3353f090b67fb8716a3c847f7
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15ddf25286095ec98f6ab7984e9966d18ff4fa8ac06fc2a5261019af9531eaf
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.384615384615385,
+  "eval_steps": 500,
+  "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": 134.7136688232422,
+      "learning_rate": 9.981600000000001e-06,
+      "loss": 5.6198,
+      "step": 100
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 115.98611450195312,
+      "learning_rate": 9.961600000000001e-06,
+      "loss": 3.5959,
+      "step": 200
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 114.23514556884766,
+      "learning_rate": 9.941600000000002e-06,
+      "loss": 3.3845,
+      "step": 300
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 140.5648193359375,
+      "learning_rate": 9.921600000000002e-06,
+      "loss": 3.1494,
+      "step": 400
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 117.4485855102539,
+      "learning_rate": 9.901600000000002e-06,
+      "loss": 3.0773,
+      "step": 500
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 389.71490478515625,
+      "learning_rate": 9.8816e-06,
+      "loss": 3.2116,
+      "step": 600
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 107.11251831054688,
+      "learning_rate": 9.8616e-06,
+      "loss": 3.0471,
+      "step": 700
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 85.49571228027344,
+      "learning_rate": 9.8416e-06,
+      "loss": 3.0201,
+      "step": 800
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 121.62274932861328,
+      "learning_rate": 9.821600000000001e-06,
+      "loss": 2.9355,
+      "step": 900
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 64.66451263427734,
+      "learning_rate": 9.801600000000001e-06,
+      "loss": 2.9637,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 770,
+  "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:ee77453dae7076acf919eb7bcd8ccb5a082573a80b4f2c85a6a7d7ad1edcbedf
+size 5240