Training in progress, step 800, checkpoint

checkpoint-800/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-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f8e45cd307dab425eb0a99128392421a34fb96f4f138e8935d1f9d87be5562
+size 166904424

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6f50f47a9b371a87c65d97d0aba883dd8735c6e64c784e514af8c4b20c9a15
+size 1072390

checkpoint-800/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-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ef16218a66b3f0d983d317b05d73e1d6cadac4c196e20c963f7636b1604922
+size 14308

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8efff1cacd697681988e6bbf427c1c9e62c117cfe7d3df4f1c0397b264d21e59
+size 1064

checkpoint-800/trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.876543209876543,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 14.113041877746582,
+      "learning_rate": 9.953000000000001e-06,
+      "loss": 9.3136,
+      "step": 50
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 11.032143592834473,
+      "learning_rate": 9.903e-06,
+      "loss": 8.8439,
+      "step": 100
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 21.83379554748535,
+      "learning_rate": 9.853e-06,
+      "loss": 8.9582,
+      "step": 150
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 13.823728561401367,
+      "learning_rate": 9.803e-06,
+      "loss": 8.5429,
+      "step": 200
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 14.090177536010742,
+      "learning_rate": 9.753e-06,
+      "loss": 8.0873,
+      "step": 250
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 16.695327758789062,
+      "learning_rate": 9.703000000000002e-06,
+      "loss": 7.5718,
+      "step": 300
+    },
+    {
+      "epoch": 4.320987654320987,
+      "grad_norm": 12.39268970489502,
+      "learning_rate": 9.653e-06,
+      "loss": 7.2107,
+      "step": 350
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 20.64848518371582,
+      "learning_rate": 9.603000000000001e-06,
+      "loss": 6.633,
+      "step": 400
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 10.930610656738281,
+      "learning_rate": 9.553000000000002e-06,
+      "loss": 6.3085,
+      "step": 450
+    },
+    {
+      "epoch": 6.172839506172839,
+      "grad_norm": 7.421260833740234,
+      "learning_rate": 9.503e-06,
+      "loss": 5.9761,
+      "step": 500
+    },
+    {
+      "epoch": 6.790123456790123,
+      "grad_norm": 19.653493881225586,
+      "learning_rate": 9.453e-06,
+      "loss": 6.0252,
+      "step": 550
+    },
+    {
+      "epoch": 7.407407407407407,
+      "grad_norm": 10.195016860961914,
+      "learning_rate": 9.403000000000001e-06,
+      "loss": 5.9531,
+      "step": 600
+    },
+    {
+      "epoch": 8.024691358024691,
+      "grad_norm": 15.588345527648926,
+      "learning_rate": 9.353000000000002e-06,
+      "loss": 5.979,
+      "step": 650
+    },
+    {
+      "epoch": 8.641975308641975,
+      "grad_norm": 11.010184288024902,
+      "learning_rate": 9.303e-06,
+      "loss": 5.9684,
+      "step": 700
+    },
+    {
+      "epoch": 9.25925925925926,
+      "grad_norm": 12.536541938781738,
+      "learning_rate": 9.253000000000001e-06,
+      "loss": 6.0309,
+      "step": 750
+    },
+    {
+      "epoch": 9.876543209876543,
+      "grad_norm": 10.15280818939209,
+      "learning_rate": 9.203000000000002e-06,
+      "loss": 5.7873,
+      "step": 800
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 124,
+  "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": 3.057945329664e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10f18946db6a2f229ca0327743a6277178ea5088c71de2a2cdecf2c028b988a
+size 5240