Training in progress, step 500, checkpoint

checkpoint-500/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-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492a3faf4473b21552303a792428a82deb50e95743c104426c38653573d67f83
+size 166904424

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7914ba0d6350069891f6fa3a397f0540b6bee8300d2065fe634dedb2a937ceb6
+size 331310970

checkpoint-500/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-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734b6c89de500a47e18fbb4e68103c6154e1ab7481195e38af40d8d8da1bfa54
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade29b533657cf27cab586927ba7e08809fda5abf41f28aeecb1e72c244cc4d1
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.564102564102564,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 81.8341293334961,
+      "learning_rate": 9.990900000000001e-06,
+      "loss": 3.5606,
+      "step": 100
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "eval_loss": 2.2667126655578613,
+      "eval_runtime": 33.7385,
+      "eval_samples_per_second": 11.648,
+      "eval_steps_per_second": 1.482,
+      "step": 100
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 30.16681671142578,
+      "learning_rate": 9.980900000000001e-06,
+      "loss": 2.1841,
+      "step": 200
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "eval_loss": 2.059685230255127,
+      "eval_runtime": 33.6897,
+      "eval_samples_per_second": 11.665,
+      "eval_steps_per_second": 1.484,
+      "step": 200
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 67.16844177246094,
+      "learning_rate": 9.970900000000001e-06,
+      "loss": 2.0949,
+      "step": 300
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 1.9054155349731445,
+      "eval_runtime": 33.6472,
+      "eval_samples_per_second": 11.68,
+      "eval_steps_per_second": 1.486,
+      "step": 300
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 46.190330505371094,
+      "learning_rate": 9.960900000000001e-06,
+      "loss": 1.9236,
+      "step": 400
+    },
+    {
+      "epoch": 2.051282051282051,
+      "eval_loss": 1.8464823961257935,
+      "eval_runtime": 33.8143,
+      "eval_samples_per_second": 11.622,
+      "eval_steps_per_second": 1.479,
+      "step": 400
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 42.82326889038086,
+      "learning_rate": 9.950900000000002e-06,
+      "loss": 1.937,
+      "step": 500
+    },
+    {
+      "epoch": 2.564102564102564,
+      "eval_loss": 1.8186373710632324,
+      "eval_runtime": 33.9112,
+      "eval_samples_per_second": 11.589,
+      "eval_steps_per_second": 1.474,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 513,
+  "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": 1.91121583104e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12024124d98d6f3527d5a0e9a760923228a8928111a77f0d825458c2cc9072c6
+size 5304