Training in progress, step 1500, checkpoint

checkpoint-1500/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": 99,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6190071f5b30ff69682a47fc2bd63241525d9a5f6fc80b88596004874f3693e
+size 166493800

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cba7fb343cccde0b579db58ab7d767725d2ae1e4cfa6ab5acff19737b9445c
+size 330489722

checkpoint-1500/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-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7349ef0f1472766a1287e86b9884a7b616eb93af1283c8643439feea6f600fa
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1eb04ddc12d7d6c54bb72789af32e8f9db628a77717b66154630fc0023731a
+size 1064

checkpoint-1500/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 23.076923076923077,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 103.745361328125,
+      "learning_rate": 9.950700000000001e-06,
+      "loss": 3.7724,
+      "step": 500
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "eval_loss": 4.843122959136963,
+      "eval_runtime": 12.2345,
+      "eval_samples_per_second": 10.707,
+      "eval_steps_per_second": 1.39,
+      "step": 500
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 134.67405700683594,
+      "learning_rate": 9.9008e-06,
+      "loss": 2.823,
+      "step": 1000
+    },
+    {
+      "epoch": 15.384615384615385,
+      "eval_loss": 4.731071472167969,
+      "eval_runtime": 11.7452,
+      "eval_samples_per_second": 11.153,
+      "eval_steps_per_second": 1.447,
+      "step": 1000
+    },
+    {
+      "epoch": 23.076923076923077,
+      "grad_norm": 67.87723541259766,
+      "learning_rate": 9.8508e-06,
+      "loss": 2.6546,
+      "step": 1500
+    },
+    {
+      "epoch": 23.076923076923077,
+      "eval_loss": 4.85584020614624,
+      "eval_runtime": 12.0536,
+      "eval_samples_per_second": 10.868,
+      "eval_steps_per_second": 1.41,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1539,
+  "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": 5.73364749312e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8cbf8e5e80b0b1d79922b7e15316817f1dd7309fcbaf2357bcb937829fb959
+size 5304