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 sha256:837afdd6731007bad599556ec1a054e3603703bfdb76097347ae81455910aa53
+size 166904424

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8feacb6133ae5f6a5b2e0e99f82d5fe7138bed0cf6d2e7a72c1cf49819651167
+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 sha256:486696d2cbd4c353d1a7d52817c10f148292d34eaba31aed1c12fe0581712f00
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db8d7316462a1d5f9d059f8ee96aa24ff6454325292befc63cba12bb8c45522
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.128205128205128,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 92.9238510131836,
+      "learning_rate": 9.9907e-06,
+      "loss": 2.4016,
+      "step": 100
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "eval_loss": 2.1255013942718506,
+      "eval_runtime": 34.4318,
+      "eval_samples_per_second": 11.414,
+      "eval_steps_per_second": 1.452,
+      "step": 100
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 47.019439697265625,
+      "learning_rate": 9.980700000000001e-06,
+      "loss": 2.0696,
+      "step": 200
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "eval_loss": 1.9405728578567505,
+      "eval_runtime": 34.0713,
+      "eval_samples_per_second": 11.535,
+      "eval_steps_per_second": 1.468,
+      "step": 200
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 52.230751037597656,
+      "learning_rate": 9.970700000000001e-06,
+      "loss": 1.9983,
+      "step": 300
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 1.900020718574524,
+      "eval_runtime": 34.1694,
+      "eval_samples_per_second": 11.502,
+      "eval_steps_per_second": 1.463,
+      "step": 300
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 39.62374496459961,
+      "learning_rate": 9.960800000000001e-06,
+      "loss": 1.8888,
+      "step": 400
+    },
+    {
+      "epoch": 2.051282051282051,
+      "eval_loss": 1.8164124488830566,
+      "eval_runtime": 34.1213,
+      "eval_samples_per_second": 11.518,
+      "eval_steps_per_second": 1.465,
+      "step": 400
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 39.697731018066406,
+      "learning_rate": 9.9508e-06,
+      "loss": 1.8456,
+      "step": 500
+    },
+    {
+      "epoch": 2.564102564102564,
+      "eval_loss": 1.7753618955612183,
+      "eval_runtime": 34.149,
+      "eval_samples_per_second": 11.508,
+      "eval_steps_per_second": 1.464,
+      "step": 500
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 52.823184967041016,
+      "learning_rate": 9.9408e-06,
+      "loss": 1.7839,
+      "step": 600
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 1.7344136238098145,
+      "eval_runtime": 34.121,
+      "eval_samples_per_second": 11.518,
+      "eval_steps_per_second": 1.465,
+      "step": 600
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 107.05223083496094,
+      "learning_rate": 9.9308e-06,
+      "loss": 1.7544,
+      "step": 700
+    },
+    {
+      "epoch": 3.58974358974359,
+      "eval_loss": 1.6865615844726562,
+      "eval_runtime": 34.0842,
+      "eval_samples_per_second": 11.53,
+      "eval_steps_per_second": 1.467,
+      "step": 700
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 53.641353607177734,
+      "learning_rate": 9.9208e-06,
+      "loss": 1.6812,
+      "step": 800
+    },
+    {
+      "epoch": 4.102564102564102,
+      "eval_loss": 1.6568766832351685,
+      "eval_runtime": 34.432,
+      "eval_samples_per_second": 11.414,
+      "eval_steps_per_second": 1.452,
+      "step": 800
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 40.92328643798828,
+      "learning_rate": 9.9109e-06,
+      "loss": 1.6501,
+      "step": 900
+    },
+    {
+      "epoch": 4.615384615384615,
+      "eval_loss": 1.6080188751220703,
+      "eval_runtime": 34.1751,
+      "eval_samples_per_second": 11.5,
+      "eval_steps_per_second": 1.463,
+      "step": 900
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 28.52039909362793,
+      "learning_rate": 9.9009e-06,
+      "loss": 1.6579,
+      "step": 1000
+    },
+    {
+      "epoch": 5.128205128205128,
+      "eval_loss": 1.6059809923171997,
+      "eval_runtime": 34.1634,
+      "eval_samples_per_second": 11.504,
+      "eval_steps_per_second": 1.464,
+      "step": 1000
+    }
+  ],
+  "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": 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 sha256:1b0aa9c0ed9f82d8189412f29063b102d91faf6206c1fb280a34cbf2cd86a454
+size 5304