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": 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-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781d4d21b2b0ffe095e246e56d73fde44e0e3c5494a4d15ed66f0261104fd54a
+size 166904424

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786759e1e0732208bec54142055124b2b081ee1cda38c71538d830d583888a5f
+size 331310970

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 sha256:8cfc6a9eabafdad8792f62449aeccf9df4a7540b8158498e5a889b871fe331e2
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4995f69312b0347929bc93968b993266c233221fa89840b3febc0de6897adf
+size 1064

checkpoint-1500/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.6923076923076925,
+  "eval_steps": 100,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 485.6934509277344,
+      "learning_rate": 9.9907e-06,
+      "loss": 3.7897,
+      "step": 100
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "eval_loss": 2.913217067718506,
+      "eval_runtime": 36.1065,
+      "eval_samples_per_second": 10.884,
+      "eval_steps_per_second": 1.385,
+      "step": 100
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 35.502872467041016,
+      "learning_rate": 9.980700000000001e-06,
+      "loss": 2.6449,
+      "step": 200
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "eval_loss": 2.1936488151550293,
+      "eval_runtime": 35.8618,
+      "eval_samples_per_second": 10.959,
+      "eval_steps_per_second": 1.394,
+      "step": 200
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 44.5572624206543,
+      "learning_rate": 9.970700000000001e-06,
+      "loss": 2.123,
+      "step": 300
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 1.9975601434707642,
+      "eval_runtime": 36.0033,
+      "eval_samples_per_second": 10.916,
+      "eval_steps_per_second": 1.389,
+      "step": 300
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 91.06848907470703,
+      "learning_rate": 9.960700000000001e-06,
+      "loss": 1.9616,
+      "step": 400
+    },
+    {
+      "epoch": 2.051282051282051,
+      "eval_loss": 1.9457911252975464,
+      "eval_runtime": 35.8591,
+      "eval_samples_per_second": 10.96,
+      "eval_steps_per_second": 1.394,
+      "step": 400
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 62.52458953857422,
+      "learning_rate": 9.950700000000001e-06,
+      "loss": 1.9329,
+      "step": 500
+    },
+    {
+      "epoch": 2.564102564102564,
+      "eval_loss": 1.8983820676803589,
+      "eval_runtime": 35.7607,
+      "eval_samples_per_second": 10.99,
+      "eval_steps_per_second": 1.398,
+      "step": 500
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 46.58191680908203,
+      "learning_rate": 9.940700000000001e-06,
+      "loss": 1.8998,
+      "step": 600
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 1.8464109897613525,
+      "eval_runtime": 35.5376,
+      "eval_samples_per_second": 11.059,
+      "eval_steps_per_second": 1.407,
+      "step": 600
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 43.859432220458984,
+      "learning_rate": 9.930700000000001e-06,
+      "loss": 1.8632,
+      "step": 700
+    },
+    {
+      "epoch": 3.58974358974359,
+      "eval_loss": 1.8351906538009644,
+      "eval_runtime": 35.8606,
+      "eval_samples_per_second": 10.959,
+      "eval_steps_per_second": 1.394,
+      "step": 700
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 36.12472152709961,
+      "learning_rate": 9.920700000000001e-06,
+      "loss": 1.8202,
+      "step": 800
+    },
+    {
+      "epoch": 4.102564102564102,
+      "eval_loss": 1.7837625741958618,
+      "eval_runtime": 35.8551,
+      "eval_samples_per_second": 10.961,
+      "eval_steps_per_second": 1.395,
+      "step": 800
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 56.74811553955078,
+      "learning_rate": 9.910700000000002e-06,
+      "loss": 1.7767,
+      "step": 900
+    },
+    {
+      "epoch": 4.615384615384615,
+      "eval_loss": 1.777076005935669,
+      "eval_runtime": 35.652,
+      "eval_samples_per_second": 11.023,
+      "eval_steps_per_second": 1.402,
+      "step": 900
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 97.7017822265625,
+      "learning_rate": 9.900700000000002e-06,
+      "loss": 1.7757,
+      "step": 1000
+    },
+    {
+      "epoch": 5.128205128205128,
+      "eval_loss": 1.7516826391220093,
+      "eval_runtime": 35.6867,
+      "eval_samples_per_second": 11.013,
+      "eval_steps_per_second": 1.401,
+      "step": 1000
+    },
+    {
+      "epoch": 5.641025641025641,
+      "grad_norm": 21.942626953125,
+      "learning_rate": 9.8907e-06,
+      "loss": 1.7592,
+      "step": 1100
+    },
+    {
+      "epoch": 5.641025641025641,
+      "eval_loss": 1.7459185123443604,
+      "eval_runtime": 35.7882,
+      "eval_samples_per_second": 10.981,
+      "eval_steps_per_second": 1.397,
+      "step": 1100
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 31.696691513061523,
+      "learning_rate": 9.8807e-06,
+      "loss": 1.8098,
+      "step": 1200
+    },
+    {
+      "epoch": 6.153846153846154,
+      "eval_loss": 1.7705851793289185,
+      "eval_runtime": 35.6241,
+      "eval_samples_per_second": 11.032,
+      "eval_steps_per_second": 1.404,
+      "step": 1200
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 69.51777648925781,
+      "learning_rate": 9.8707e-06,
+      "loss": 1.6903,
+      "step": 1300
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 1.717505693435669,
+      "eval_runtime": 35.7343,
+      "eval_samples_per_second": 10.998,
+      "eval_steps_per_second": 1.399,
+      "step": 1300
+    },
+    {
+      "epoch": 7.17948717948718,
+      "grad_norm": 159.8116455078125,
+      "learning_rate": 9.8607e-06,
+      "loss": 1.7428,
+      "step": 1400
+    },
+    {
+      "epoch": 7.17948717948718,
+      "eval_loss": 1.7039239406585693,
+      "eval_runtime": 35.6477,
+      "eval_samples_per_second": 11.025,
+      "eval_steps_per_second": 1.403,
+      "step": 1400
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 52.08290100097656,
+      "learning_rate": 9.8507e-06,
+      "loss": 1.6913,
+      "step": 1500
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "eval_loss": 1.6931686401367188,
+      "eval_runtime": 35.6627,
+      "eval_samples_per_second": 11.02,
+      "eval_steps_per_second": 1.402,
+      "step": 1500
+    }
+  ],
+  "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": 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 sha256:3e1ab50c89af47345b449e34818f6f00e03a868edf459f7a8b74e316d1f072ee
+size 5368