Training in progress, step 150, checkpoint

checkpoint-150/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": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

checkpoint-150/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefba5dfa505cde8aedb527e401028cc2ab775768785c6e018872f5d8f8f60ed
+size 166494824

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa2db285acf4a63b9bce22157cca125b36ce429286ba179f75bb95a1c9dc052
+size 330491770

checkpoint-150/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-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487bc3d9a46ff7416da08865bd0791907d68c05b273e0a1370cc8cee1e1969df
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7152a7d028087b30d80573b704043ae27387c6b5a89c5d6ee49d5bc7be1a84b0
+size 1064

checkpoint-150/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3076923076923075,
+  "eval_steps": 50,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 38.090023040771484,
+      "learning_rate": 7.75e-06,
+      "loss": 3.4036,
+      "step": 50
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 2.0667002201080322,
+      "eval_runtime": 12.5463,
+      "eval_samples_per_second": 10.441,
+      "eval_steps_per_second": 1.355,
+      "step": 50
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 76.00936889648438,
+      "learning_rate": 5.300000000000001e-06,
+      "loss": 2.1551,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 1.8017847537994385,
+      "eval_runtime": 12.1789,
+      "eval_samples_per_second": 10.756,
+      "eval_steps_per_second": 1.396,
+      "step": 100
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 51.53462219238281,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.8526,
+      "step": 150
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "eval_loss": 1.7186994552612305,
+      "eval_runtime": 12.3313,
+      "eval_samples_per_second": 10.623,
+      "eval_steps_per_second": 1.379,
+      "step": 150
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 50,
+  "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+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e23ef637d7030f7f57d03652d74014083ad2b70c4cbb5bd54d624160dc76661
+size 5304