Training in progress, step 200

config.json

@@ -1,71 +1,48 @@
 {
-  "_name_or_path": "mserrasa/detr-resnet-50_finetuned_cppe5",
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "_name_or_path": "mserrasa/yolos_finetuned_VinBigData",
   "architectures": [
-    "DetrForObjectDetection"
+    "YolosForObjectDetection"
   ],
-  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.0,
   "auxiliary_loss": false,
-  "backbone": "resnet50",
-  "backbone_config": null,
-  "backbone_kwargs": {
-    "in_chans": 3,
-    "out_indices": [
-      1,
-      2,
-      3,
-      4
-    ]
-  },
   "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": false,
-  "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,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "Aortic enlargement",
     "1": "Cardiomegaly",
     "2": "Nodule/Mass",
     "3": "Pleural thickening",
-    "4": "Pulmonary fibrosis",
-    "5": "No finding"
+    "4": "Pulmonary fibrosis"
   },
-  "init_std": 0.02,
-  "init_xavier_std": 1.0,
-  "is_encoder_decoder": true,
+  "image_size": [
+    800,
+    1344
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Aortic enlargement": 0,
     "Cardiomegaly": 1,
-    "No finding": 5,
     "Nodule/Mass": 2,
     "Pleural thickening": 3,
     "Pulmonary fibrosis": 4
   },
-  "mask_loss_coefficient": 1,
-  "max_position_embeddings": 1024,
-  "model_type": "detr",
+  "layer_norm_eps": 1e-12,
+  "model_type": "yolos",
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "num_hidden_layers": 6,
-  "num_queries": 100,
-  "position_embedding_type": "sine",
-  "scale_embedding": false,
+  "num_detection_tokens": 100,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
-  "use_pretrained_backbone": true,
-  "use_timm_backbone": true
+  "transformers_version": "4.43.1",
+  "use_mid_position_embeddings": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c76679ce1a84a8e51be43e8be3efff0cdb6b5864fa8ad154017f5b8e9ea9759
-size 166499964
+oid sha256:90e32831e9343545e5251e73f922104e20d9bb77c9418506ef74a0a24d22f799
+size 510953464

preprocessor_config.json

@@ -10,7 +10,7 @@
     0.456,
     0.406
   ],
-  "image_processor_type": "DetrImageProcessor",
+  "image_processor_type": "YolosImageProcessor",
   "image_std": [
     0.229,
     0.224,

runs/Jul24_14-11-03_ae16a8937d18/events.out.tfevents.1721830289.ae16a8937d18.161.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5edb89a04a87fbc5a01bed04b1ec2bff58e23b2654bc3376b85277321d294d
+size 6235

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f36e5a6f6f214716ce8d142d54bbda01be39b7bd0a696f8049b33d1ff64f9b
-size 5112
+oid sha256:f4aac4a6519f12ce50e6cdf31b273abd984cc246e2acc567feaa5384a0466784
+size 5176