Training in progress, epoch 1

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: facebook/detr-resnet-50
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # detr-resnet-50_finetuned_cppe5
 
-This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 
 ## Model description
 
@@ -32,13 +30,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 1e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 2
 - mixed_precision_training: Native AMP
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "total_flos": 9.4894217943552e+17,
-    "train_loss": 2.403542724609375,
-    "train_runtime": 150.6018,
-    "train_samples_per_second": 13.187,
-    "train_steps_per_second": 1.66
+    "train_loss": 1.8031856994628905,
+    "train_runtime": 142.4314,
+    "train_samples_per_second": 13.944,
+    "train_steps_per_second": 1.755
 }

config.json

@@ -63,7 +63,7 @@
   "position_embedding_type": "sine",
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.41.2",
   "use_pretrained_backbone": true,
   "use_timm_backbone": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73355bf1c2b0aaaa79377fd04c7b494d2b789359dc73d10d1d256a08a6e2e00
+oid sha256:00e1dea6fd3393e3877796b7ddf75d7a00d15f449f5bffb04ea67b4a5ffa6917
 size 166498936

preprocessor_config.json

@@ -1,4 +1,24 @@
 {
+  "_valid_processor_keys": [
+    "images",
+    "annotations",
+    "return_segmentation_masks",
+    "masks_path",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "do_convert_annotations",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "format",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "do_convert_annotations": true,
   "do_normalize": true,
   "do_pad": true,
@@ -16,7 +36,6 @@
     0.224,
     0.225
   ],
-  "pad_size": null,
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {

runs/Sep02_15-50-18_Lab4/events.out.tfevents.1725263419.Lab4.15736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5deca30f565d22bade83a6ce28fa341eec7de7d0767f1d24c7a40556cf94d1
+size 6057

runs/Sep02_15-50-18_Lab4/events.out.tfevents.1725263572.Lab4.15736.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47eb96d943b14f294866855b7b3e8f2e1dba5d3a61b02c0270b499d7d46dd3b4
+size 6057

runs/Sep02_16-01-54_Lab4/events.out.tfevents.1725264115.Lab4.15568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7227acf0a7ffe521798cbc72cf67dc3ceefd14ba299e6ebaab7495b5fcfd12e3
+size 6057

runs/Sep02_17-19-45_Lab4/events.out.tfevents.1725268786.Lab4.15568.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22abadbff9706ab2cd4b9563ec5742d2acfb869cc79bdfa808b49ca0c701ee31
+size 6052

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "total_flos": 9.4894217943552e+17,
-    "train_loss": 2.403542724609375,
-    "train_runtime": 150.6018,
-    "train_samples_per_second": 13.187,
-    "train_steps_per_second": 1.66
+    "train_loss": 1.8031856994628905,
+    "train_runtime": 142.4314,
+    "train_samples_per_second": 13.944,
+    "train_steps_per_second": 1.755
 }

trainer_state.json

@@ -10,54 +10,54 @@
   "log_history": [
     {
       "epoch": 0.4,
-      "grad_norm": 33.137107849121094,
-      "learning_rate": 4.555555555555556e-05,
-      "loss": 3.3716,
+      "grad_norm": 30.619651794433594,
+      "learning_rate": 8.16e-06,
+      "loss": 1.8291,
       "step": 50
     },
     {
       "epoch": 0.8,
-      "grad_norm": 36.46946334838867,
-      "learning_rate": 3.444444444444445e-05,
-      "loss": 2.356,
+      "grad_norm": 155.9861297607422,
+      "learning_rate": 6.24e-06,
+      "loss": 1.8251,
       "step": 100
     },
     {
       "epoch": 1.2,
-      "grad_norm": 74.00175476074219,
-      "learning_rate": 2.3333333333333336e-05,
-      "loss": 2.1861,
+      "grad_norm": 59.954654693603516,
+      "learning_rate": 4.2800000000000005e-06,
+      "loss": 1.8171,
       "step": 150
     },
     {
       "epoch": 1.6,
-      "grad_norm": 65.44611358642578,
-      "learning_rate": 1.2444444444444445e-05,
-      "loss": 2.0689,
+      "grad_norm": 32.81400680541992,
+      "learning_rate": 2.28e-06,
+      "loss": 1.7688,
       "step": 200
     },
     {
       "epoch": 2.0,
-      "grad_norm": 94.77667236328125,
-      "learning_rate": 1.3333333333333334e-06,
-      "loss": 2.035,
+      "grad_norm": 64.24483489990234,
+      "learning_rate": 2.8e-07,
+      "loss": 1.7759,
       "step": 250
     },
     {
       "epoch": 2.0,
       "step": 250,
       "total_flos": 9.4894217943552e+17,
-      "train_loss": 2.403542724609375,
-      "train_runtime": 150.6018,
-      "train_samples_per_second": 13.187,
-      "train_steps_per_second": 1.66
+      "train_loss": 1.8031856994628905,
+      "train_runtime": 142.4314,
+      "train_samples_per_second": 13.944,
+      "train_steps_per_second": 1.755
     }
   ],
   "logging_steps": 50,
   "max_steps": 250,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "save_steps": 500,
+  "save_steps": 200,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b6a0cf736061a3332d7ac2d0092adbc2a6199c06b942f875b47e5ec700793d
+oid sha256:86c6259079b69f6db6635f359fa67c7a97cf9e5dba1af552f6df19457c2ac1aa
 size 5112