End of training

README.md

@@ -2,6 +2,8 @@
 license: other
 base_model: nvidia/mit-b0
 tags:
+- image-segmentation
+- vision
 - generated_from_trainer
 model-index:
 - name: Segments
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Segments
 
-This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the segments/sidewalk-semantic dataset.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,5 @@
 {
-    "epoch": 19.81,
+    "epoch": 0.99,
     "eval_accuracy_construction-bridge": 0.0,
     "eval_accuracy_construction-building": 0.9044887536731845,
     "eval_accuracy_construction-door": 0.0,
@@ -77,8 +77,8 @@
     "eval_runtime": 166.5888,
     "eval_samples_per_second": 0.9,
     "eval_steps_per_second": 0.114,
-    "train_loss": 1.3936616789619878,
-    "train_runtime": 1998.0806,
-    "train_samples_per_second": 8.508,
-    "train_steps_per_second": 0.531
+    "train_loss": 3.0431386119914503,
+    "train_runtime": 103.8023,
+    "train_samples_per_second": 8.189,
+    "train_steps_per_second": 0.511
 }

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 19.81,
-    "train_loss": 1.3936616789619878,
-    "train_runtime": 1998.0806,
-    "train_samples_per_second": 8.508,
-    "train_steps_per_second": 0.531
+    "epoch": 0.99,
+    "train_loss": 3.0431386119914503,
+    "train_runtime": 103.8023,
+    "train_samples_per_second": 8.189,
+    "train_steps_per_second": 0.511
 }

trainer_state.json

@@ -1,40 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.813084112149532,
+  "epoch": 0.9906542056074766,
   "eval_steps": 500,
-  "global_step": 1060,
+  "global_step": 53,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 9.35,
-      "learning_rate": 2.641509433962264e-05,
-      "loss": 1.7451,
-      "step": 500
-    },
-    {
-      "epoch": 18.69,
-      "learning_rate": 2.830188679245283e-06,
-      "loss": 1.087,
-      "step": 1000
-    },
-    {
-      "epoch": 19.81,
-      "step": 1060,
-      "total_flos": 2.9595008832425165e+17,
-      "train_loss": 1.3936616789619878,
-      "train_runtime": 1998.0806,
-      "train_samples_per_second": 8.508,
-      "train_steps_per_second": 0.531
+      "epoch": 0.99,
+      "step": 53,
+      "total_flos": 1.4897641867444224e+16,
+      "train_loss": 3.0431386119914503,
+      "train_runtime": 103.8023,
+      "train_samples_per_second": 8.189,
+      "train_steps_per_second": 0.511
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1060,
-  "num_train_epochs": 20,
+  "max_steps": 53,
+  "num_train_epochs": 1,
   "save_steps": 200,
-  "total_flos": 2.9595008832425165e+17,
+  "total_flos": 1.4897641867444224e+16,
   "trial_name": null,
   "trial_params": null
 }