End of training

README.md

@@ -1,6 +1,8 @@
 ---
 base_model: microsoft/dit-base-finetuned-rvlcdip
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - f1
@@ -16,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- F1: 0.9705
-- Loss: 0.0391
+- Loss: 0.0385
+- F1: 0.6332
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
-    "eval_f1": 0.9557601497125016,
+    "eval_f1": 0.6331799591002044,
     "eval_loss": 0.038467586040496826,
-    "eval_runtime": 795.0811,
-    "eval_samples_per_second": 259.423,
-    "eval_steps_per_second": 2.027,
+    "eval_runtime": 570.2428,
+    "eval_samples_per_second": 361.709,
+    "eval_steps_per_second": 2.827,
     "total_flos": 9.82152667464321e+19,
     "train_loss": 0.0,
-    "train_runtime": 0.0939,
-    "train_samples_per_second": 13490351.86,
-    "train_steps_per_second": 105438.282
+    "train_runtime": 0.0648,
+    "train_samples_per_second": 19542495.273,
+    "train_steps_per_second": 152740.8
 }

config.json

@@ -48,6 +48,7 @@
     3,
     6
   ],
+  "problem_type": "regression",
   "reshape_hidden_states": true,
   "semantic_loss_ignore_index": 255,
   "stage_names": [

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "eval_f1": 0.9557601497125016,
+    "eval_f1": 0.6331799591002044,
     "eval_loss": 0.038467586040496826,
-    "eval_runtime": 795.0811,
-    "eval_samples_per_second": 259.423,
-    "eval_steps_per_second": 2.027
+    "eval_runtime": 570.2428,
+    "eval_samples_per_second": 361.709,
+    "eval_steps_per_second": 2.827
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "total_flos": 9.82152667464321e+19,
     "train_loss": 0.0,
-    "train_runtime": 0.0939,
-    "train_samples_per_second": 13490351.86,
-    "train_steps_per_second": 105438.282
+    "train_runtime": 0.0648,
+    "train_samples_per_second": 19542495.273,
+    "train_steps_per_second": 152740.8
 }

trainer_state.json

@@ -6988,9 +6988,9 @@
       "step": 9905,
       "total_flos": 9.82152667464321e+19,
       "train_loss": 0.0,
-      "train_runtime": 0.0939,
-      "train_samples_per_second": 13490351.86,
-      "train_steps_per_second": 105438.282
+      "train_runtime": 0.0648,
+      "train_samples_per_second": 19542495.273,
+      "train_steps_per_second": 152740.8
     }
   ],
   "logging_steps": 10,