End of training

README.md

@@ -2,9 +2,11 @@
 license: apache-2.0
 base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
-- accuracy
+- f1
 model-index:
 - name: donut-base-beans
   results: []
@@ -17,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.4973
-- Loss: 0.0527
+- Loss: 0.0508
+- F1: 0.4973
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.49727767695099817,
-    "eval_f1": 0.0,
+    "eval_f1": 0.49727767695099817,
     "eval_loss": 0.05081513151526451,
-    "eval_runtime": 972.1481,
-    "eval_samples_per_second": 39.108,
-    "eval_steps_per_second": 2.445,
+    "eval_runtime": 147.4767,
+    "eval_samples_per_second": 257.797,
+    "eval_steps_per_second": 2.021,
     "total_flos": 1.6687666486602124e+20,
     "train_loss": 0.0,
-    "train_runtime": 6.1126,
-    "train_samples_per_second": 352456.018,
-    "train_steps_per_second": 5508.327
+    "train_runtime": 6.8845,
+    "train_samples_per_second": 156467.844,
+    "train_steps_per_second": 2445.343
 }

config.json

@@ -42,6 +42,7 @@
     3,
     6
   ],
+  "problem_type": "regression",
   "reshape_hidden_states": true,
   "semantic_loss_ignore_index": 255,
   "stage_names": [

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "eval_f1": 0.0,
+    "eval_f1": 0.49727767695099817,
     "eval_loss": 0.05081513151526451,
-    "eval_runtime": 972.1481,
-    "eval_samples_per_second": 39.108,
-    "eval_steps_per_second": 2.445
+    "eval_runtime": 147.4767,
+    "eval_samples_per_second": 257.797,
+    "eval_steps_per_second": 2.021
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 10.0,
     "total_flos": 1.6687666486602124e+20,
     "train_loss": 0.0,
-    "train_runtime": 6.1126,
-    "train_samples_per_second": 352456.018,
-    "train_steps_per_second": 5508.327
+    "train_runtime": 6.8845,
+    "train_samples_per_second": 156467.844,
+    "train_steps_per_second": 2445.343
 }

trainer_state.json

@@ -23672,15 +23672,15 @@
       "step": 33670,
       "total_flos": 1.6687666486602124e+20,
       "train_loss": 0.0,
-      "train_runtime": 6.1126,
-      "train_samples_per_second": 352456.018,
-      "train_steps_per_second": 5508.327
+      "train_runtime": 6.8845,
+      "train_samples_per_second": 156467.844,
+      "train_steps_per_second": 2445.343
     }
   ],
   "logging_steps": 10,
-  "max_steps": 33670,
+  "max_steps": 16835,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {