End of training

README.md

@@ -3,11 +3,23 @@ license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- datasets/all_binary_and_xe_ey_fae_counterfactual
 metrics:
 - accuracy
 model-index:
 - name: testing
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: datasets/all_binary_and_xe_ey_fae_counterfactual
+      type: datasets/all_binary_and_xe_ey_fae_counterfactual
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6740440005371309
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # testing
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the datasets/all_binary_and_xe_ey_fae_counterfactual dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7192
-- Accuracy: 0.6736
+- Loss: 1.7135
+- Accuracy: 0.6740
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 0.0,
     "eval_accuracy": 0.6740440005371309,
     "eval_loss": 1.7135361433029175,
-    "eval_runtime": 79.7989,
+    "eval_runtime": 79.6522,
     "eval_samples": 15525,
-    "eval_samples_per_second": 194.551,
-    "eval_steps_per_second": 24.324,
+    "eval_samples_per_second": 194.91,
+    "eval_steps_per_second": 24.368,
     "perplexity": 5.548547286429599,
     "train_loss": 1.9919448852539063,
-    "train_runtime": 161.5625,
+    "train_runtime": 161.1653,
     "train_samples": 124124,
-    "train_samples_per_second": 0.99,
+    "train_samples_per_second": 0.993,
     "train_steps_per_second": 0.062
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 0.0,
     "eval_accuracy": 0.6740440005371309,
     "eval_loss": 1.7135361433029175,
-    "eval_runtime": 79.7989,
+    "eval_runtime": 79.6522,
     "eval_samples": 15525,
-    "eval_samples_per_second": 194.551,
-    "eval_steps_per_second": 24.324,
+    "eval_samples_per_second": 194.91,
+    "eval_steps_per_second": 24.368,
     "perplexity": 5.548547286429599
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0,
     "train_loss": 1.9919448852539063,
-    "train_runtime": 161.5625,
+    "train_runtime": 161.1653,
     "train_samples": 124124,
-    "train_samples_per_second": 0.99,
+    "train_samples_per_second": 0.993,
     "train_steps_per_second": 0.062
 }

trainer_state.json

@@ -18,9 +18,9 @@
       "epoch": 0.0,
       "eval_accuracy": 0.6649938341745655,
       "eval_loss": 1.775834321975708,
-      "eval_runtime": 78.8594,
-      "eval_samples_per_second": 196.869,
-      "eval_steps_per_second": 24.613,
+      "eval_runtime": 78.6312,
+      "eval_samples_per_second": 197.441,
+      "eval_steps_per_second": 24.685,
       "step": 5
     },
     {
@@ -33,9 +33,9 @@
       "epoch": 0.0,
       "eval_accuracy": 0.6735738398990131,
       "eval_loss": 1.719245433807373,
-      "eval_runtime": 79.7924,
-      "eval_samples_per_second": 194.567,
-      "eval_steps_per_second": 24.326,
+      "eval_runtime": 79.5982,
+      "eval_samples_per_second": 195.042,
+      "eval_steps_per_second": 24.385,
       "step": 10
     },
     {
@@ -43,8 +43,8 @@
       "step": 10,
       "total_flos": 42112770048000.0,
       "train_loss": 1.9919448852539063,
-      "train_runtime": 161.5625,
-      "train_samples_per_second": 0.99,
+      "train_runtime": 161.1653,
+      "train_samples_per_second": 0.993,
       "train_steps_per_second": 0.062
     }
   ],