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

@@ -1,15 +1,15 @@
 {
     "epoch": 0.0,
-    "eval_accuracy": 0.6748837865685497,
-    "eval_loss": 1.6915348768234253,
-    "eval_runtime": 75.3619,
-    "eval_samples": 15520,
-    "eval_samples_per_second": 205.94,
-    "eval_steps_per_second": 25.742,
-    "perplexity": 5.427805327461157,
-    "train_loss": 1.9789411544799804,
-    "train_runtime": 156.255,
-    "train_samples": 124120,
-    "train_samples_per_second": 1.024,
-    "train_steps_per_second": 0.064
+    "eval_accuracy": 0.6740440005371309,
+    "eval_loss": 1.7135361433029175,
+    "eval_runtime": 78.7535,
+    "eval_samples": 15525,
+    "eval_samples_per_second": 197.134,
+    "eval_steps_per_second": 24.647,
+    "perplexity": 5.548547286429599,
+    "train_loss": 1.9919448852539063,
+    "train_runtime": 160.975,
+    "train_samples": 124124,
+    "train_samples_per_second": 0.994,
+    "train_steps_per_second": 0.062
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.0,
-    "eval_accuracy": 0.6748837865685497,
-    "eval_loss": 1.6915348768234253,
-    "eval_runtime": 75.3619,
-    "eval_samples": 15520,
-    "eval_samples_per_second": 205.94,
-    "eval_steps_per_second": 25.742,
-    "perplexity": 5.427805327461157
+    "eval_accuracy": 0.6740440005371309,
+    "eval_loss": 1.7135361433029175,
+    "eval_runtime": 78.7535,
+    "eval_samples": 15525,
+    "eval_samples_per_second": 197.134,
+    "eval_steps_per_second": 24.647,
+    "perplexity": 5.548547286429599
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0,
-    "train_loss": 1.9789411544799804,
-    "train_runtime": 156.255,
-    "train_samples": 124120,
-    "train_samples_per_second": 1.024,
-    "train_steps_per_second": 0.064
+    "train_loss": 1.9919448852539063,
+    "train_runtime": 160.975,
+    "train_samples": 124124,
+    "train_samples_per_second": 0.994,
+    "train_steps_per_second": 0.062
 }

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012890750886239124,
+  "epoch": 0.001288992008249549,
   "eval_steps": 5,
   "global_step": 10,
   "is_hyper_param_search": false,
@@ -11,41 +11,41 @@
     {
       "epoch": 0.0,
       "learning_rate": 5e-05,
-      "loss": 2.0686,
+      "loss": 2.068,
       "step": 5
     },
     {
       "epoch": 0.0,
-      "eval_accuracy": 0.6686630088781412,
-      "eval_loss": 1.7577065229415894,
-      "eval_runtime": 76.2786,
-      "eval_samples_per_second": 203.465,
-      "eval_steps_per_second": 25.433,
+      "eval_accuracy": 0.6649938341745655,
+      "eval_loss": 1.775834321975708,
+      "eval_runtime": 78.5903,
+      "eval_samples_per_second": 197.544,
+      "eval_steps_per_second": 24.698,
       "step": 5
     },
     {
       "epoch": 0.0,
       "learning_rate": 0.0,
-      "loss": 1.8893,
+      "loss": 1.9159,
       "step": 10
     },
     {
       "epoch": 0.0,
-      "eval_accuracy": 0.6742729158223068,
-      "eval_loss": 1.6961551904678345,
-      "eval_runtime": 76.8494,
-      "eval_samples_per_second": 201.953,
-      "eval_steps_per_second": 25.244,
+      "eval_accuracy": 0.6735738398990131,
+      "eval_loss": 1.719245433807373,
+      "eval_runtime": 79.477,
+      "eval_samples_per_second": 195.339,
+      "eval_steps_per_second": 24.422,
       "step": 10
     },
     {
       "epoch": 0.0,
       "step": 10,
       "total_flos": 42112770048000.0,
-      "train_loss": 1.9789411544799804,
-      "train_runtime": 156.255,
-      "train_samples_per_second": 1.024,
-      "train_steps_per_second": 0.064
+      "train_loss": 1.9919448852539063,
+      "train_runtime": 160.975,
+      "train_samples_per_second": 0.994,
+      "train_steps_per_second": 0.062
     }
   ],
   "logging_steps": 5,