End of training

README.md

@@ -1,11 +1,23 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
 metrics:
 - accuracy
 model-index:
 - name: smolm-autoreg-bpe-counterfactual-babylm-indef_articles_with_pl_nouns_removal-1e-3
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
+      type: kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.41252109443859236
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # smolm-autoreg-bpe-counterfactual-babylm-indef_articles_with_pl_nouns_removal-1e-3
 
-This model was trained from scratch on an unknown dataset.
+This model was trained from scratch on the kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.4176
 - Accuracy: 0.4125

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.41252109443859236,
+    "eval_loss": 3.417576313018799,
+    "eval_runtime": 147.5666,
+    "eval_samples": 57920,
+    "eval_samples_per_second": 392.501,
+    "eval_steps_per_second": 6.133,
+    "perplexity": 30.495414041670983,
+    "train_loss": 2.994195082282441,
+    "train_runtime": 55239.7487,
+    "train_samples": 595216,
+    "train_samples_per_second": 215.503,
+    "train_steps_per_second": 13.469
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.41252109443859236,
+    "eval_loss": 3.417576313018799,
+    "eval_runtime": 147.5666,
+    "eval_samples": 57920,
+    "eval_samples_per_second": 392.501,
+    "eval_steps_per_second": 6.133,
+    "perplexity": 30.495414041670983
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 2.994195082282441,
+    "train_runtime": 55239.7487,
+    "train_samples": 595216,
+    "train_samples_per_second": 215.503,
+    "train_steps_per_second": 13.469
+}