End of training

README.md

@@ -3,11 +3,23 @@ license: mit
 base_model: openai-community/gpt2
 tags:
 - generated_from_trainer
+datasets:
+- gokuls/wiki_book_corpus_raw_dataset_tiny
 metrics:
 - accuracy
 model-index:
 - name: gpt_train_12_384
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: gokuls/wiki_book_corpus_raw_dataset_tiny
+      type: gokuls/wiki_book_corpus_raw_dataset_tiny
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.10244681503029747
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt_train_12_384
 
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the gokuls/wiki_book_corpus_raw_dataset_tiny dataset.
 It achieves the following results on the evaluation set:
 - Loss: 8.8125
 - Accuracy: 0.1024

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.016516516516516516,
+    "eval_accuracy": 0.10244681503029747,
+    "eval_loss": 8.8125,
+    "eval_runtime": 271.7768,
+    "eval_samples": 33767,
+    "eval_samples_per_second": 124.245,
+    "eval_steps_per_second": 3.886,
+    "perplexity": 6717.692523019596,
+    "total_flos": 1427643152990208.0,
+    "train_loss": 9.567586143695015,
+    "train_runtime": 93928.2806,
+    "train_samples": 660643,
+    "train_samples_per_second": 703.348,
+    "train_steps_per_second": 21.981
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.016516516516516516,
+    "eval_accuracy": 0.10244681503029747,
+    "eval_loss": 8.8125,
+    "eval_runtime": 271.7768,
+    "eval_samples": 33767,
+    "eval_samples_per_second": 124.245,
+    "eval_steps_per_second": 3.886,
+    "perplexity": 6717.692523019596
+}

logs/events.out.tfevents.1719936280.s_005_m.77168.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9629f0683df0f70f7d93390236256b0680384aaf97970279c54610c3693d36
+size 363

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.016516516516516516,
+    "total_flos": 1427643152990208.0,
+    "train_loss": 9.567586143695015,
+    "train_runtime": 93928.2806,
+    "train_samples": 660643,
+    "train_samples_per_second": 703.348,
+    "train_steps_per_second": 21.981
+}