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_128
-  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: 0.07807518032045319
 ---
 
 <!-- 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_128
 
-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: 10.0781
 - Accuracy: 0.0781

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.025573961057832027,
+    "eval_accuracy": 0.07807518032045319,
+    "eval_loss": 10.078125,
+    "eval_runtime": 263.2075,
+    "eval_samples": 33767,
+    "eval_samples_per_second": 128.29,
+    "eval_steps_per_second": 2.675,
+    "perplexity": 23816.28811114398,
+    "total_flos": 247015648788480.0,
+    "train_loss": 10.390092329545455,
+    "train_runtime": 94034.2968,
+    "train_samples": 660643,
+    "train_samples_per_second": 702.555,
+    "train_steps_per_second": 14.637
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.025573961057832027,
+    "eval_accuracy": 0.07807518032045319,
+    "eval_loss": 10.078125,
+    "eval_runtime": 263.2075,
+    "eval_samples": 33767,
+    "eval_samples_per_second": 128.29,
+    "eval_steps_per_second": 2.675,
+    "perplexity": 23816.28811114398
+}

logs/events.out.tfevents.1719936452.s_005_m.77188.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7156aa810215abe99cde784be3683644b2711b83b429da4f2adad674e057bbf
+size 363

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.025573961057832027,
+    "total_flos": 247015648788480.0,
+    "train_loss": 10.390092329545455,
+    "train_runtime": 94034.2968,
+    "train_samples": 660643,
+    "train_samples_per_second": 702.555,
+    "train_steps_per_second": 14.637
+}