End of training

README.md

@@ -4,11 +4,23 @@ license: apache-2.0
 base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- gokulsrinivasagan/processed_book_corpus-ld
 metrics:
 - accuracy
 model-index:
 - name: distilbert_base_train_book_v2
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: gokulsrinivasagan/processed_book_corpus-ld
+      type: gokulsrinivasagan/processed_book_corpus-ld
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7300233078924688
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,9 +28,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_base_train_book_v2
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the gokulsrinivasagan/processed_book_corpus-ld dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2005
+- Loss: 1.2024
 - Accuracy: 0.7300
 
 ## Model description

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 25.0,
+    "eval_accuracy": 0.7300233078924688,
+    "eval_loss": 1.202447533607483,
+    "eval_runtime": 143.1897,
+    "eval_samples": 120706,
+    "eval_samples_per_second": 842.98,
+    "eval_steps_per_second": 5.273,
+    "perplexity": 3.328252973052478,
+    "total_flos": 7.547177208649421e+18,
+    "train_loss": 1.849292092869351,
+    "train_runtime": 122993.5623,
+    "train_samples": 2277342,
+    "train_samples_per_second": 462.899,
+    "train_steps_per_second": 2.893
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 25.0,
+    "eval_accuracy": 0.7300233078924688,
+    "eval_loss": 1.202447533607483,
+    "eval_runtime": 143.1897,
+    "eval_samples": 120706,
+    "eval_samples_per_second": 842.98,
+    "eval_steps_per_second": 5.273,
+    "perplexity": 3.328252973052478
+}

logs/events.out.tfevents.1738218533.ki-g0009.121324.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8489158806c095b7ea29528202a5b058b0bb8aae32ca47a806d2edcdc6e30834
+size 417

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 25.0,
+    "total_flos": 7.547177208649421e+18,
+    "train_loss": 1.849292092869351,
+    "train_runtime": 122993.5623,
+    "train_samples": 2277342,
+    "train_samples_per_second": 462.899,
+    "train_steps_per_second": 2.893
+}