End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+trainer_state.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -3,11 +3,23 @@ license: apache-2.0
 base_model: bert-large-uncased
 tags:
 - generated_from_trainer
+datasets:
+- gokuls/wiki_book_corpus_complete_processed_bert_dataset
 metrics:
 - accuracy
 model-index:
 - name: BERT_pretraining_h_100_wo_deepspeed
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: gokuls/wiki_book_corpus_complete_processed_bert_dataset
+      type: gokuls/wiki_book_corpus_complete_processed_bert_dataset
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.15387755648267093
 ---
 
 <!-- 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. -->
 
 # BERT_pretraining_h_100_wo_deepspeed
 
-This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.7886
-- Accuracy: 0.1537
+- Loss: 5.7778
+- Accuracy: 0.1539
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.38,
+    "eval_accuracy": 0.15387755648267093,
+    "eval_loss": 5.777781009674072,
+    "eval_runtime": 1304.9893,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 236.29,
+    "eval_steps_per_second": 1.136,
+    "perplexity": 323.04156839839476,
+    "train_loss": 6.089181384976974,
+    "train_runtime": 360000.8199,
+    "train_samples": 5858758,
+    "train_samples_per_second": 1627.429,
+    "train_steps_per_second": 7.824
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 7.38,
+    "eval_accuracy": 0.15387755648267093,
+    "eval_loss": 5.777781009674072,
+    "eval_runtime": 1304.9893,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 236.29,
+    "eval_steps_per_second": 1.136,
+    "perplexity": 323.04156839839476
+}

logs/events.out.tfevents.1708112140.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c431ae2685a054d2fb5033133a6e1e1f16c0433f5bd6327d451630ada4a1e5c
+size 40

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.38,
+    "train_loss": 6.089181384976974,
+    "train_runtime": 360000.8199,
+    "train_samples": 5858758,
+    "train_samples_per_second": 1627.429,
+    "train_steps_per_second": 7.824
+}

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e603f20753ed7e32845b1bccb707eba2db0f1b7a9291e53eb512fa206c929a
+size 24872636