End of training

README.md

@@ -1,9 +1,23 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- gokuls/wiki_book_corpus_complete_processed_bert_dataset
+metrics:
+- accuracy
 model-index:
 - name: model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_2
-  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: 0.3842983143791092
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,7 +25,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_2
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.7039
+- Accuracy: 0.3843
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 13.8,
+    "eval_accuracy": 0.3842983143791092,
+    "eval_loss": 3.703929901123047,
+    "eval_runtime": 491.0314,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 627.976,
+    "eval_steps_per_second": 3.491,
+    "perplexity": 40.60657101301762,
+    "train_loss": 4.181136763339477,
+    "train_runtime": 190799.4817,
+    "train_samples": 5858758,
+    "train_samples_per_second": 3070.636,
+    "train_steps_per_second": 17.059
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 13.8,
+    "eval_accuracy": 0.3842983143791092,
+    "eval_loss": 3.703929901123047,
+    "eval_runtime": 491.0314,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 627.976,
+    "eval_steps_per_second": 3.491,
+    "perplexity": 40.60657101301762
+}

logs/events.out.tfevents.1700444446.serv-9220.3432283.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5258ee325d9971f2be9e19ad68801680f1f8e25fe54950fcaea9d1a1f59cb05
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 13.8,
+    "train_loss": 4.181136763339477,
+    "train_runtime": 190799.4817,
+    "train_samples": 5858758,
+    "train_samples_per_second": 3070.636,
+    "train_steps_per_second": 17.059
+}