End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- akahana/GlotCC-V1-jav-Latn-content-only
+metrics:
+- accuracy
 model-index:
 - name: tinybert-javanese
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: akahana/GlotCC-V1-jav-Latn-content-only default
+      type: akahana/GlotCC-V1-jav-Latn-content-only
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.1400072934534502
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,7 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinybert-javanese
 
-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 akahana/GlotCC-V1-jav-Latn-content-only default dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.2427
+- Accuracy: 0.1400
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 50.0,
-    "eval_accuracy": 0.1519208618470086,
-    "eval_loss": 5.8251872062683105,
-    "eval_runtime": 11.1208,
+    "epoch": 30.0,
+    "eval_accuracy": 0.1400072934534502,
+    "eval_loss": 6.242714881896973,
+    "eval_runtime": 11.5498,
     "eval_samples": 3852,
-    "eval_samples_per_second": 346.376,
-    "eval_steps_per_second": 86.594,
-    "perplexity": 338.7245384996336,
-    "total_flos": 5161725447936000.0,
-    "train_loss": 6.140905278960581,
-    "train_runtime": 7883.0646,
+    "eval_samples_per_second": 333.512,
+    "eval_steps_per_second": 83.378,
+    "perplexity": 514.2527529747575,
+    "total_flos": 781486986700800.0,
+    "train_loss": 6.528281962779993,
+    "train_runtime": 3948.1737,
     "train_samples": 76378,
-    "train_samples_per_second": 484.444,
-    "train_steps_per_second": 30.28
+    "train_samples_per_second": 580.354,
+    "train_steps_per_second": 18.137
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 50.0,
-    "eval_accuracy": 0.1519208618470086,
-    "eval_loss": 5.8251872062683105,
-    "eval_runtime": 11.1208,
+    "epoch": 30.0,
+    "eval_accuracy": 0.1400072934534502,
+    "eval_loss": 6.242714881896973,
+    "eval_runtime": 11.5498,
     "eval_samples": 3852,
-    "eval_samples_per_second": 346.376,
-    "eval_steps_per_second": 86.594,
-    "perplexity": 338.7245384996336
+    "eval_samples_per_second": 333.512,
+    "eval_steps_per_second": 83.378,
+    "perplexity": 514.2527529747575
 }

runs/Aug03_01-12-12_9eaebf5603b2/events.out.tfevents.1722651590.9eaebf5603b2.1249.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b7c7d6c246c448a7a4bf8225ad4de66e7796d2e7beeb7940a0279e142deb5d
+size 417

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 50.0,
-    "total_flos": 5161725447936000.0,
-    "train_loss": 6.140905278960581,
-    "train_runtime": 7883.0646,
+    "epoch": 30.0,
+    "total_flos": 781486986700800.0,
+    "train_loss": 6.528281962779993,
+    "train_runtime": 3948.1737,
     "train_samples": 76378,
-    "train_samples_per_second": 484.444,
-    "train_steps_per_second": 30.28
+    "train_samples_per_second": 580.354,
+    "train_steps_per_second": 18.137
 }