End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- akahana/GlotCC-V1-jav-Latn
+metrics:
+- accuracy
 model-index:
 - name: roberta-javanese
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: akahana/GlotCC-V1-jav-Latn default
+      type: akahana/GlotCC-V1-jav-Latn
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.14735192890532697
 ---
 
 <!-- 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. -->
 
 # roberta-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 default dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.4370
+- Accuracy: 0.1474
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.14504326392276684,
-    "eval_loss": 6.46232795715332,
-    "eval_runtime": 30.9776,
+    "eval_accuracy": 0.14735192890532697,
+    "eval_loss": 6.437006950378418,
+    "eval_runtime": 32.2258,
     "eval_samples": 4053,
-    "eval_samples_per_second": 130.836,
-    "eval_steps_per_second": 32.733,
-    "perplexity": 640.550496330922,
+    "eval_samples_per_second": 125.769,
+    "eval_steps_per_second": 31.465,
+    "perplexity": 624.5347361636025,
     "total_flos": 2.639861525017728e+16,
-    "train_loss": 5.285465436767286,
-    "train_runtime": 6500.188,
+    "train_loss": 0.0,
+    "train_runtime": 0.014,
     "train_samples": 80219,
-    "train_samples_per_second": 61.705,
-    "train_steps_per_second": 3.857
+    "train_samples_per_second": 28664900.797,
+    "train_steps_per_second": 1791667.966
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.14504326392276684,
-    "eval_loss": 6.46232795715332,
-    "eval_runtime": 30.9776,
+    "eval_accuracy": 0.14735192890532697,
+    "eval_loss": 6.437006950378418,
+    "eval_runtime": 32.2258,
     "eval_samples": 4053,
-    "eval_samples_per_second": 130.836,
-    "eval_steps_per_second": 32.733,
-    "perplexity": 640.550496330922
+    "eval_samples_per_second": 125.769,
+    "eval_steps_per_second": 31.465,
+    "perplexity": 624.5347361636025
 }

runs/Jul12_22-11-43_6b2d4ff0fae4/events.out.tfevents.1720822417.6b2d4ff0fae4.1295.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4b45dd1980bd8e6957f5ff9cc4ea38f12528662383d657cf322e70ec109df4
+size 417

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
     "total_flos": 2.639861525017728e+16,
-    "train_loss": 5.285465436767286,
-    "train_runtime": 6500.188,
+    "train_loss": 0.0,
+    "train_runtime": 0.014,
     "train_samples": 80219,
-    "train_samples_per_second": 61.705,
-    "train_steps_per_second": 3.857
+    "train_samples_per_second": 28664900.797,
+    "train_steps_per_second": 1791667.966
 }

trainer_state.json

@@ -366,6 +366,15 @@
       "train_runtime": 6500.188,
       "train_samples_per_second": 61.705,
       "train_steps_per_second": 3.857
+    },
+    {
+      "epoch": 5.0,
+      "step": 25070,
+      "total_flos": 2.639861525017728e+16,
+      "train_loss": 0.0,
+      "train_runtime": 0.014,
+      "train_samples_per_second": 28664900.797,
+      "train_steps_per_second": 1791667.966
     }
   ],
   "logging_steps": 500,