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

@@ -2,15 +2,15 @@
     "epoch": 5.0,
     "eval_accuracy": 0.14735192890532697,
     "eval_loss": 6.437006950378418,
-    "eval_runtime": 32.2258,
+    "eval_runtime": 32.1887,
     "eval_samples": 4053,
-    "eval_samples_per_second": 125.769,
-    "eval_steps_per_second": 31.465,
+    "eval_samples_per_second": 125.914,
+    "eval_steps_per_second": 31.502,
     "perplexity": 624.5347361636025,
     "total_flos": 2.639861525017728e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.014,
+    "train_runtime": 0.0088,
     "train_samples": 80219,
-    "train_samples_per_second": 28664900.797,
-    "train_steps_per_second": 1791667.966
+    "train_samples_per_second": 45629508.88,
+    "train_steps_per_second": 2852022.059
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 5.0,
     "eval_accuracy": 0.14735192890532697,
     "eval_loss": 6.437006950378418,
-    "eval_runtime": 32.2258,
+    "eval_runtime": 32.1887,
     "eval_samples": 4053,
-    "eval_samples_per_second": 125.769,
-    "eval_steps_per_second": 31.465,
+    "eval_samples_per_second": 125.914,
+    "eval_steps_per_second": 31.502,
     "perplexity": 624.5347361636025
 }

runs/Jul12_22-14-05_6b2d4ff0fae4/events.out.tfevents.1720822500.6b2d4ff0fae4.1951.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10748fd24f71de06628443303f26bd47042625b8c64697fccd7c049c123a98b
+size 417

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 5.0,
     "total_flos": 2.639861525017728e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.014,
+    "train_runtime": 0.0088,
     "train_samples": 80219,
-    "train_samples_per_second": 28664900.797,
-    "train_steps_per_second": 1791667.966
+    "train_samples_per_second": 45629508.88,
+    "train_steps_per_second": 2852022.059
 }

trainer_state.json

@@ -372,9 +372,9 @@
       "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
+      "train_runtime": 0.0088,
+      "train_samples_per_second": 45629508.88,
+      "train_steps_per_second": 2852022.059
     }
   ],
   "logging_steps": 500,