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: 0.16528946828166702
 ---
 
 <!-- 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: 6.0064
+- Accuracy: 0.1653
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.14735192890532697,
-    "eval_loss": 6.437006950378418,
-    "eval_runtime": 32.1887,
+    "epoch": 8.0,
+    "eval_accuracy": 0.16528946828166702,
+    "eval_loss": 6.006351470947266,
+    "eval_runtime": 28.9332,
     "eval_samples": 4053,
-    "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": 0.0088,
+    "eval_samples_per_second": 140.081,
+    "eval_steps_per_second": 35.046,
+    "perplexity": 405.99931440686527,
+    "total_flos": 4.223778440028365e+16,
+    "train_loss": 2.356345704317949,
+    "train_runtime": 3822.1574,
     "train_samples": 80219,
-    "train_samples_per_second": 45629508.88,
-    "train_steps_per_second": 2852022.059
+    "train_samples_per_second": 167.903,
+    "train_steps_per_second": 10.495
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.14735192890532697,
-    "eval_loss": 6.437006950378418,
-    "eval_runtime": 32.1887,
+    "epoch": 8.0,
+    "eval_accuracy": 0.16528946828166702,
+    "eval_loss": 6.006351470947266,
+    "eval_runtime": 28.9332,
     "eval_samples": 4053,
-    "eval_samples_per_second": 125.914,
-    "eval_steps_per_second": 31.502,
-    "perplexity": 624.5347361636025
+    "eval_samples_per_second": 140.081,
+    "eval_steps_per_second": 35.046,
+    "perplexity": 405.99931440686527
 }

runs/Jul12_22-15-22_6b2d4ff0fae4/events.out.tfevents.1720826418.6b2d4ff0fae4.2315.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2115f7e967f854d07cf94877bdb52cbf1ec524233de60bab2ea57c6dde3d51a8
+size 417

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 5.0,
-    "total_flos": 2.639861525017728e+16,
-    "train_loss": 0.0,
-    "train_runtime": 0.0088,
+    "epoch": 8.0,
+    "total_flos": 4.223778440028365e+16,
+    "train_loss": 2.356345704317949,
+    "train_runtime": 3822.1574,
     "train_samples": 80219,
-    "train_samples_per_second": 45629508.88,
-    "train_steps_per_second": 2852022.059
+    "train_samples_per_second": 167.903,
+    "train_steps_per_second": 10.495
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 25070,
+  "global_step": 40112,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -368,19 +368,229 @@
       "train_steps_per_second": 3.857
     },
     {
-      "epoch": 5.0,
-      "step": 25070,
-      "total_flos": 2.639861525017728e+16,
-      "train_loss": 0.0,
-      "train_runtime": 0.0088,
-      "train_samples_per_second": 45629508.88,
-      "train_steps_per_second": 2852022.059
+      "epoch": 5.085759872357399,
+      "grad_norm": 3.5418105125427246,
+      "learning_rate": 4.946400079776626e-05,
+      "loss": 6.5458,
+      "step": 25500
+    },
+    {
+      "epoch": 5.1854806541683285,
+      "grad_norm": 4.323005676269531,
+      "learning_rate": 4.884074591144795e-05,
+      "loss": 6.5604,
+      "step": 26000
+    },
+    {
+      "epoch": 5.285201435979258,
+      "grad_norm": 4.445618629455566,
+      "learning_rate": 4.8217491025129644e-05,
+      "loss": 6.5452,
+      "step": 26500
+    },
+    {
+      "epoch": 5.384922217790187,
+      "grad_norm": 4.320890426635742,
+      "learning_rate": 4.759423613881133e-05,
+      "loss": 6.5239,
+      "step": 27000
+    },
+    {
+      "epoch": 5.484642999601117,
+      "grad_norm": 3.8980209827423096,
+      "learning_rate": 4.697098125249302e-05,
+      "loss": 6.5278,
+      "step": 27500
+    },
+    {
+      "epoch": 5.584363781412046,
+      "grad_norm": 4.074916362762451,
+      "learning_rate": 4.6347726366174716e-05,
+      "loss": 6.5044,
+      "step": 28000
+    },
+    {
+      "epoch": 5.684084563222975,
+      "grad_norm": 4.465285778045654,
+      "learning_rate": 4.572447147985641e-05,
+      "loss": 6.472,
+      "step": 28500
+    },
+    {
+      "epoch": 5.783805345033905,
+      "grad_norm": 4.351347923278809,
+      "learning_rate": 4.5101216593538095e-05,
+      "loss": 6.4504,
+      "step": 29000
+    },
+    {
+      "epoch": 5.883526126844835,
+      "grad_norm": 4.14565372467041,
+      "learning_rate": 4.447796170721978e-05,
+      "loss": 6.4375,
+      "step": 29500
+    },
+    {
+      "epoch": 5.983246908655763,
+      "grad_norm": 4.669959545135498,
+      "learning_rate": 4.3854706820901474e-05,
+      "loss": 6.4393,
+      "step": 30000
+    },
+    {
+      "epoch": 6.082967690466694,
+      "grad_norm": 4.345717430114746,
+      "learning_rate": 4.323145193458317e-05,
+      "loss": 6.3808,
+      "step": 30500
+    },
+    {
+      "epoch": 6.182688472277623,
+      "grad_norm": 4.040054798126221,
+      "learning_rate": 4.260819704826486e-05,
+      "loss": 6.3705,
+      "step": 31000
+    },
+    {
+      "epoch": 6.282409254088552,
+      "grad_norm": 4.663171291351318,
+      "learning_rate": 4.198618867171919e-05,
+      "loss": 6.3803,
+      "step": 31500
+    },
+    {
+      "epoch": 6.382130035899482,
+      "grad_norm": 4.45890474319458,
+      "learning_rate": 4.136293378540088e-05,
+      "loss": 6.3256,
+      "step": 32000
+    },
+    {
+      "epoch": 6.481850817710411,
+      "grad_norm": 4.158110618591309,
+      "learning_rate": 4.073967889908257e-05,
+      "loss": 6.3351,
+      "step": 32500
+    },
+    {
+      "epoch": 6.58157159952134,
+      "grad_norm": 4.460795879364014,
+      "learning_rate": 4.0116424012764265e-05,
+      "loss": 6.3137,
+      "step": 33000
+    },
+    {
+      "epoch": 6.68129238133227,
+      "grad_norm": 4.767895221710205,
+      "learning_rate": 3.949316912644596e-05,
+      "loss": 6.2751,
+      "step": 33500
+    },
+    {
+      "epoch": 6.781013163143199,
+      "grad_norm": 4.399994850158691,
+      "learning_rate": 3.887116074990028e-05,
+      "loss": 6.2345,
+      "step": 34000
+    },
+    {
+      "epoch": 6.8807339449541285,
+      "grad_norm": 4.522914886474609,
+      "learning_rate": 3.8247905863581976e-05,
+      "loss": 6.218,
+      "step": 34500
+    },
+    {
+      "epoch": 6.980454726765058,
+      "grad_norm": 4.697731018066406,
+      "learning_rate": 3.762465097726366e-05,
+      "loss": 6.1819,
+      "step": 35000
+    },
+    {
+      "epoch": 7.080175508575987,
+      "grad_norm": 5.113608360290527,
+      "learning_rate": 3.7001396090945355e-05,
+      "loss": 6.1566,
+      "step": 35500
+    },
+    {
+      "epoch": 7.179896290386917,
+      "grad_norm": 4.987142086029053,
+      "learning_rate": 3.637814120462705e-05,
+      "loss": 6.1504,
+      "step": 36000
+    },
+    {
+      "epoch": 7.279617072197846,
+      "grad_norm": 4.797494888305664,
+      "learning_rate": 3.5756132828081373e-05,
+      "loss": 6.0915,
+      "step": 36500
+    },
+    {
+      "epoch": 7.379337854008775,
+      "grad_norm": 5.114543437957764,
+      "learning_rate": 3.5132877941763066e-05,
+      "loss": 6.0859,
+      "step": 37000
+    },
+    {
+      "epoch": 7.479058635819705,
+      "grad_norm": 5.5212721824646,
+      "learning_rate": 3.450962305544476e-05,
+      "loss": 6.0643,
+      "step": 37500
+    },
+    {
+      "epoch": 7.578779417630634,
+      "grad_norm": 4.77981424331665,
+      "learning_rate": 3.3886368169126446e-05,
+      "loss": 6.038,
+      "step": 38000
+    },
+    {
+      "epoch": 7.678500199441563,
+      "grad_norm": 5.6912760734558105,
+      "learning_rate": 3.326311328280814e-05,
+      "loss": 6.0327,
+      "step": 38500
+    },
+    {
+      "epoch": 7.778220981252493,
+      "grad_norm": 5.021594524383545,
+      "learning_rate": 3.2641104906262464e-05,
+      "loss": 6.0089,
+      "step": 39000
+    },
+    {
+      "epoch": 7.877941763063422,
+      "grad_norm": 4.9512410163879395,
+      "learning_rate": 3.201785001994416e-05,
+      "loss": 5.9914,
+      "step": 39500
+    },
+    {
+      "epoch": 7.9776625448743514,
+      "grad_norm": 4.6659088134765625,
+      "learning_rate": 3.139459513362585e-05,
+      "loss": 5.9688,
+      "step": 40000
+    },
+    {
+      "epoch": 8.0,
+      "step": 40112,
+      "total_flos": 4.223778440028365e+16,
+      "train_loss": 2.356345704317949,
+      "train_runtime": 3822.1574,
+      "train_samples_per_second": 167.903,
+      "train_steps_per_second": 10.495
     }
   ],
   "logging_steps": 500,
-  "max_steps": 25070,
+  "max_steps": 40112,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 8,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -394,7 +604,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.639861525017728e+16,
+  "total_flos": 4.223778440028365e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null