End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- akahana/GlotCC-V1-jav-Latn
+metrics:
+- accuracy
 model-index:
 - name: distilgpt2-javanese
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: akahana/GlotCC-V1-jav-Latn default
+      type: akahana/GlotCC-V1-jav-Latn
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.349037028434276
 ---
 
 <!-- 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. -->
 
 # distilgpt2-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: 4.1864
+- Accuracy: 0.3490
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.29955480711534366,
-    "eval_loss": 4.690457820892334,
-    "eval_runtime": 18.6192,
+    "epoch": 10.0,
+    "eval_accuracy": 0.349037028434276,
+    "eval_loss": 4.1864213943481445,
+    "eval_runtime": 17.3075,
     "eval_samples": 2026,
-    "eval_samples_per_second": 108.812,
-    "eval_steps_per_second": 27.23,
-    "perplexity": 108.9030264768815,
-    "total_flos": 1.310011259092992e+16,
-    "train_loss": 5.274392118328446,
-    "train_runtime": 3806.2907,
+    "eval_samples_per_second": 117.059,
+    "eval_steps_per_second": 29.294,
+    "perplexity": 65.78694368142702,
+    "total_flos": 2.620022518185984e+16,
+    "train_loss": 2.0909440845904905,
+    "train_runtime": 3914.0913,
     "train_samples": 40108,
-    "train_samples_per_second": 52.686,
-    "train_steps_per_second": 3.293
+    "train_samples_per_second": 102.471,
+    "train_steps_per_second": 6.405
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.29955480711534366,
-    "eval_loss": 4.690457820892334,
-    "eval_runtime": 18.6192,
+    "epoch": 10.0,
+    "eval_accuracy": 0.349037028434276,
+    "eval_loss": 4.1864213943481445,
+    "eval_runtime": 17.3075,
     "eval_samples": 2026,
-    "eval_samples_per_second": 108.812,
-    "eval_steps_per_second": 27.23,
-    "perplexity": 108.9030264768815
+    "eval_samples_per_second": 117.059,
+    "eval_steps_per_second": 29.294,
+    "perplexity": 65.78694368142702
 }

runs/Jul24_00-46-24_73a83f74d69d/events.out.tfevents.1721785958.73a83f74d69d.3048.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7444f25960ac57f53d145c6210eeadfb497c89628cdb2dd0465835cb8ae181
+size 417

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 5.0,
-    "total_flos": 1.310011259092992e+16,
-    "train_loss": 5.274392118328446,
-    "train_runtime": 3806.2907,
+    "epoch": 10.0,
+    "total_flos": 2.620022518185984e+16,
+    "train_loss": 2.0909440845904905,
+    "train_runtime": 3914.0913,
     "train_samples": 40108,
-    "train_samples_per_second": 52.686,
-    "train_steps_per_second": 3.293
+    "train_samples_per_second": 102.471,
+    "train_steps_per_second": 6.405
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 12535,
+  "global_step": 25070,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,12 +191,196 @@
       "train_runtime": 3806.2907,
       "train_samples_per_second": 52.686,
       "train_steps_per_second": 3.293
+    },
+    {
+      "epoch": 5.1854806541683285,
+      "grad_norm": 2.7731709480285645,
+      "learning_rate": 4.907259672915836e-05,
+      "loss": 4.7681,
+      "step": 13000
+    },
+    {
+      "epoch": 5.384922217790187,
+      "grad_norm": 2.5628647804260254,
+      "learning_rate": 4.8075388911049066e-05,
+      "loss": 4.7441,
+      "step": 13500
+    },
+    {
+      "epoch": 5.584363781412046,
+      "grad_norm": 2.7598373889923096,
+      "learning_rate": 4.707818109293977e-05,
+      "loss": 4.6634,
+      "step": 14000
+    },
+    {
+      "epoch": 5.783805345033905,
+      "grad_norm": 2.619565486907959,
+      "learning_rate": 4.608097327483047e-05,
+      "loss": 4.6238,
+      "step": 14500
+    },
+    {
+      "epoch": 5.983246908655763,
+      "grad_norm": 2.6309878826141357,
+      "learning_rate": 4.508376545672118e-05,
+      "loss": 4.6015,
+      "step": 15000
+    },
+    {
+      "epoch": 6.182688472277623,
+      "grad_norm": 2.6872658729553223,
+      "learning_rate": 4.4086557638611886e-05,
+      "loss": 4.4218,
+      "step": 15500
+    },
+    {
+      "epoch": 6.382130035899482,
+      "grad_norm": 2.780477285385132,
+      "learning_rate": 4.3089349820502596e-05,
+      "loss": 4.405,
+      "step": 16000
+    },
+    {
+      "epoch": 6.58157159952134,
+      "grad_norm": 2.700143575668335,
+      "learning_rate": 4.2092142002393306e-05,
+      "loss": 4.3785,
+      "step": 16500
+    },
+    {
+      "epoch": 6.781013163143199,
+      "grad_norm": 2.7577366828918457,
+      "learning_rate": 4.1094934184284e-05,
+      "loss": 4.3257,
+      "step": 17000
+    },
+    {
+      "epoch": 6.980454726765058,
+      "grad_norm": 2.6972854137420654,
+      "learning_rate": 4.009772636617471e-05,
+      "loss": 4.3124,
+      "step": 17500
+    },
+    {
+      "epoch": 7.179896290386917,
+      "grad_norm": 2.8049590587615967,
+      "learning_rate": 3.9100518548065417e-05,
+      "loss": 4.1901,
+      "step": 18000
+    },
+    {
+      "epoch": 7.379337854008775,
+      "grad_norm": 3.0153963565826416,
+      "learning_rate": 3.810331072995613e-05,
+      "loss": 4.1466,
+      "step": 18500
+    },
+    {
+      "epoch": 7.578779417630634,
+      "grad_norm": 3.010798215866089,
+      "learning_rate": 3.710610291184683e-05,
+      "loss": 4.1345,
+      "step": 19000
+    },
+    {
+      "epoch": 7.778220981252493,
+      "grad_norm": 2.857867956161499,
+      "learning_rate": 3.610889509373754e-05,
+      "loss": 4.1093,
+      "step": 19500
+    },
+    {
+      "epoch": 7.9776625448743514,
+      "grad_norm": 2.9866838455200195,
+      "learning_rate": 3.5111687275628244e-05,
+      "loss": 4.091,
+      "step": 20000
+    },
+    {
+      "epoch": 8.177104108496211,
+      "grad_norm": 3.2831859588623047,
+      "learning_rate": 3.411447945751895e-05,
+      "loss": 3.9812,
+      "step": 20500
+    },
+    {
+      "epoch": 8.37654567211807,
+      "grad_norm": 3.1285603046417236,
+      "learning_rate": 3.311926605504587e-05,
+      "loss": 3.955,
+      "step": 21000
+    },
+    {
+      "epoch": 8.575987235739928,
+      "grad_norm": 2.9974467754364014,
+      "learning_rate": 3.212205823693658e-05,
+      "loss": 3.9307,
+      "step": 21500
+    },
+    {
+      "epoch": 8.775428799361787,
+      "grad_norm": 3.0734570026397705,
+      "learning_rate": 3.1124850418827286e-05,
+      "loss": 3.9186,
+      "step": 22000
+    },
+    {
+      "epoch": 8.974870362983646,
+      "grad_norm": 3.024569034576416,
+      "learning_rate": 3.0129637016354212e-05,
+      "loss": 3.9455,
+      "step": 22500
+    },
+    {
+      "epoch": 9.174311926605505,
+      "grad_norm": 3.05592679977417,
+      "learning_rate": 2.9132429198244916e-05,
+      "loss": 3.8104,
+      "step": 23000
+    },
+    {
+      "epoch": 9.373753490227363,
+      "grad_norm": 3.2957406044006348,
+      "learning_rate": 2.8135221380135622e-05,
+      "loss": 3.8007,
+      "step": 23500
+    },
+    {
+      "epoch": 9.573195053849222,
+      "grad_norm": 3.398186683654785,
+      "learning_rate": 2.7138013562026326e-05,
+      "loss": 3.8345,
+      "step": 24000
+    },
+    {
+      "epoch": 9.77263661747108,
+      "grad_norm": 3.1825666427612305,
+      "learning_rate": 2.6140805743917036e-05,
+      "loss": 3.7761,
+      "step": 24500
+    },
+    {
+      "epoch": 9.97207818109294,
+      "grad_norm": 2.9551422595977783,
+      "learning_rate": 2.514359792580774e-05,
+      "loss": 3.777,
+      "step": 25000
+    },
+    {
+      "epoch": 10.0,
+      "step": 25070,
+      "total_flos": 2.620022518185984e+16,
+      "train_loss": 2.0909440845904905,
+      "train_runtime": 3914.0913,
+      "train_samples_per_second": 102.471,
+      "train_steps_per_second": 6.405
     }
   ],
   "logging_steps": 500,
-  "max_steps": 12535,
+  "max_steps": 25070,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -210,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.310011259092992e+16,
+  "total_flos": 2.620022518185984e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null