End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- akahana/GlotCC-V1-jav-Latn
+metrics:
+- accuracy
 model-index:
 - name: gpt2-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: 0.3642142345585816
 ---
 
 <!-- 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. -->
 
 # gpt2-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: 4.0790
+- Accuracy: 0.3642
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.3174747885333798,
-    "eval_loss": 4.555253505706787,
-    "eval_runtime": 23.033,
+    "epoch": 10.0,
+    "eval_accuracy": 0.3642142345585816,
+    "eval_loss": 4.079000473022461,
+    "eval_runtime": 23.2829,
     "eval_samples": 2026,
-    "eval_samples_per_second": 87.961,
-    "eval_steps_per_second": 22.012,
-    "perplexity": 95.1308683970671,
-    "total_flos": 2.619975204864e+16,
-    "train_loss": 5.155460170506956,
-    "train_runtime": 6504.3825,
+    "eval_samples_per_second": 87.017,
+    "eval_steps_per_second": 21.776,
+    "perplexity": 59.08638189209135,
+    "total_flos": 5.239950409728e+16,
+    "train_loss": 1.9918543002688176,
+    "train_runtime": 6309.7744,
     "train_samples": 40108,
-    "train_samples_per_second": 30.832,
-    "train_steps_per_second": 1.927
+    "train_samples_per_second": 63.565,
+    "train_steps_per_second": 3.973
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.3174747885333798,
-    "eval_loss": 4.555253505706787,
-    "eval_runtime": 23.033,
+    "epoch": 10.0,
+    "eval_accuracy": 0.3642142345585816,
+    "eval_loss": 4.079000473022461,
+    "eval_runtime": 23.2829,
     "eval_samples": 2026,
-    "eval_samples_per_second": 87.961,
-    "eval_steps_per_second": 22.012,
-    "perplexity": 95.1308683970671
+    "eval_samples_per_second": 87.017,
+    "eval_steps_per_second": 21.776,
+    "perplexity": 59.08638189209135
 }

runs/Jul22_00-53-04_850d126be01f/events.out.tfevents.1721616051.850d126be01f.953.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073bd173b309bd65eac9d86e1ba421aa46d293c7471834b59c24500a7ff1ab0f
+size 417

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 5.0,
-    "total_flos": 2.619975204864e+16,
-    "train_loss": 5.155460170506956,
-    "train_runtime": 6504.3825,
+    "epoch": 10.0,
+    "total_flos": 5.239950409728e+16,
+    "train_loss": 1.9918543002688176,
+    "train_runtime": 6309.7744,
     "train_samples": 40108,
-    "train_samples_per_second": 30.832,
-    "train_steps_per_second": 1.927
+    "train_samples_per_second": 63.565,
+    "train_steps_per_second": 3.973
 }

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": 6504.3825,
       "train_samples_per_second": 30.832,
       "train_steps_per_second": 1.927
+    },
+    {
+      "epoch": 5.1854806541683285,
+      "grad_norm": 2.8765642642974854,
+      "learning_rate": 4.907259672915836e-05,
+      "loss": 4.6174,
+      "step": 13000
+    },
+    {
+      "epoch": 5.384922217790187,
+      "grad_norm": 2.5134449005126953,
+      "learning_rate": 4.8075388911049066e-05,
+      "loss": 4.5994,
+      "step": 13500
+    },
+    {
+      "epoch": 5.584363781412046,
+      "grad_norm": 2.6400318145751953,
+      "learning_rate": 4.707818109293977e-05,
+      "loss": 4.5189,
+      "step": 14000
+    },
+    {
+      "epoch": 5.783805345033905,
+      "grad_norm": 2.5880420207977295,
+      "learning_rate": 4.608097327483047e-05,
+      "loss": 4.4798,
+      "step": 14500
+    },
+    {
+      "epoch": 5.983246908655763,
+      "grad_norm": 2.620410919189453,
+      "learning_rate": 4.508376545672118e-05,
+      "loss": 4.4567,
+      "step": 15000
+    },
+    {
+      "epoch": 6.182688472277623,
+      "grad_norm": 2.8458619117736816,
+      "learning_rate": 4.4086557638611886e-05,
+      "loss": 4.2553,
+      "step": 15500
+    },
+    {
+      "epoch": 6.382130035899482,
+      "grad_norm": 2.748814105987549,
+      "learning_rate": 4.3089349820502596e-05,
+      "loss": 4.2376,
+      "step": 16000
+    },
+    {
+      "epoch": 6.58157159952134,
+      "grad_norm": 2.752399444580078,
+      "learning_rate": 4.2092142002393306e-05,
+      "loss": 4.2098,
+      "step": 16500
+    },
+    {
+      "epoch": 6.781013163143199,
+      "grad_norm": 2.8099758625030518,
+      "learning_rate": 4.1094934184284e-05,
+      "loss": 4.1562,
+      "step": 17000
+    },
+    {
+      "epoch": 6.980454726765058,
+      "grad_norm": 2.6280643939971924,
+      "learning_rate": 4.009772636617471e-05,
+      "loss": 4.1439,
+      "step": 17500
+    },
+    {
+      "epoch": 7.179896290386917,
+      "grad_norm": 2.8597283363342285,
+      "learning_rate": 3.9100518548065417e-05,
+      "loss": 3.9943,
+      "step": 18000
+    },
+    {
+      "epoch": 7.379337854008775,
+      "grad_norm": 3.049448251724243,
+      "learning_rate": 3.810331072995613e-05,
+      "loss": 3.9513,
+      "step": 18500
+    },
+    {
+      "epoch": 7.578779417630634,
+      "grad_norm": 3.0431199073791504,
+      "learning_rate": 3.710610291184683e-05,
+      "loss": 3.9371,
+      "step": 19000
+    },
+    {
+      "epoch": 7.778220981252493,
+      "grad_norm": 2.9101345539093018,
+      "learning_rate": 3.610889509373754e-05,
+      "loss": 3.9142,
+      "step": 19500
+    },
+    {
+      "epoch": 7.9776625448743514,
+      "grad_norm": 3.04560923576355,
+      "learning_rate": 3.5111687275628244e-05,
+      "loss": 3.897,
+      "step": 20000
+    },
+    {
+      "epoch": 8.177104108496211,
+      "grad_norm": 3.3787050247192383,
+      "learning_rate": 3.411447945751895e-05,
+      "loss": 3.7559,
+      "step": 20500
+    },
+    {
+      "epoch": 8.37654567211807,
+      "grad_norm": 3.308147430419922,
+      "learning_rate": 3.311926605504587e-05,
+      "loss": 3.727,
+      "step": 21000
+    },
+    {
+      "epoch": 8.575987235739928,
+      "grad_norm": 3.117141008377075,
+      "learning_rate": 3.212205823693658e-05,
+      "loss": 3.7048,
+      "step": 21500
+    },
+    {
+      "epoch": 8.775428799361787,
+      "grad_norm": 3.0353927612304688,
+      "learning_rate": 3.1124850418827286e-05,
+      "loss": 3.6959,
+      "step": 22000
+    },
+    {
+      "epoch": 8.974870362983646,
+      "grad_norm": 3.1278910636901855,
+      "learning_rate": 3.0127642600717993e-05,
+      "loss": 3.7229,
+      "step": 22500
+    },
+    {
+      "epoch": 9.174311926605505,
+      "grad_norm": 3.2263429164886475,
+      "learning_rate": 2.9132429198244916e-05,
+      "loss": 3.5526,
+      "step": 23000
+    },
+    {
+      "epoch": 9.373753490227363,
+      "grad_norm": 3.4758195877075195,
+      "learning_rate": 2.8135221380135622e-05,
+      "loss": 3.5455,
+      "step": 23500
+    },
+    {
+      "epoch": 9.573195053849222,
+      "grad_norm": 3.5570030212402344,
+      "learning_rate": 2.7138013562026326e-05,
+      "loss": 3.5792,
+      "step": 24000
+    },
+    {
+      "epoch": 9.77263661747108,
+      "grad_norm": 3.397296667098999,
+      "learning_rate": 2.6140805743917036e-05,
+      "loss": 3.5237,
+      "step": 24500
+    },
+    {
+      "epoch": 9.97207818109294,
+      "grad_norm": 3.1818623542785645,
+      "learning_rate": 2.5145592341443958e-05,
+      "loss": 3.5251,
+      "step": 25000
+    },
+    {
+      "epoch": 10.0,
+      "step": 25070,
+      "total_flos": 5.239950409728e+16,
+      "train_loss": 1.9918543002688176,
+      "train_runtime": 6309.7744,
+      "train_samples_per_second": 63.565,
+      "train_steps_per_second": 3.973
     }
   ],
   "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": 2.619975204864e+16,
+  "total_flos": 5.239950409728e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null