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: 0.3174747885333798
 ---
 
 <!-- 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: 4.5553
+- Accuracy: 0.3175
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.3174747885333798,
+    "eval_loss": 4.555253505706787,
+    "eval_runtime": 23.033,
+    "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,
+    "train_samples": 40108,
+    "train_samples_per_second": 30.832,
+    "train_steps_per_second": 1.927
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.3174747885333798,
+    "eval_loss": 4.555253505706787,
+    "eval_runtime": 23.033,
+    "eval_samples": 2026,
+    "eval_samples_per_second": 87.961,
+    "eval_steps_per_second": 22.012,
+    "perplexity": 95.1308683970671
+}

runs/Jul21_05-43-41_c7096466ca2f/events.out.tfevents.1721547201.c7096466ca2f.3775.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dada30d8c4ffa739f813ef992a44fbdb6954c4c18e75b63e76ff989a432a3d19
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.619975204864e+16,
+    "train_loss": 5.155460170506956,
+    "train_runtime": 6504.3825,
+    "train_samples": 40108,
+    "train_samples_per_second": 30.832,
+    "train_steps_per_second": 1.927
+}

trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 12535,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1994415636218588,
+      "grad_norm": 1.8192601203918457,
+      "learning_rate": 4.8005584363781416e-05,
+      "loss": 7.5114,
+      "step": 500
+    },
+    {
+      "epoch": 0.3988831272437176,
+      "grad_norm": 1.543924331665039,
+      "learning_rate": 4.601116872756282e-05,
+      "loss": 6.6557,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5983246908655764,
+      "grad_norm": 1.7416774034500122,
+      "learning_rate": 4.4016753091344236e-05,
+      "loss": 6.2893,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7977662544874352,
+      "grad_norm": 1.72893488407135,
+      "learning_rate": 4.202233745512565e-05,
+      "loss": 6.0012,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9972078181092939,
+      "grad_norm": 2.0189125537872314,
+      "learning_rate": 4.002792181890706e-05,
+      "loss": 5.7968,
+      "step": 2500
+    },
+    {
+      "epoch": 1.1966493817311528,
+      "grad_norm": 1.9939076900482178,
+      "learning_rate": 3.803350618268847e-05,
+      "loss": 5.5695,
+      "step": 3000
+    },
+    {
+      "epoch": 1.3960909453530115,
+      "grad_norm": 2.0916945934295654,
+      "learning_rate": 3.6039090546469884e-05,
+      "loss": 5.4321,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5955325089748702,
+      "grad_norm": 2.1514716148376465,
+      "learning_rate": 3.4044674910251304e-05,
+      "loss": 5.3137,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7949740725967291,
+      "grad_norm": 2.0663416385650635,
+      "learning_rate": 3.205025927403271e-05,
+      "loss": 5.2554,
+      "step": 4500
+    },
+    {
+      "epoch": 1.994415636218588,
+      "grad_norm": 2.196505546569824,
+      "learning_rate": 3.0055843637814124e-05,
+      "loss": 5.171,
+      "step": 5000
+    },
+    {
+      "epoch": 2.193857199840447,
+      "grad_norm": 2.258173704147339,
+      "learning_rate": 2.8061428001595534e-05,
+      "loss": 4.9799,
+      "step": 5500
+    },
+    {
+      "epoch": 2.3932987634623055,
+      "grad_norm": 2.3806893825531006,
+      "learning_rate": 2.6067012365376948e-05,
+      "loss": 4.9378,
+      "step": 6000
+    },
+    {
+      "epoch": 2.5927403270841642,
+      "grad_norm": 2.332186222076416,
+      "learning_rate": 2.4072596729158358e-05,
+      "loss": 4.9042,
+      "step": 6500
+    },
+    {
+      "epoch": 2.792181890706023,
+      "grad_norm": 2.366901159286499,
+      "learning_rate": 2.207818109293977e-05,
+      "loss": 4.8437,
+      "step": 7000
+    },
+    {
+      "epoch": 2.9916234543278817,
+      "grad_norm": 2.328530788421631,
+      "learning_rate": 2.008376545672118e-05,
+      "loss": 4.806,
+      "step": 7500
+    },
+    {
+      "epoch": 3.191065017949741,
+      "grad_norm": 2.5201773643493652,
+      "learning_rate": 1.8089349820502595e-05,
+      "loss": 4.6991,
+      "step": 8000
+    },
+    {
+      "epoch": 3.3905065815715996,
+      "grad_norm": 2.608670949935913,
+      "learning_rate": 1.6098923015556443e-05,
+      "loss": 4.6476,
+      "step": 8500
+    },
+    {
+      "epoch": 3.5899481451934583,
+      "grad_norm": 2.5904150009155273,
+      "learning_rate": 1.4104507379337855e-05,
+      "loss": 4.6051,
+      "step": 9000
+    },
+    {
+      "epoch": 3.789389708815317,
+      "grad_norm": 2.5216405391693115,
+      "learning_rate": 1.2110091743119267e-05,
+      "loss": 4.6082,
+      "step": 9500
+    },
+    {
+      "epoch": 3.988831272437176,
+      "grad_norm": 2.5698513984680176,
+      "learning_rate": 1.0115676106900679e-05,
+      "loss": 4.5688,
+      "step": 10000
+    },
+    {
+      "epoch": 4.188272836059035,
+      "grad_norm": 2.6962502002716064,
+      "learning_rate": 8.125249301954529e-06,
+      "loss": 4.4808,
+      "step": 10500
+    },
+    {
+      "epoch": 4.387714399680894,
+      "grad_norm": 2.8604938983917236,
+      "learning_rate": 6.13083366573594e-06,
+      "loss": 4.4745,
+      "step": 11000
+    },
+    {
+      "epoch": 4.587155963302752,
+      "grad_norm": 2.820222854614258,
+      "learning_rate": 4.136418029517352e-06,
+      "loss": 4.4775,
+      "step": 11500
+    },
+    {
+      "epoch": 4.786597526924611,
+      "grad_norm": 2.6641643047332764,
+      "learning_rate": 2.1420023932987634e-06,
+      "loss": 4.4463,
+      "step": 12000
+    },
+    {
+      "epoch": 4.98603909054647,
+      "grad_norm": 2.8485090732574463,
+      "learning_rate": 1.515755883526127e-07,
+      "loss": 4.456,
+      "step": 12500
+    },
+    {
+      "epoch": 5.0,
+      "step": 12535,
+      "total_flos": 2.619975204864e+16,
+      "train_loss": 5.155460170506956,
+      "train_runtime": 6504.3825,
+      "train_samples_per_second": 30.832,
+      "train_steps_per_second": 1.927
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.619975204864e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}