End of training

README.md

@@ -2,9 +2,24 @@
 base_model: zaenalium/indonesia-distilgpt2
 tags:
 - generated_from_trainer
+datasets:
+- MBZUAI/Bactrian-X
+metrics:
+- accuracy
 model-index:
 - name: indonesia-distilgpt2
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: MBZUAI/Bactrian-X id
+      type: MBZUAI/Bactrian-X
+      args: id
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.3808162267839687
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -12,7 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # indonesia-distilgpt2
 
-This model is a fine-tuned version of [zaenalium/indonesia-distilgpt2](https://huggingface.co/zaenalium/indonesia-distilgpt2) on an unknown dataset.
+This model is a fine-tuned version of [zaenalium/indonesia-distilgpt2](https://huggingface.co/zaenalium/indonesia-distilgpt2) on the MBZUAI/Bactrian-X id dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1376
+- Accuracy: 0.3808
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.3808162267839687,
+    "eval_loss": 3.1375937461853027,
+    "eval_runtime": 3.1064,
+    "eval_samples": 40,
+    "eval_samples_per_second": 12.876,
+    "eval_steps_per_second": 3.219,
+    "perplexity": 23.04833992370074,
+    "total_flos": 450998191521792.0,
+    "train_loss": 3.38958450599953,
+    "train_runtime": 386.6866,
+    "train_samples": 863,
+    "train_samples_per_second": 4.464,
+    "train_steps_per_second": 1.117
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.3808162267839687,
+    "eval_loss": 3.1375937461853027,
+    "eval_runtime": 3.1064,
+    "eval_samples": 40,
+    "eval_samples_per_second": 12.876,
+    "eval_steps_per_second": 3.219,
+    "perplexity": 23.04833992370074
+}

runs/Jan31_16-06-34_e1d82b87f05d/events.out.tfevents.1706717676.e1d82b87f05d.1707.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac0a65dc5e347f985b3e957c8cd7acfe195783bf5a4773c22d481c526b5bc79
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 450998191521792.0,
+    "train_loss": 3.38958450599953,
+    "train_runtime": 386.6866,
+    "train_samples": 863,
+    "train_samples_per_second": 4.464,
+    "train_steps_per_second": 1.117
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 432,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6851851851851855e-05,
+      "loss": 3.6154,
+      "step": 200
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 3.2032,
+      "step": 400
+    },
+    {
+      "epoch": 2.0,
+      "step": 432,
+      "total_flos": 450998191521792.0,
+      "train_loss": 3.38958450599953,
+      "train_runtime": 386.6866,
+      "train_samples_per_second": 4.464,
+      "train_steps_per_second": 1.117
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 432,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 450998191521792.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}