End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- MBZUAI/Bactrian-X
+metrics:
+- accuracy
 model-index:
 - name: TinyLlama-Indo
-  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: 0.2550262872843518
 ---
 
 <!-- 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. -->
 
 # TinyLlama-Indo
 
-This model was trained from scratch on an unknown dataset.
+This model was trained from scratch on the MBZUAI/Bactrian-X id dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.2103
+- Accuracy: 0.2550
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.2550262872843518,
+    "eval_loss": 5.2102789878845215,
+    "eval_runtime": 10.0113,
+    "eval_samples": 37,
+    "eval_samples_per_second": 3.696,
+    "eval_steps_per_second": 1.898,
+    "perplexity": 183.14514634383818,
+    "total_flos": 4578913057505280.0,
+    "train_loss": 6.445547739664714,
+    "train_runtime": 1136.4366,
+    "train_samples": 767,
+    "train_samples_per_second": 1.35,
+    "train_steps_per_second": 0.169
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.2550262872843518,
+    "eval_loss": 5.2102789878845215,
+    "eval_runtime": 10.0113,
+    "eval_samples": 37,
+    "eval_samples_per_second": 3.696,
+    "eval_steps_per_second": 1.898,
+    "perplexity": 183.14514634383818
+}

runs/Jan31_01-27-05_de2702907b26/events.out.tfevents.1706665677.de2702907b26.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697a9ca82a56ac99b374c30864aaed86fdd361e8c3fd1de94a2fdf90fdc2d7f9
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 4578913057505280.0,
+    "train_loss": 6.445547739664714,
+    "train_runtime": 1136.4366,
+    "train_samples": 767,
+    "train_samples_per_second": 1.35,
+    "train_steps_per_second": 0.169
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "step": 192,
+      "total_flos": 4578913057505280.0,
+      "train_loss": 6.445547739664714,
+      "train_runtime": 1136.4366,
+      "train_samples_per_second": 1.35,
+      "train_steps_per_second": 0.169
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2000,
+  "total_flos": 4578913057505280.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}