End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 base_model: kajuma/falcon3_1b_patch
 tags:
 - generated_from_trainer
+datasets:
+- kajuma/training_12-23_token
 model-index:
 - name: results
   results: []
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [kajuma/falcon3_1b_patch](https://huggingface.co/kajuma/falcon3_1b_patch) on an unknown dataset.
+This model is a fine-tuned version of [kajuma/falcon3_1b_patch](https://huggingface.co/kajuma/falcon3_1b_patch) on the kajuma/training_12-23_token dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.2373
 

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999656899746105,
+    "total_flos": 4.21458105504419e+19,
+    "train_loss": 0.746276973770012,
+    "train_runtime": 40997.541,
+    "train_samples": 2448242,
+    "train_samples_per_second": 59.717,
+    "train_steps_per_second": 0.237
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999656899746105,
+    "total_flos": 4.21458105504419e+19,
+    "train_loss": 0.746276973770012,
+    "train_runtime": 40997.541,
+    "train_samples": 2448242,
+    "train_samples_per_second": 59.717,
+    "train_steps_per_second": 0.237
+}