End of training

README.md

@@ -2,11 +2,16 @@
 license: gemma
 base_model: google/gemma-2-2b
 tags:
+- easylm
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- ultrafeedback-sft
 model-index:
 - name: easylm-ultrafeedback-sft-gemma-2-2b
   results: []
@@ -17,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # easylm-ultrafeedback-sft-gemma-2-2b
 
-This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on the ultrafeedback-sft dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2897
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.2897049188613892,
+    "eval_runtime": 23.1699,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 19.249,
+    "eval_steps_per_second": 9.625,
     "total_flos": 3.3534568071535e+17,
     "train_loss": 1.3545556901116753,
     "train_runtime": 10924.2621,

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.2897049188613892,
+    "eval_runtime": 23.1699,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 19.249,
+    "eval_steps_per_second": 9.625
+}