End of training

README.md

@@ -2,6 +2,10 @@
 license: gemma
 base_model: google/gemma-2-9b
 tags:
+- easylm
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
@@ -19,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on the alpaca_farm dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1208
+- Loss: 1.1304
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.9952,
+    "eval_loss": 1.1304032802581787,
+    "eval_runtime": 12.0051,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 166.596,
+    "eval_steps_per_second": 10.412,
     "total_flos": 2.810905532469084e+17,
     "train_loss": 0.4079937795415903,
     "train_runtime": 2322.7378,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "eval_loss": 0.6364463567733765,
-    "eval_runtime": 12.0722,
+    "epoch": 2.9952,
+    "eval_loss": 1.1304032802581787,
+    "eval_runtime": 12.0051,
     "eval_samples": 2000,
-    "eval_samples_per_second": 165.67,
-    "eval_steps_per_second": 10.354
+    "eval_samples_per_second": 166.596,
+    "eval_steps_per_second": 10.412
 }