End of training

README.md

@@ -2,6 +2,10 @@
 license: gemma
 base_model: google/gemma-2-2b
 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-2-2b](https://huggingface.co/google/gemma-2-2b) on the alpaca_farm dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6650
+- Loss: 0.6649
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.664948046207428,
+    "eval_runtime": 7.2125,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 277.295,
+    "eval_steps_per_second": 17.331,
     "total_flos": 2.283996277689549e+16,
     "train_loss": 0.6787182281494141,
     "train_runtime": 858.483,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 1.4030561447143555,
-    "eval_runtime": 13.4119,
+    "epoch": 1.0,
+    "eval_loss": 0.664948046207428,
+    "eval_runtime": 7.2125,
     "eval_samples": 2000,
-    "eval_samples_per_second": 149.122,
-    "eval_steps_per_second": 18.64
+    "eval_samples_per_second": 277.295,
+    "eval_steps_per_second": 17.331
 }