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
@@ -17,7 +21,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1501
+- Loss: 1.1448
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.0,
+    "eval_loss": 1.1447688341140747,
+    "eval_runtime": 5.2882,
+    "eval_samples": 360,
+    "eval_samples_per_second": 68.076,
+    "eval_steps_per_second": 17.019,
     "total_flos": 8.351047625159475e+16,
     "train_loss": 0.9289274918937465,
     "train_runtime": 3314.9598,

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.1447688341140747,
+    "eval_runtime": 5.2882,
+    "eval_samples": 360,
+    "eval_samples_per_second": 68.076,
+    "eval_steps_per_second": 17.019
+}