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
@@ -16,6 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 # easylm-hs-sft-gemma-2-2b
 
 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: 1.0783
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9988545246277205,
+    "eval_loss": 1.078296184539795,
+    "eval_runtime": 7.8356,
+    "eval_samples": 360,
+    "eval_samples_per_second": 45.944,
+    "eval_steps_per_second": 5.743,
     "total_flos": 5.419062457584845e+16,
     "train_loss": 1.1514144337505376,
     "train_runtime": 718.1022,

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9988545246277205,
+    "eval_loss": 1.078296184539795,
+    "eval_runtime": 7.8356,
+    "eval_samples": 360,
+    "eval_samples_per_second": 45.944,
+    "eval_steps_per_second": 5.743
+}