End of training

README.md

@@ -1,13 +1,13 @@
 ---
 base_model: facebook/opt-350m
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 library_name: peft
 license: other
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: opt350
@@ -19,7 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # opt350
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the generator dataset.
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the HuggingFaceH4/ultrachat_200k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7869
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.9999380306128772,
     "eval_loss": 1.7869144678115845,
-    "eval_runtime": 145.3758,
+    "eval_runtime": 154.2539,
     "eval_samples": 23109,
-    "eval_samples_per_second": 98.221,
-    "eval_steps_per_second": 6.143,
+    "eval_samples_per_second": 92.568,
+    "eval_steps_per_second": 5.789,
     "total_flos": 4248917998829568.0,
     "train_loss": 0.0,
     "train_runtime": 0.013,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9999380306128772,
     "eval_loss": 1.7869144678115845,
-    "eval_runtime": 145.3758,
+    "eval_runtime": 154.2539,
     "eval_samples": 23109,
-    "eval_samples_per_second": 98.221,
-    "eval_steps_per_second": 6.143
+    "eval_samples_per_second": 92.568,
+    "eval_steps_per_second": 5.789
 }

runs/Nov06_12-35-29_gnode001.cluster/events.out.tfevents.1730925495.gnode001.cluster.319001.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38afe43ac8b29eb807db84a8b801811bbf234b7edb7a7c45bb15515cde766bd
+size 359