End of training

README.md

@@ -1,10 +1,11 @@
 ---
 base_model: facebook/opt-350m
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 library_name: peft
 license: other
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -18,7 +19,7 @@ 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
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9999380306128772,
+    "eval_loss": 1.7869144678115845,
+    "eval_runtime": 145.3758,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 98.221,
+    "eval_steps_per_second": 6.143,
     "total_flos": 4248917998829568.0,
     "train_loss": 1.8640377591255577,
     "train_runtime": 7899.8856,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9999380306128772,
-    "eval_loss": 1.7869231700897217,
-    "eval_runtime": 154.2674,
+    "eval_loss": 1.7869144678115845,
+    "eval_runtime": 145.3758,
     "eval_samples": 23109,
-    "eval_samples_per_second": 92.56,
-    "eval_steps_per_second": 5.789
+    "eval_samples_per_second": 98.221,
+    "eval_steps_per_second": 6.143
 }

runs/Nov05_11-16-57_gnode001.cluster/events.out.tfevents.1730842275.gnode001.cluster.293646.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d56846a8befa144c2048fa95f51ffd7872c7047e388b763389d734d3628f98
+size 359