Model save

README.md

@@ -1,20 +1,17 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
-datasets:
-- argilla/distilabel-capybara-dpo-7k-binarized
 library_name: transformers
-model_name: mistralai/Mistral-7B-v0.1
+model_name: zephyr-orpo-7b-hehe
 tags:
 - generated_from_trainer
-- alignment-handbook
 - trl
 - orpo
 licence: license
 ---
 
-# Model Card for mistralai/Mistral-7B-v0.1
+# Model Card for zephyr-orpo-7b-hehe
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [['argilla/distilabel-capybara-dpo-7k-binarized']](https://huggingface.co/datasets/['argilla/distilabel-capybara-dpo-7k-binarized']) dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 1.4294498003771459,
-    "train_runtime": 7808.9602,
-    "train_samples": 7210,
-    "train_samples_per_second": 2.77,
-    "train_steps_per_second": 0.173
+    "train_loss": 1.0584710824750894,
+    "train_runtime": 37613.9724,
+    "train_samples": 61065,
+    "train_samples_per_second": 4.87,
+    "train_steps_per_second": 0.304
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 1.4294498003771459,
-    "train_runtime": 7808.9602,
-    "train_samples": 7210,
-    "train_samples_per_second": 2.77,
-    "train_steps_per_second": 0.173
+    "train_loss": 1.0584710824750894,
+    "train_runtime": 37613.9724,
+    "train_samples": 61065,
+    "train_samples_per_second": 4.87,
+    "train_steps_per_second": 0.304
 }