End of training

README.md

@@ -2,12 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-7b-sft-qlora
   results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9584
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.9584344029426575,
+    "eval_runtime": 2495.3524,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 6.184,
+    "eval_steps_per_second": 0.773,
     "train_loss": 0.9710182381772446,
     "train_runtime": 17696.8906,
     "train_samples": 41573,

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9584344029426575,
+    "eval_runtime": 2495.3524,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 6.184,
+    "eval_steps_per_second": 0.773
+}