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: 0.9524
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.9523706436157227,
+    "eval_runtime": 523.5784,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 29.472,
+    "eval_steps_per_second": 0.462,
     "total_flos": 1.2254844500131709e+19,
     "train_loss": 0.9352519262663926,
     "train_runtime": 32149.2413,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9999856554731542,
-    "eval_loss": 0.9543404579162598,
-    "eval_runtime": 2086.5983,
+    "epoch": 1.0,
+    "eval_loss": 0.9523706436157227,
+    "eval_runtime": 523.5784,
     "eval_samples": 23109,
-    "eval_samples_per_second": 7.395,
+    "eval_samples_per_second": 29.472,
     "eval_steps_per_second": 0.462
 }

runs/May03_23-45-29_p4d-24xl-us-west-2-st-p4d-24xl-us-west-2-5/events.out.tfevents.1714812667.p4d-24xl-us-west-2-st-p4d-24xl-us-west-2-5.46666.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b580303bb61a45f4c2edfae4b99d3f49652d8510bf6d39c531844a0c6f2bec6
+size 364