Model save

README.md

@@ -1,18 +1,17 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
-datasets:
-- HuggingFaceH4/ultrachat_200k
 library_name: transformers
-model_name: mistralai/Mistral-7B-v0.1
+model_name: zephyr-7b-sft-qlora-new
 tags:
 - generated_from_trainer
-- alignment-handbook
+- trl
+- sft
 licence: license
 ---
 
-# Model Card for mistralai/Mistral-7B-v0.1
+# Model Card for zephyr-7b-sft-qlora-new
 
-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']](https://huggingface.co/datasets/['HuggingFaceH4/ultrachat_200k']) 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
@@ -21,7 +20,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="awsuineg/zephyr-7b-sft-qlora", device="cuda")
+generator = pipeline("text-generation", model="awsuineg/zephyr-7b-sft-qlora-new", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62512eab037e82f894798fb76a443615054ced2821d693ab45770ee124a7af8
+oid sha256:c9287b78f9d956efa4729903fab8e8bc3f672ecb62566eec974b3b7fd1fb9ef9
 size 671149168

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
-    "total_flos": 1.1487027058043781e+19,
-    "train_loss": 0.0,
-    "train_runtime": 0.0143,
+    "epoch": 3.0,
+    "total_flos": 3.7211673621310734e+19,
+    "train_loss": 0.9273421984235244,
+    "train_runtime": 99241.3322,
     "train_samples": 207864,
-    "train_samples_per_second": 9715326.166,
-    "train_steps_per_second": 404831.526
+    "train_samples_per_second": 4.192,
+    "train_steps_per_second": 0.262
 }

runs/Nov21_18-45-34_d28f7adca72c/events.out.tfevents.1732214764.d28f7adca72c.2391037.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9958792a768a8e79e28af418e18f9e1c63fb8957dc5e3668e9d957c6215ff992
-size 1112199
+oid sha256:a2259f60968942e9ca033cda3968ada4750e2ffc94d2d92f7d16b02581c15840
+size 1112835

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
-    "total_flos": 1.1487027058043781e+19,
-    "train_loss": 0.0,
-    "train_runtime": 0.0143,
+    "epoch": 3.0,
+    "total_flos": 3.7211673621310734e+19,
+    "train_loss": 0.9273421984235244,
+    "train_runtime": 99241.3322,
     "train_samples": 207864,
-    "train_samples_per_second": 9715326.166,
-    "train_steps_per_second": 404831.526
+    "train_samples_per_second": 4.192,
+    "train_steps_per_second": 0.262
 }