End of training

README.md

@@ -2,13 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-7b-sft-qlora
   results: []
@@ -19,7 +19,9 @@ 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: 0.9488
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.99,
-    "eval_loss": 0.9485585689544678,
-    "eval_runtime": 565.6562,
+    "eval_loss": 0.9488300681114197,
+    "eval_runtime": 555.5017,
     "eval_samples": 23109,
-    "eval_samples_per_second": 27.28,
-    "eval_steps_per_second": 0.854,
+    "eval_samples_per_second": 27.778,
+    "eval_steps_per_second": 0.869,
     "total_flos": 1.2254141370096157e+19,
     "train_loss": 0.0,
     "train_runtime": 0.0433,

config.json

@@ -35,7 +35,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.39.3",
   "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9998852553069421,
-    "eval_loss": 0.9485585689544678,
-    "eval_runtime": 565.6562,
+    "epoch": 0.99,
+    "eval_loss": 0.9488300681114197,
+    "eval_runtime": 555.5017,
     "eval_samples": 23109,
-    "eval_samples_per_second": 27.28,
-    "eval_steps_per_second": 0.854
+    "eval_samples_per_second": 27.778,
+    "eval_steps_per_second": 0.869
 }

runs/May19_07-08-46_training-queue-st-p4d-24xlarge-1/events.out.tfevents.1716103304.training-queue-st-p4d-24xlarge-1.3797.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c832332a21f4a84c2f53f8a6274cea0b6a76963d74eece1de80bc4ece0c7e45
+size 359