End of training

README.md

@@ -3,10 +3,16 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: preference_p0.1_seed42_level2_syntaxdirtybatch16
   results: []
@@ -17,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_syntaxdirtybatch16
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_runtime": 3.2433,
+    "eval_runtime": 4.2085,
     "eval_samples": 10,
-    "eval_samples_per_second": 3.083,
-    "eval_steps_per_second": 0.925,
+    "eval_samples_per_second": 2.376,
+    "eval_steps_per_second": 0.713,
     "total_flos": 252302485094400.0,
     "train_loss": 0.0,
     "train_runtime": 0.0084,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
-    "eval_runtime": 3.2433,
+    "eval_runtime": 4.2085,
     "eval_samples": 10,
-    "eval_samples_per_second": 3.083,
-    "eval_steps_per_second": 0.925
+    "eval_samples_per_second": 2.376,
+    "eval_steps_per_second": 0.713
 }

runs/Sep24_11-52-09_COE-CS-sv003/events.out.tfevents.1727178868.COE-CS-sv003.783277.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9da7b9824d4faeee5cf7535c6151f8bee2d371aa2f22bed94519a57914faf94
+size 311