End of training

README.md

@@ -3,9 +3,15 @@ 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
+- generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: feedback_p0.1_seed42_level2_styledirtybatch16
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # feedback_p0.1_seed42_level2_styledirtybatch16
 
-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

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
+    "eval_runtime": 3.1499,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.175,
+    "eval_steps_per_second": 0.952,
     "total_flos": 176088290426880.0,
     "train_loss": 0.5311898304931332,
     "train_runtime": 14992.3235,

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

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_runtime": 3.1499,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.175,
+    "eval_steps_per_second": 0.952
+}

runs/Sep15_04-56-03_COE-CS-sv003/events.out.tfevents.1726391671.COE-CS-sv003.3473779.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd215d91675e7ea52ce83526053313e7af3aa6ded85bdb0f6e6f805dafef4d1
+size 311