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: preference_p0.1_seed42_level2_styledirtybatch16_reverse
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_styledirtybatch16_reverse
 
-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": 3.2449,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.082,
+    "eval_steps_per_second": 0.925,
     "total_flos": 253558763028480.0,
     "train_loss": 0.530042272082643,
     "train_runtime": 21564.4437,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_runtime": 3.2449,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.082,
+    "eval_steps_per_second": 0.925
+}

runs/Sep27_19-58-10_COE-CS-sv003/events.out.tfevents.1727489296.COE-CS-sv003.928272.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d27374c3ac67fc64aed6b4daf0cb8767cccd77be4addaee99d1c27fd1eb093
+size 311