End of training

README.md

@@ -2,10 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-Instruct-v0.2
+datasets:
+- preference-data
 model-index:
 - name: feedback_p0.1_seed42_level2_raremixbatch16
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # feedback_p0.1_seed42_level2_raremixbatch16
 
-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.
 It achieves the following results on the evaluation set:
 - Loss: 0.7062
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.7062155604362488,
+    "eval_runtime": 3.3943,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.946,
+    "eval_steps_per_second": 0.884,
     "total_flos": 1963824696786944.0,
     "train_loss": 0.7727144511168101,
     "train_runtime": 22636.3522,

config.json

@@ -21,7 +21,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.4",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.31497257947921753,
-    "eval_runtime": 1.3051,
+    "eval_loss": 0.7062155604362488,
+    "eval_runtime": 3.3943,
     "eval_samples": 10,
-    "eval_samples_per_second": 1.532,
-    "eval_steps_per_second": 0.766
+    "eval_samples_per_second": 2.946,
+    "eval_steps_per_second": 0.884
 }

runs/Sep14_01-23-23_COE-CS-sv003/events.out.tfevents.1726299784.COE-CS-sv003.3342495.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00de91c723def85a72c987867942c92d8aedc909f9a400b4baf339a1a10826d2
+size 359