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: preference_p0.1_seed42_level2_raremixbatch16
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_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: 0.8599
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.8599082231521606,
+    "eval_runtime": 2.8502,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.508,
+    "eval_steps_per_second": 1.053,
     "total_flos": 2571089024581632.0,
     "train_loss": 0.8638364601301117,
     "train_runtime": 28571.7374,

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": 0.28806865215301514,
-    "eval_runtime": 1.3149,
+    "eval_loss": 0.8599082231521606,
+    "eval_runtime": 2.8502,
     "eval_samples": 10,
-    "eval_samples_per_second": 2.282,
-    "eval_steps_per_second": 0.761
+    "eval_samples_per_second": 3.508,
+    "eval_steps_per_second": 1.053
 }

runs/Sep14_01-24-34_COE-CS-sv004/events.out.tfevents.1726305896.COE-CS-sv004.1678647.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e573ef94f6dbccbfd715725e0dab57e9e294bd6acc82d075f25bbf4d70bb26
+size 359