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_p0.01_seed42_level2_raremixbatch16
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.01_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.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
+    "eval_runtime": 2.4667,
+    "eval_samples": 10,
+    "eval_samples_per_second": 4.054,
+    "eval_steps_per_second": 1.216,
     "total_flos": 252825934233600.0,
     "train_loss": 0.5143274352170419,
     "train_runtime": 26101.4191,

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": 2.4667,
+    "eval_samples": 10,
+    "eval_samples_per_second": 4.054,
+    "eval_steps_per_second": 1.216
+}

runs/Sep16_07-59-08_COE-CS-sv004/events.out.tfevents.1726500638.COE-CS-sv004.2273395.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe383ebd0b280ee2480b7b9d7d828c7f3319cc1c24d5a8fe88e575a4490a03dd
+size 311