End of training

README.md

@@ -2,11 +2,15 @@
 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:
-- generator
+- preference-data
 model-index:
 - name: preference_0.1p_seed42_level3_rare
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_0.1p_seed42_level3_rare
 
-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 generator 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: 0.7365
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9967355821545157,
+    "eval_loss": 0.7364564538002014,
+    "eval_runtime": 106.4286,
+    "eval_samples": 999,
+    "eval_samples_per_second": 3.664,
+    "eval_steps_per_second": 0.921,
     "total_flos": 47895596236800.0,
     "train_loss": 0.7106172507506792,
     "train_runtime": 7254.3633,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.4",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9967355821545157,
+    "eval_loss": 0.7364564538002014,
+    "eval_runtime": 106.4286,
+    "eval_samples": 999,
+    "eval_samples_per_second": 3.664,
+    "eval_steps_per_second": 0.921
+}

runs/Aug13_11-11-29_COE-CS-sv004/events.out.tfevents.1723555874.COE-CS-sv004.2666524.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e187692853d1526dafa25bf7958bff355e134ebc9644d8f132185261a058ffe1
+size 359