End of training

README.md

@@ -2,9 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: mistral-7b-dpo-full-wo-kqa_silver_wogold-ep3
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-7b-dpo-full-wo-kqa_silver_wogold-ep3
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Logits/chosen: -3.2790
-- Logits/rejected: -3.1123
-- Logps/chosen: -721.5319
-- Logps/rejected: -1477.7874
-- Loss: 0.3206
-- Rewards/accuracies: 0.8707
-- Rewards/chosen: -1.9160
-- Rewards/margins: 3.5495
-- Rewards/rejected: -5.4655
+- Loss: 0.2946
+- Rewards/chosen: -2.2047
+- Rewards/rejected: -5.9058
+- Rewards/accuracies: 0.8793
+- Rewards/margins: 3.7012
+- Logps/rejected: -1521.8148
+- Logps/chosen: -750.3969
+- Logits/rejected: -3.0916
+- Logits/chosen: -3.2432
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -3.2432265281677246,
+    "eval_logits/rejected": -3.091603994369507,
+    "eval_logps/chosen": -750.3968505859375,
+    "eval_logps/rejected": -1521.8148193359375,
+    "eval_loss": 0.2945583164691925,
+    "eval_rewards/accuracies": 0.8792613744735718,
+    "eval_rewards/chosen": -2.2046568393707275,
+    "eval_rewards/margins": 3.7011642456054688,
+    "eval_rewards/rejected": -5.905820846557617,
+    "eval_runtime": 293.4477,
+    "eval_samples": 2804,
+    "eval_samples_per_second": 9.555,
+    "eval_steps_per_second": 0.3,
     "train_loss": 0.04516718044779659,
     "train_runtime": 721.6494,
     "train_samples": 9808,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -3.2432265281677246,
+    "eval_logits/rejected": -3.091603994369507,
+    "eval_logps/chosen": -750.3968505859375,
+    "eval_logps/rejected": -1521.8148193359375,
+    "eval_loss": 0.2945583164691925,
+    "eval_rewards/accuracies": 0.8792613744735718,
+    "eval_rewards/chosen": -2.2046568393707275,
+    "eval_rewards/margins": 3.7011642456054688,
+    "eval_rewards/rejected": -5.905820846557617,
+    "eval_runtime": 293.4477,
+    "eval_samples": 2804,
+    "eval_samples_per_second": 9.555,
+    "eval_steps_per_second": 0.3
+}