End of training

README.md

@@ -2,10 +2,16 @@
 license: llama2
 base_model: epfl-llm/meditron-7b
 tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
 - trl
 - dpo
 - alignment-handbook
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: meditron-7b-dpo-full-wo-kqa_golden-ep3
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # meditron-7b-dpo-full-wo-kqa_golden-ep3
 
-This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on an unknown dataset.
+This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Logits/chosen: -0.8310
-- Logits/rejected: -0.9203
-- Logps/chosen: -859.0582
-- Logps/rejected: -1444.6896
 - Loss: 0.4459
-- Rewards/accuracies: 0.8068
 - Rewards/chosen: -0.4566
-- Rewards/margins: 0.9447
 - Rewards/rejected: -1.4012
+- Rewards/accuracies: 0.8068
+- Rewards/margins: 0.9447
+- Logps/rejected: -1444.6896
+- Logps/chosen: -859.0582
+- Logits/rejected: -0.9203
+- Logits/chosen: -0.8310
 
 ## Model description
 

all_results.json

@@ -9,10 +9,10 @@
     "eval_rewards/chosen": -0.4565673768520355,
     "eval_rewards/margins": 0.9446592926979065,
     "eval_rewards/rejected": -1.4012266397476196,
-    "eval_runtime": 80.5227,
+    "eval_runtime": 81.0885,
     "eval_samples": 676,
-    "eval_samples_per_second": 8.395,
-    "eval_steps_per_second": 0.273,
+    "eval_samples_per_second": 8.337,
+    "eval_steps_per_second": 0.271,
     "train_loss": 0.0,
     "train_runtime": 2.1286,
     "train_samples": 12791,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32017
 }

eval_results.json

@@ -9,8 +9,8 @@
     "eval_rewards/chosen": -0.4565673768520355,
     "eval_rewards/margins": 0.9446592926979065,
     "eval_rewards/rejected": -1.4012266397476196,
-    "eval_runtime": 80.5227,
+    "eval_runtime": 81.0885,
     "eval_samples": 676,
-    "eval_samples_per_second": 8.395,
-    "eval_steps_per_second": 0.273
+    "eval_samples_per_second": 8.337,
+    "eval_steps_per_second": 0.271
 }