End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- data/rlced_conifer
 model-index:
 - name: rlced-conifer-zephyr-7b-dpo-full
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # rlced-conifer-zephyr-7b-dpo-full
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the data/rlced_conifer dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1691
+- Rewards/chosen: -2.9092
+- Rewards/rejected: -8.6906
+- Rewards/accuracies: 0.9240
+- Rewards/margins: 5.7814
+- Logps/rejected: -1311.8641
+- Logps/chosen: -712.8596
+- Logits/rejected: 0.8491
+- Logits/chosen: -0.7188
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9963674104826155,
+    "eval_logits/chosen": -0.7187579870223999,
+    "eval_logits/rejected": 0.8491049408912659,
+    "eval_logps/chosen": -712.8595581054688,
+    "eval_logps/rejected": -1311.8641357421875,
+    "eval_loss": 0.16912925243377686,
+    "eval_rewards/accuracies": 0.9240196347236633,
+    "eval_rewards/chosen": -2.9091784954071045,
+    "eval_rewards/margins": 5.781402111053467,
+    "eval_rewards/rejected": -8.690580368041992,
+    "eval_runtime": 602.9119,
+    "eval_samples": 6491,
+    "eval_samples_per_second": 10.766,
+    "eval_steps_per_second": 0.169,
     "total_flos": 0.0,
     "train_loss": 0.250737202167511,
     "train_runtime": 29028.2374,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9963674104826155,
+    "eval_logits/chosen": -0.7187579870223999,
+    "eval_logits/rejected": 0.8491049408912659,
+    "eval_logps/chosen": -712.8595581054688,
+    "eval_logps/rejected": -1311.8641357421875,
+    "eval_loss": 0.16912925243377686,
+    "eval_rewards/accuracies": 0.9240196347236633,
+    "eval_rewards/chosen": -2.9091784954071045,
+    "eval_rewards/margins": 5.781402111053467,
+    "eval_rewards/rejected": -8.690580368041992,
+    "eval_runtime": 602.9119,
+    "eval_samples": 6491,
+    "eval_samples_per_second": 10.766,
+    "eval_steps_per_second": 0.169
+}