End of training

README.md

@@ -2,9 +2,15 @@
 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:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-dpo-full-ultrabin-reward-scale-01
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-full-ultrabin-reward-scale-01
 
-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 HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5341
-- Rewards/chosen: -1.6701
-- Rewards/rejected: -3.0297
+- Loss: 0.5340
+- Rewards/chosen: -1.6749
+- Rewards/rejected: -3.0354
 - Rewards/accuracies: 0.7852
-- Rewards/margins: 1.3596
-- Logps/rejected: -565.6297
-- Logps/chosen: -429.6380
-- Logits/rejected: 2.3444
-- Logits/chosen: 1.3858
+- Rewards/margins: 1.3605
+- Logps/rejected: -566.2047
+- Logps/chosen: -430.1231
+- Logits/rejected: 2.3565
+- Logits/chosen: 1.3978
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": 1.397847294807434,
+    "eval_logits/rejected": 2.356464147567749,
+    "eval_logps/chosen": -430.1231384277344,
+    "eval_logps/rejected": -566.2046508789062,
+    "eval_loss": 0.534032940864563,
+    "eval_rewards/accuracies": 0.78515625,
+    "eval_rewards/chosen": -1.6749324798583984,
+    "eval_rewards/margins": 1.3604930639266968,
+    "eval_rewards/rejected": -3.0354254245758057,
+    "eval_runtime": 103.4008,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 19.342,
+    "eval_steps_per_second": 0.309,
     "total_flos": 0.0,
     "train_loss": 0.5431942655451627,
     "train_runtime": 12655.0807,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 1.397847294807434,
+    "eval_logits/rejected": 2.356464147567749,
+    "eval_logps/chosen": -430.1231384277344,
+    "eval_logps/rejected": -566.2046508789062,
+    "eval_loss": 0.534032940864563,
+    "eval_rewards/accuracies": 0.78515625,
+    "eval_rewards/chosen": -1.6749324798583984,
+    "eval_rewards/margins": 1.3604930639266968,
+    "eval_rewards/rejected": -3.0354254245758057,
+    "eval_runtime": 103.4008,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 19.342,
+    "eval_steps_per_second": 0.309
+}