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
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 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 HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4969
-- Rewards/chosen: -1.1626
-- Rewards/rejected: -2.1853
-- Rewards/accuracies: 0.7773
-- Rewards/margins: 1.0227
-- Logps/rejected: -481.1959
-- Logps/chosen: -378.8522
-- Logits/rejected: 1.4928
-- Logits/chosen: 0.5873
+- Loss: 0.4968
+- Rewards/chosen: -1.2029
+- Rewards/rejected: -2.2447
+- Rewards/accuracies: 0.7617
+- Rewards/margins: 1.0418
+- Logps/rejected: -487.1403
+- Logps/chosen: -382.8826
+- Logits/rejected: 1.6118
+- Logits/chosen: 0.6753
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": 0.675320029258728,
+    "eval_logits/rejected": 1.6118428707122803,
+    "eval_logps/chosen": -382.88262939453125,
+    "eval_logps/rejected": -487.1402893066406,
+    "eval_loss": 0.4968120753765106,
+    "eval_rewards/accuracies": 0.76171875,
+    "eval_rewards/chosen": -1.2028917074203491,
+    "eval_rewards/margins": 1.0418392419815063,
+    "eval_rewards/rejected": -2.2447309494018555,
+    "eval_runtime": 96.2043,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 20.789,
+    "eval_steps_per_second": 0.333,
     "total_flos": 0.0,
     "train_loss": 0.5340489398485447,
     "train_runtime": 7520.1807,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 0.675320029258728,
+    "eval_logits/rejected": 1.6118428707122803,
+    "eval_logps/chosen": -382.88262939453125,
+    "eval_logps/rejected": -487.1402893066406,
+    "eval_loss": 0.4968120753765106,
+    "eval_rewards/accuracies": 0.76171875,
+    "eval_rewards/chosen": -1.2028917074203491,
+    "eval_rewards/margins": 1.0418392419815063,
+    "eval_rewards/rejected": -2.2447309494018555,
+    "eval_runtime": 96.2043,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 20.789,
+    "eval_steps_per_second": 0.333
+}

runs/Apr26_18-03-59_n136-098-146/events.out.tfevents.1714145747.n136-098-146.2262128.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359b03fd13762ecea21e7043ada3a383695493599f6a5c3f2d2b976bf7149366
+size 828