End of training

README.md

@@ -2,9 +2,15 @@
 license: other
 base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- argilla/dpo-mix-7k
 model-index:
 - name: zephyr-7b-gemma-dpo
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sanqiang/wdpo/runs/cbwapxr3)
 # zephyr-7b-gemma-dpo
 
-This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the None dataset.
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4631
-- Rewards/chosen: -3.9815
-- Rewards/rejected: -5.5353
-- Rewards/accuracies: 0.7083
-- Rewards/margins: 1.5538
-- Logps/rejected: -472.6590
-- Logps/chosen: -442.3637
-- Logits/rejected: 88.4677
-- Logits/chosen: 94.3385
+- Loss: 0.4694
+- Rewards/chosen: -3.9430
+- Rewards/rejected: -5.5568
+- Rewards/accuracies: 0.7292
+- Rewards/margins: 1.6137
+- Logps/rejected: -473.0876
+- Logps/chosen: -441.5945
+- Logits/rejected: 88.3937
+- Logits/chosen: 94.2780
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.971563981042654,
+    "eval_logits/chosen": 94.27800750732422,
+    "eval_logits/rejected": 88.3936767578125,
+    "eval_logps/chosen": -441.594482421875,
+    "eval_logps/rejected": -473.087646484375,
+    "eval_loss": 0.4694259464740753,
+    "eval_rewards/accuracies": 0.7291666865348816,
+    "eval_rewards/chosen": -3.94303035736084,
+    "eval_rewards/margins": 1.613731026649475,
+    "eval_rewards/rejected": -5.556761264801025,
+    "eval_runtime": 20.9081,
+    "eval_samples": 750,
+    "eval_samples_per_second": 35.871,
+    "eval_steps_per_second": 1.148,
     "total_flos": 0.0,
     "train_loss": 0.38818228932527393,
     "train_runtime": 1555.646,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.971563981042654,
+    "eval_logits/chosen": 94.27800750732422,
+    "eval_logits/rejected": 88.3936767578125,
+    "eval_logps/chosen": -441.594482421875,
+    "eval_logps/rejected": -473.087646484375,
+    "eval_loss": 0.4694259464740753,
+    "eval_rewards/accuracies": 0.7291666865348816,
+    "eval_rewards/chosen": -3.94303035736084,
+    "eval_rewards/margins": 1.613731026649475,
+    "eval_rewards/rejected": -5.556761264801025,
+    "eval_runtime": 20.9081,
+    "eval_samples": 750,
+    "eval_samples_per_second": 35.871,
+    "eval_steps_per_second": 1.148
+}

runs/May21_06-37-19_pytorchjob-summarization-debugkd-3zab-sanqiang-zhao-master-0/events.out.tfevents.1716275321.pytorchjob-summarization-debugkd-3zab-sanqiang-zhao-master-0.5067.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9be7911210b60808371dee5636db9c44a3368e75b25d68eb3ef706de8d1b70d
+size 767