End of training

README.md

@@ -2,9 +2,15 @@
 license: other
 base_model: deepseek-ai/deepseek-math-7b-base
 tags:
+- alignment-handbook
 - trl
 - orpo
 - generated_from_trainer
+- trl
+- orpo
+- generated_from_trainer
+datasets:
+- zfz1/my_preference_gsm8k_deepseek
 model-index:
 - name: deepseek-8b-orpo-full
   results: []
@@ -16,7 +22,20 @@ 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/thuzfz1/huggingface/runs/dtbyb3v7)
 # deepseek-8b-orpo-full
 
-This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on an unknown dataset.
+This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on the zfz1/my_preference_gsm8k_deepseek dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0797
+- Rewards/chosen: -0.0089
+- Rewards/rejected: -0.2196
+- Rewards/accuracies: 1.0
+- Rewards/margins: 0.2107
+- Logps/rejected: -2.1960
+- Logps/chosen: -0.0885
+- Logits/rejected: 13.8906
+- Logits/chosen: 8.5947
+- Nll Loss: 0.0786
+- Log Odds Ratio: -0.0204
+- Log Odds Chosen: 5.3533
 
 ## Model description
 

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 2.0,
+    "eval_log_odds_chosen": 5.353264808654785,
+    "eval_log_odds_ratio": -0.020422911271452904,
+    "eval_logits/chosen": 8.594698905944824,
+    "eval_logits/rejected": 13.890603065490723,
+    "eval_logps/chosen": -0.08852054923772812,
+    "eval_logps/rejected": -2.195981502532959,
+    "eval_loss": 0.07974232733249664,
+    "eval_nll_loss": 0.07859200984239578,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -0.008852055296301842,
+    "eval_rewards/margins": 0.21074610948562622,
+    "eval_rewards/rejected": -0.2195981740951538,
+    "eval_runtime": 336.9846,
+    "eval_samples": 5398,
+    "eval_samples_per_second": 16.019,
+    "eval_steps_per_second": 1.003,
     "total_flos": 0.0,
     "train_loss": 0.2130171504020691,
     "train_runtime": 11716.0982,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 102400
 }

eval_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 2.0,
+    "eval_log_odds_chosen": 5.353264808654785,
+    "eval_log_odds_ratio": -0.020422911271452904,
+    "eval_logits/chosen": 8.594698905944824,
+    "eval_logits/rejected": 13.890603065490723,
+    "eval_logps/chosen": -0.08852054923772812,
+    "eval_logps/rejected": -2.195981502532959,
+    "eval_loss": 0.07974232733249664,
+    "eval_nll_loss": 0.07859200984239578,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -0.008852055296301842,
+    "eval_rewards/margins": 0.21074610948562622,
+    "eval_rewards/rejected": -0.2195981740951538,
+    "eval_runtime": 336.9846,
+    "eval_samples": 5398,
+    "eval_samples_per_second": 16.019,
+    "eval_steps_per_second": 1.003
+}

runs/Jul15_19-44-09_phe108-jieyuzhao-01/events.out.tfevents.1721110827.phe108-jieyuzhao-01.232196.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf97d2bac05783325fe82fbf6438b7fb3ee4844a180c37697700a19087006a60
+size 997