End of training

README.md

@@ -2,9 +2,16 @@
 license: apache-2.0
 base_model: hZzy/qwen2.5-0.5b-sft-25-1
 tags:
+- alignment-handbook
+- ndcg
 - trl
 - expo
 - generated_from_trainer
+- trl
+- expo
+- generated_from_trainer
+datasets:
+- hZzy/train_pairwise_strong_new
 model-index:
 - name: qwen2.5-0.5b-expo-L2EXPO-25-3
   results: []
@@ -16,18 +23,18 @@ 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/zhiyuzha-university-of-florida/huggingface/runs/vdeeps75)
 # qwen2.5-0.5b-expo-L2EXPO-25-3
 
-This model is a fine-tuned version of [hZzy/qwen2.5-0.5b-sft-25-1](https://huggingface.co/hZzy/qwen2.5-0.5b-sft-25-1) on an unknown dataset.
+This model is a fine-tuned version of [hZzy/qwen2.5-0.5b-sft-25-1](https://huggingface.co/hZzy/qwen2.5-0.5b-sft-25-1) on the hZzy/train_pairwise_strong_new dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4185
-- Objective: 0.4335
-- Ranking Simple: 0.4918
-- Reward Accuracy: 0.6264
-- Logp Accuracy: 0.4918
-- Log Diff Policy: 0.6265
-- Chosen Logps: -93.7758
-- Rejected Logps: -94.4023
-- Chosen Rewards: 0.1562
-- Rejected Rewards: 0.0877
+- Loss: 0.4184
+- Objective: 0.4334
+- Ranking Simple: 0.4905
+- Reward Accuracy: 0.6291
+- Logp Accuracy: 0.4905
+- Log Diff Policy: 0.6270
+- Chosen Logps: -93.7722
+- Rejected Logps: -94.3992
+- Chosen Rewards: 0.1566
+- Rejected Rewards: 0.0880
 - Logits: -1.2008
 
 ## Model description

all_results.json

@@ -1,5 +1,20 @@
 {
     "epoch": 2.987152034261242,
+    "eval_chosen_logps": -93.77220916748047,
+    "eval_chosen_rewards": 0.1566028594970703,
+    "eval_log_diff_policy": 0.627028226852417,
+    "eval_logits": -1.2008216381072998,
+    "eval_logp_accuracy": 0.49048912525177,
+    "eval_loss": 0.4184386134147644,
+    "eval_objective": 0.4334131181240082,
+    "eval_ranking_simple": 0.49048912525177,
+    "eval_rejected_logps": -94.39924621582031,
+    "eval_rejected_rewards": 0.08802003413438797,
+    "eval_reward_accuracy": 0.6290760636329651,
+    "eval_runtime": 251.8277,
+    "eval_samples": 4407,
+    "eval_samples_per_second": 17.5,
+    "eval_steps_per_second": 0.731,
     "total_flos": 0.0,
     "train_loss": 0.27528571787700856,
     "train_runtime": 19429.5857,

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.42.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151665

eval_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 2.987152034261242,
+    "eval_chosen_logps": -93.77220916748047,
+    "eval_chosen_rewards": 0.1566028594970703,
+    "eval_log_diff_policy": 0.627028226852417,
+    "eval_logits": -1.2008216381072998,
+    "eval_logp_accuracy": 0.49048912525177,
+    "eval_loss": 0.4184386134147644,
+    "eval_objective": 0.4334131181240082,
+    "eval_ranking_simple": 0.49048912525177,
+    "eval_rejected_logps": -94.39924621582031,
+    "eval_rejected_rewards": 0.08802003413438797,
+    "eval_reward_accuracy": 0.6290760636329651,
+    "eval_runtime": 251.8277,
+    "eval_samples": 4407,
+    "eval_samples_per_second": 17.5,
+    "eval_steps_per_second": 0.731
+}