Merge remote-tracking branch 'origin/main' into dev/shuchang

Author: TaoShuchang

README.md

@@ -1,6 +1,6 @@
 # AgentJet (Beta)
 
-[![Benchmarking](https://img.shields.io/badge/Benchmarking-0078D4?style=for-the-badge&logo=github)](https://benchmark.agent-matrix.com/)
+[![Benchmarking](https://img.shields.io/badge/Benchmarking-0078D4?style=for-the-badge&logo=github)](https://benchmark.agentjet.top/)
 [![Docs](https://img.shields.io/badge/Docs-Read%20the%20Documents-0A7ECC?style=for-the-badge&logo=readthedocs&logoColor=white)](https://modelscope.github.io/AgentJet)
 [![License](https://img.shields.io/badge/License-Apache--2.0-4c1?style=for-the-badge)](LICENSE)
 [![Python](https://img.shields.io/badge/Python-3.10+-3776AB?style=for-the-badge&logo=python&logoColor=white)](https://modelscope.github.io/AgentJet/en/installation#requirements)
@@ -40,7 +40,7 @@ We aim to build a easy-to-learn Agent tuner that unlock more possibilities for a
 - **Rich Tutorial Library**. AgentJet provides a rich library of [examples](https://github.com/modelscope/AgentJet/tree/main/tutorial) as tutorials.
 - **Efficient and Scalable**. AgentJet uses [verl] as the default backbone (`--backbone=verl`). However, we also support [trinity](https://github.com/modelscope/Trinity-RFT/) as alternative backbone, accelerating your tuning process via fully asynchronous RFT.
 - **Flexible and Fast**. AgentJet supports [multi-agent workflows](https://modelscope.github.io/AgentJet/en/workflow/) and adopts a context merging technique, accelerating training by 1.5x to 10x when the workflow involves multi-turn (or multi-agent) conversations.
-- **Reliability and Reproducibility**. Our team keeps track of framework performance across multiple [tasks + major-git-version + training-backbones](https://benchmark.agent-matrix.com/) (under construction, still gathering data, coming soon).
+- **Reliability and Reproducibility**. Our team keeps track of framework performance across multiple [tasks + major-git-version + training-backbones](https://benchmark.agentjet.top/) (under construction, still gathering data, coming soon).
 
 For advanced researchers, AgentJet also provides high-resolution logging and debugging solutions:
 <!-- For advanced researchers, AgentJet provides high-resolution logging and debugging solutions that are, to our knowledge, unprecedented in other prior projects. -->

ajet/utils/config_utils.py

@@ -275,7 +275,7 @@ def prepare_experiment_config(yaml_path, exp_dir, backbone):
     else:
         exp_name = exp_name.replace("|", "-")
 
-    backup_dir = os.path.join(exp_dir, exp_name, "backup")
+    backup_dir = os.path.abspath(os.path.join(exp_dir, exp_name, "backup"))
     yaml_backup_dst = os.path.join(exp_dir, exp_name, "yaml_backup.yaml")
     yaml_backup_dst = os.path.abspath(yaml_backup_dst)
     exe_exp_base = os.path.dirname(yaml_backup_dst)

docs/en/intro.md

@@ -13,7 +13,7 @@ AgentJet aims to build a state-of-the-art agent tuning platform for both develop
 - **Rich Tutorial Library**. AgentJet provides a rich library of [examples](https://github.com/modelscope/AgentJet/tree/main/tutorial) as tutorials.
 - **Efficient and Scalable**. AgentJet uses [verl] as the default backbone (`--backbone=verl`). However, we also support [trinity](https://github.com/modelscope/Trinity-RFT/) as alternative backbone, accelerating your tuning process via fully asynchronous RFT.
 - **Flexible and Fast**. AgentJet supports [multi-agent workflows](workflow.md) and adopts a context merging technique, accelerating training by 1.5x to 10x when the workflow involves multi-turn (or multi-agent) conversations.
-- **Reliability and Reproducibility**. Our team keeps track of framework performance across multiple [tasks + major-git-version + training-backbones](https://benchmark.agent-matrix.com/) (under construction, still gathering data, coming soon).
+- **Reliability and Reproducibility**. Our team keeps track of framework performance across multiple [tasks + major-git-version + training-backbones](https://benchmark.agentjet.top/) (under construction, still gathering data, coming soon).
 
 For advanced researchers, AgentJet also provides high-resolution logging and debugging solutions:
 <!-- For advanced researchers, AgentJet provides high-resolution logging and debugging solutions that are, to our knowledge, unprecedented in other prior projects. -->

docs/en/quickstart.md

@@ -45,7 +45,7 @@ tuned_model = job.tune()
 ## 3. Compare with Community Training Curves
 
 <div class="card-grid">
-<a href="https://benchmark.agent-matrix.com/examples" class="feature-card"><div class="card-header"><img src="https://api.iconify.design/mdi:calculator-variant.svg" class="card-icon card-icon-math" alt=""><h3>AgentJet Benchmark Tracking System (Developing-In-Progress)</h3></div><p class="card-desc">Compare training curves with community. Investigate the influence of versions, backbones, hyper-parameters, etc.</p></a>
+<a href="https://benchmark.agentjet.top/examples" class="feature-card"><div class="card-header"><img src="https://api.iconify.design/mdi:calculator-variant.svg" class="card-icon card-icon-math" alt=""><h3>AgentJet Benchmark Tracking System (Developing-In-Progress)</h3></div><p class="card-desc">Compare training curves with community. Investigate the influence of versions, backbones, hyper-parameters, etc.</p></a>
 </div>
 
 

docs/index.md

@@ -29,7 +29,7 @@
             Rich examples as beginner's tutorial: <b>math agent</b>, <b>werewolves rpg</b>, <b>appworld</b> ... All with step-by-step
             guides. Covering various agentic frameworks.</p>
     </a>
-    <a href="https://benchmark.agent-matrix.com/" class="feature-card">
+    <a href="https://benchmark.agentjet.top/" class="feature-card">
         <div class="card-header"><img src="https://api.iconify.design/lucide:shield-check.svg" class="card-icon card-icon-tool"
                 alt="">
             <h3>Reliable and Reproducible</h3>

tutorial/README.md

@@ -8,4 +8,4 @@ Explore our rich library of examples to kickstart your journey.
 
 - Example Benchmark Tracking System:
 
-    https://benchmark.agent-matrix.com/examples
+    https://benchmark.agentjet.top/examples