[25.05.20] update code support resume from checkpoints

requirements_version.txt

@@ -1,4 +1,4 @@
-<<<<<<< HEAD
+accelerate==1.7.0
 aiohappyeyeballs==2.6.1
 aiohttp==3.11.18
 aiosignal==1.3.2
@@ -20,6 +20,7 @@ comm==0.2.2
 datasets==3.6.0
 debugpy==1.8.2
 decorator==5.1.1
+deepspeed==0.16.7
 defusedxml==0.7.1
 dill==0.3.8
 distlib==0.3.9
@@ -54,8 +55,6 @@ jupyterlab==4.2.3
 jupyterlab-language-pack-zh-CN==4.2.post1
 jupyterlab_pygments==0.3.0
 jupyterlab_server==2.27.2
-# Editable install with no version control (llm_dolly==0.0.1)
--e /mnt/han.luzhi/dolly_llm
 MarkupSafe==2.1.5
 matplotlib-inline==0.1.7
 mistune==3.0.2
@@ -71,39 +70,6 @@ networkx==3.3
 notebook==6.5.2
 notebook_shim==0.2.4
 numpy==2.0.0
-=======
-<<<<<<< HEAD
-certifi==2025.4.26
-charset-normalizer==3.4.2
-filelock==3.18.0
-fsspec==2025.3.2
-=======
-accelerate==1.7.0
-aiohappyeyeballs==2.6.1
-aiohttp==3.11.18
-aiosignal==1.3.2
-attrs==25.3.0
-certifi==2025.4.26
-charset-normalizer==3.4.2
-datasets==3.6.0
-dill==0.3.8
-filelock==3.18.0
-frozenlist==1.6.0
-fsspec==2025.3.0
->>>>>>> fc9eefc (add pretrain code)
-huggingface-hub==0.30.2
-idna==3.10
-Jinja2==3.1.6
-MarkupSafe==3.0.2
-mpmath==1.3.0
-<<<<<<< HEAD
-=======
-multidict==6.4.3
-multiprocess==0.70.16
->>>>>>> fc9eefc (add pretrain code)
-networkx==3.4.2
-numpy==2.2.5
->>>>>>> 11473a798f338efdf3f70d665a00810099f51174
 nvidia-cublas-cu12==12.1.3.1
 nvidia-cuda-cupti-cu12==12.1.105
 nvidia-cuda-nvrtc-cu12==12.1.105
@@ -114,7 +80,6 @@ nvidia-curand-cu12==10.3.2.106
 nvidia-cusolver-cu12==11.4.5.107
 nvidia-cusparse-cu12==12.1.0.106
 nvidia-nccl-cu12==2.20.5
-<<<<<<< HEAD
 nvidia-nvjitlink-cu12==12.5.82
 nvidia-nvtx-cu12==12.1.105
 overrides==7.7.0
@@ -156,12 +121,13 @@ sniffio==1.3.1
 soupsieve==2.5
 stack-data==0.6.3
 sympy==1.13.0
+tensorboardX==2.6.2.2
 terminado==0.18.1
 tinycss2==1.3.0
 tokenizers==0.21.1
-torch @ file:///workspace/torch-2.3.1%2Bcu121-cp312-cp312-linux_x86_64.whl#sha256=b3c586f4ab25e83efffccfb97079e91325329bc228166555c4bb93957753d4ea
-torchaudio @ file:///workspace/torchaudio-2.3.1%2Bcu121-cp312-cp312-linux_x86_64.whl#sha256=b00773dde3aa30d9b1b98875650428fbfb69fe30b98ebb5ceffbd8fc61de8125
-torchvision @ file:///workspace/torchvision-0.18.1%2Bcu121-cp312-cp312-linux_x86_64.whl#sha256=ce8d5b992056f0640a39ef5734342e43ca4a801547de27fb8dbc3055d9345947
+torch==torch-2.3.1
+torchaudio==-2.3.1
+torchvision==-0.18.1
 tornado==6.4.1
 tqdm==4.67.1
 traitlets==5.14.3
@@ -178,46 +144,3 @@ webencodings==0.5.1
 websocket-client==1.8.0
 xxhash==3.5.0
 yarl==1.20.0
-=======
-nvidia-nvjitlink-cu12==12.9.41
-nvidia-nvtx-cu12==12.1.105
-packaging==25.0
-<<<<<<< HEAD
-protobuf==3.20.0
-=======
-pandas==2.2.3
-propcache==0.3.1
-protobuf==3.20.0
-psutil==7.0.0
-pyarrow==20.0.0
-python-dateutil==2.9.0.post0
-pytz==2025.2
->>>>>>> fc9eefc (add pretrain code)
-PyYAML==6.0.2
-regex==2024.11.6
-requests==2.32.3
-safetensors==0.5.3
-sentencepiece==0.2.0
-<<<<<<< HEAD
-=======
-setuptools==78.1.1
-six==1.17.0
->>>>>>> fc9eefc (add pretrain code)
-sympy==1.14.0
-tokenizers==0.21.1
-torch==2.3.1
-tqdm==4.67.1
-transformers==4.51.3
-<<<<<<< HEAD
-triton==2.3.1
-typing_extensions==4.13.2
-urllib3==2.4.0
-=======
-typing_extensions==4.13.2
-tzdata==2025.2
-urllib3==2.4.0
-wheel==0.45.1
-xxhash==3.5.0
-yarl==1.20.0
->>>>>>> fc9eefc (add pretrain code)
->>>>>>> 11473a798f338efdf3f70d665a00810099f51174