update readme
This commit is contained in:
parent
0411a4b3e1
commit
62dca5bb82
|
@ -12,6 +12,8 @@
|
||||||
|
|
||||||
## Changelog
|
## Changelog
|
||||||
|
|
||||||
|
[23/07/31] Now we support dataset streaming. Try `--streaming` and `--max_steps 100` arguments to stream your dataset.
|
||||||
|
|
||||||
[23/07/19] Now we support training the **LLaMA-2** models in this repo. Try `--model_name_or_path meta-llama/Llama-2-7b-hf` argument to use the LLaMA-2 model. Remember to use `--template llama2` argument when you are using the LLaMA-2-chat model.
|
[23/07/19] Now we support training the **LLaMA-2** models in this repo. Try `--model_name_or_path meta-llama/Llama-2-7b-hf` argument to use the LLaMA-2 model. Remember to use `--template llama2` argument when you are using the LLaMA-2-chat model.
|
||||||
|
|
||||||
[23/07/18] Now we develop an all-in-one Web UI for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development.
|
[23/07/18] Now we develop an all-in-one Web UI for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development.
|
||||||
|
|
|
@ -12,6 +12,8 @@
|
||||||
|
|
||||||
## 更新日志
|
## 更新日志
|
||||||
|
|
||||||
|
[23/07/31] 现在我们支持了训练数据流式加载。请尝试使用 `--streaming` 和 `--max_steps 100` 参数来流式加载数据集。
|
||||||
|
|
||||||
[23/07/19] 现在我们支持了 **LLaMA-2** 模型的训练。请尝试使用 `--model_name_or_path meta-llama/Llama-2-7b-hf` 参数。请注意使用 LLaMA-2-chat 模型需要添加 `--template llama2` 参数。
|
[23/07/19] 现在我们支持了 **LLaMA-2** 模型的训练。请尝试使用 `--model_name_or_path meta-llama/Llama-2-7b-hf` 参数。请注意使用 LLaMA-2-chat 模型需要添加 `--template llama2` 参数。
|
||||||
|
|
||||||
[23/07/18] 我们开发了支持训练和测试的浏览器一键微调界面。请尝试使用 `train_web.py` 在您的浏览器中微调模型。感谢 [@KanadeSiina](https://github.com/KanadeSiina) 和 [@codemayq](https://github.com/codemayq) 在该功能开发中付出的努力。
|
[23/07/18] 我们开发了支持训练和测试的浏览器一键微调界面。请尝试使用 `train_web.py` 在您的浏览器中微调模型。感谢 [@KanadeSiina](https://github.com/KanadeSiina) 和 [@codemayq](https://github.com/codemayq) 在该功能开发中付出的努力。
|
||||||
|
|
|
@ -108,6 +108,8 @@ def get_train_args(
|
||||||
logger.warning("`dev_ratio` is incompatible with `streaming`. Disabling development set.")
|
logger.warning("`dev_ratio` is incompatible with `streaming`. Disabling development set.")
|
||||||
data_args.dev_ratio = 0
|
data_args.dev_ratio = 0
|
||||||
|
|
||||||
|
assert not (training_args.max_steps == -1 and data_args.streaming), "Please specify `max_steps` in streaming mode."
|
||||||
|
|
||||||
training_args.optim = "adamw_torch" if training_args.optim == "adamw_hf" else training_args.optim # suppress warning
|
training_args.optim = "adamw_torch" if training_args.optim == "adamw_hf" else training_args.optim # suppress warning
|
||||||
|
|
||||||
if model_args.quantization_bit is not None:
|
if model_args.quantization_bit is not None:
|
||||||
|
@ -119,10 +121,10 @@ def get_train_args(
|
||||||
model_args.compute_dtype = torch.float32
|
model_args.compute_dtype = torch.float32
|
||||||
|
|
||||||
# Log on each process the small summary:
|
# Log on each process the small summary:
|
||||||
logger.info(
|
logger.info("Process rank: {}, device: {}, n_gpu: {}\n distributed training: {}, 16-bits training: {}".format(
|
||||||
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}\n"
|
training_args.local_rank, training_args.device, training_args.n_gpu,
|
||||||
+ f" distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
|
bool(training_args.local_rank != -1), training_args.fp16
|
||||||
)
|
))
|
||||||
logger.info(f"Training/evaluation parameters {training_args}")
|
logger.info(f"Training/evaluation parameters {training_args}")
|
||||||
|
|
||||||
# Set seed before initializing model.
|
# Set seed before initializing model.
|
||||||
|
|
Loading…
Reference in New Issue