Instructions to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1")
model = AutoModelForCausalLM.from_pretrained("PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1

SGLang

How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with Docker Model Runner:
```
docker model run hf.co/PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1
```

ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 / trainer_log.jsonl

TianyiQ

Upload folder using huggingface_hub

30547d4 verified over 2 years ago

Raw History Blame Contribute Delete

5.35 kB

	{"current_steps": 1, "total_steps": 60, "loss": 1.1097, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.008333333333333333, "percentage": 1.67, "elapsed_time": "0:06:00", "remaining_time": "5:54:22"}
	{"current_steps": 3, "total_steps": 60, "loss": 1.1424, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.025, "percentage": 5.0, "elapsed_time": "0:16:35", "remaining_time": "5:15:09"}
	{"current_steps": 6, "total_steps": 60, "loss": 1.1714, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.000000000000001e-07, "epoch": 0.05, "percentage": 10.0, "elapsed_time": "0:32:17", "remaining_time": "4:50:41"}
	{"current_steps": 9, "total_steps": 60, "loss": 1.1459, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4000000000000003e-06, "epoch": 0.075, "percentage": 15.0, "elapsed_time": "0:47:54", "remaining_time": "4:31:29"}
	{"current_steps": 12, "total_steps": 60, "loss": 1.1465, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-06, "epoch": 0.1, "percentage": 20.0, "elapsed_time": "1:03:49", "remaining_time": "4:15:16"}
	{"current_steps": 15, "total_steps": 60, "loss": 1.1517, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.839090909090909e-06, "epoch": 0.125, "percentage": 25.0, "elapsed_time": "1:19:38", "remaining_time": "3:58:54"}
	{"current_steps": 18, "total_steps": 60, "loss": 1.0991, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.678181818181818e-06, "epoch": 0.15, "percentage": 30.0, "elapsed_time": "1:35:30", "remaining_time": "3:42:51"}
	{"current_steps": 21, "total_steps": 60, "loss": 1.1481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5172727272727275e-06, "epoch": 0.175, "percentage": 35.0, "elapsed_time": "1:51:38", "remaining_time": "3:27:19"}
	{"current_steps": 24, "total_steps": 60, "loss": 1.151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3563636363636366e-06, "epoch": 0.2, "percentage": 40.0, "elapsed_time": "2:07:35", "remaining_time": "3:11:23"}
	{"current_steps": 27, "total_steps": 60, "loss": 1.1132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1954545454545456e-06, "epoch": 0.225, "percentage": 45.0, "elapsed_time": "2:23:39", "remaining_time": "2:55:34"}
	{"current_steps": 30, "total_steps": 60, "loss": 1.1043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0345454545454546e-06, "epoch": 0.25, "percentage": 50.0, "elapsed_time": "2:39:34", "remaining_time": "2:39:34"}
	{"current_steps": 33, "total_steps": 60, "loss": 1.0492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9272727272727273e-06, "epoch": 0.275, "percentage": 55.0, "elapsed_time": "2:55:27", "remaining_time": "2:23:33"}
	{"current_steps": 36, "total_steps": 60, "loss": 1.1206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8199999999999997e-06, "epoch": 0.3, "percentage": 60.0, "elapsed_time": "3:11:35", "remaining_time": "2:07:43"}
	{"current_steps": 39, "total_steps": 60, "loss": 1.0908, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.659090909090909e-06, "epoch": 0.325, "percentage": 65.0, "elapsed_time": "3:27:25", "remaining_time": "1:51:41"}
	{"current_steps": 42, "total_steps": 60, "loss": 1.0982, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4981818181818184e-06, "epoch": 0.35, "percentage": 70.0, "elapsed_time": "3:43:08", "remaining_time": "1:35:37"}
	{"current_steps": 45, "total_steps": 60, "loss": 1.1147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3372727272727274e-06, "epoch": 0.375, "percentage": 75.0, "elapsed_time": "3:58:47", "remaining_time": "1:19:35"}
	{"current_steps": 48, "total_steps": 60, "loss": 1.1004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1763636363636364e-06, "epoch": 0.4, "percentage": 80.0, "elapsed_time": "4:14:31", "remaining_time": "1:03:37"}
	{"current_steps": 51, "total_steps": 60, "loss": 1.0982, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0154545454545454e-06, "epoch": 0.425, "percentage": 85.0, "elapsed_time": "4:30:10", "remaining_time": "0:47:40"}
	{"current_steps": 54, "total_steps": 60, "loss": 1.0794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.545454545454544e-07, "epoch": 0.45, "percentage": 90.0, "elapsed_time": "4:46:02", "remaining_time": "0:31:46"}
	{"current_steps": 57, "total_steps": 60, "loss": 1.0948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.936363636363635e-07, "epoch": 0.475, "percentage": 95.0, "elapsed_time": "5:01:44", "remaining_time": "0:15:52"}
	{"current_steps": 60, "total_steps": 60, "loss": 1.1091, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.327272727272729e-07, "epoch": 0.5, "percentage": 100.0, "elapsed_time": "5:17:33", "remaining_time": "0:00:00"}
	{"current_steps": 60, "total_steps": 60, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5, "percentage": 100.0, "elapsed_time": "5:17:33", "remaining_time": "0:00:00"}