Instructions to use PKU-Alignment/ProgressGym-HistLlama3-70B-C013-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-C013-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-C013-pretrain-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PKU-Alignment/ProgressGym-HistLlama3-70B-C013-pretrain-v0.1")
model = AutoModelForCausalLM.from_pretrained("PKU-Alignment/ProgressGym-HistLlama3-70B-C013-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=40)
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-C013-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-C013-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-C013-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-C013-pretrain-v0.1

SGLang

How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C013-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-C013-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-C013-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-C013-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-C013-pretrain-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C013-pretrain-v0.1 with Docker Model Runner:
```
docker model run hf.co/PKU-Alignment/ProgressGym-HistLlama3-70B-C013-pretrain-v0.1
```

ProgressGym-HistLlama3-70B-C013-pretrain-v0.1 / trainer_log.jsonl

TianyiQ

Upload folder using huggingface_hub

591063c verified about 2 years ago

Raw

History Blame Contribute Delete

10 kB

	{"current_steps": 1, "total_steps": 132, "loss": 0.8787, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.029850746268656716, "percentage": 0.76, "elapsed_time": "0:03:12", "remaining_time": "7:00:00"}
	{"current_steps": 7, "total_steps": 132, "loss": 0.8776, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0000000000000004e-07, "epoch": 0.208955223880597, "percentage": 5.3, "elapsed_time": "0:18:27", "remaining_time": "5:29:30"}
	{"current_steps": 7, "total_steps": 132, "loss": null, "eval_loss": 0.7901861071586609, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.208955223880597, "percentage": 5.3, "elapsed_time": "0:18:27", "remaining_time": "5:29:30"}
	{"current_steps": 14, "total_steps": 132, "loss": 0.8473, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8e-06, "epoch": 0.417910447761194, "percentage": 10.61, "elapsed_time": "0:38:54", "remaining_time": "5:27:55"}
	{"current_steps": 14, "total_steps": 132, "loss": null, "eval_loss": 0.7702628374099731, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.417910447761194, "percentage": 10.61, "elapsed_time": "0:38:54", "remaining_time": "5:27:55"}
	{"current_steps": 21, "total_steps": 132, "loss": 0.8293, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5095609265912853e-06, "epoch": 0.6268656716417911, "percentage": 15.91, "elapsed_time": "0:59:08", "remaining_time": "5:12:35"}
	{"current_steps": 21, "total_steps": 132, "loss": null, "eval_loss": 0.760272204875946, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6268656716417911, "percentage": 15.91, "elapsed_time": "0:59:08", "remaining_time": "5:12:35"}
	{"current_steps": 28, "total_steps": 132, "loss": 0.8173, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3197749551783641e-06, "epoch": 0.835820895522388, "percentage": 21.21, "elapsed_time": "1:29:14", "remaining_time": "5:31:27"}
	{"current_steps": 28, "total_steps": 132, "loss": null, "eval_loss": 0.7481057047843933, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.835820895522388, "percentage": 21.21, "elapsed_time": "1:29:14", "remaining_time": "5:31:27"}
	{"current_steps": 35, "total_steps": 132, "loss": 0.7415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.783887430182062e-07, "epoch": 1.044776119402985, "percentage": 26.52, "elapsed_time": "1:49:14", "remaining_time": "5:02:43"}
	{"current_steps": 35, "total_steps": 132, "loss": null, "eval_loss": 0.7402028441429138, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.044776119402985, "percentage": 26.52, "elapsed_time": "1:49:14", "remaining_time": "5:02:43"}
	{"current_steps": 42, "total_steps": 132, "loss": 0.6794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8102735091851235e-07, "epoch": 1.2537313432835822, "percentage": 31.82, "elapsed_time": "2:08:50", "remaining_time": "4:36:05"}
	{"current_steps": 42, "total_steps": 132, "loss": null, "eval_loss": 0.7418723106384277, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2537313432835822, "percentage": 31.82, "elapsed_time": "2:08:50", "remaining_time": "4:36:05"}
	{"current_steps": 49, "total_steps": 132, "loss": 0.6688, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9899658436440185e-07, "epoch": 1.462686567164179, "percentage": 37.12, "elapsed_time": "2:28:47", "remaining_time": "4:12:02"}
	{"current_steps": 49, "total_steps": 132, "loss": null, "eval_loss": 0.7392202615737915, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.462686567164179, "percentage": 37.12, "elapsed_time": "2:28:47", "remaining_time": "4:12:02"}
	{"current_steps": 56, "total_steps": 132, "loss": 0.6498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1300091285551449e-07, "epoch": 1.671641791044776, "percentage": 42.42, "elapsed_time": "2:59:07", "remaining_time": "4:03:05"}
	{"current_steps": 56, "total_steps": 132, "loss": null, "eval_loss": 0.7367225289344788, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.671641791044776, "percentage": 42.42, "elapsed_time": "2:59:07", "remaining_time": "4:03:05"}
	{"current_steps": 63, "total_steps": 132, "loss": 0.6701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.476064096023686e-08, "epoch": 1.8805970149253732, "percentage": 47.73, "elapsed_time": "3:19:23", "remaining_time": "3:38:22"}
	{"current_steps": 63, "total_steps": 132, "loss": null, "eval_loss": 0.7358315587043762, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.8805970149253732, "percentage": 47.73, "elapsed_time": "3:19:23", "remaining_time": "3:38:22"}
	{"current_steps": 70, "total_steps": 132, "loss": 0.664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.89232146321995e-08, "epoch": 2.08955223880597, "percentage": 53.03, "elapsed_time": "3:39:45", "remaining_time": "3:14:38"}
	{"current_steps": 70, "total_steps": 132, "loss": null, "eval_loss": 0.7354702353477478, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.08955223880597, "percentage": 53.03, "elapsed_time": "3:39:45", "remaining_time": "3:14:38"}
	{"current_steps": 77, "total_steps": 132, "loss": 0.6447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.289674857255442e-08, "epoch": 2.298507462686567, "percentage": 58.33, "elapsed_time": "3:59:54", "remaining_time": "2:51:22"}
	{"current_steps": 77, "total_steps": 132, "loss": null, "eval_loss": 0.736127495765686, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.298507462686567, "percentage": 58.33, "elapsed_time": "3:59:54", "remaining_time": "2:51:22"}
	{"current_steps": 84, "total_steps": 132, "loss": 0.6412, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.082712625717188e-08, "epoch": 2.5074626865671643, "percentage": 63.64, "elapsed_time": "4:29:23", "remaining_time": "2:33:56"}
	{"current_steps": 84, "total_steps": 132, "loss": null, "eval_loss": 0.7373142242431641, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5074626865671643, "percentage": 63.64, "elapsed_time": "4:29:23", "remaining_time": "2:33:56"}
	{"current_steps": 91, "total_steps": 132, "loss": 0.6458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.020097212085352e-08, "epoch": 2.716417910447761, "percentage": 68.94, "elapsed_time": "4:49:02", "remaining_time": "2:10:13"}
	{"current_steps": 91, "total_steps": 132, "loss": null, "eval_loss": 0.7382717728614807, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.716417910447761, "percentage": 68.94, "elapsed_time": "4:49:02", "remaining_time": "2:10:13"}
	{"current_steps": 98, "total_steps": 132, "loss": 0.6356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0050722602692304e-08, "epoch": 2.925373134328358, "percentage": 74.24, "elapsed_time": "5:08:53", "remaining_time": "1:47:10"}
	{"current_steps": 98, "total_steps": 132, "loss": null, "eval_loss": 0.7387175559997559, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.925373134328358, "percentage": 74.24, "elapsed_time": "5:08:53", "remaining_time": "1:47:10"}
	{"current_steps": 105, "total_steps": 132, "loss": 0.6398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.001050931854095e-08, "epoch": 3.1343283582089554, "percentage": 79.55, "elapsed_time": "5:29:03", "remaining_time": "1:24:36"}
	{"current_steps": 105, "total_steps": 132, "loss": null, "eval_loss": 0.7387120723724365, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.1343283582089554, "percentage": 79.55, "elapsed_time": "5:29:03", "remaining_time": "1:24:36"}
	{"current_steps": 112, "total_steps": 132, "loss": 0.6228, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000119265172339e-08, "epoch": 3.343283582089552, "percentage": 84.85, "elapsed_time": "5:59:29", "remaining_time": "1:04:11"}
	{"current_steps": 112, "total_steps": 132, "loss": null, "eval_loss": 0.7390681505203247, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.343283582089552, "percentage": 84.85, "elapsed_time": "5:59:29", "remaining_time": "1:04:11"}
	{"current_steps": 119, "total_steps": 132, "loss": 0.6139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000078923070654e-08, "epoch": 3.5522388059701493, "percentage": 90.15, "elapsed_time": "6:19:38", "remaining_time": "0:41:28"}
	{"current_steps": 119, "total_steps": 132, "loss": null, "eval_loss": 0.7394906282424927, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.5522388059701493, "percentage": 90.15, "elapsed_time": "6:19:38", "remaining_time": "0:41:28"}
	{"current_steps": 126, "total_steps": 132, "loss": 0.591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000212746016e-08, "epoch": 3.7611940298507465, "percentage": 95.45, "elapsed_time": "6:40:09", "remaining_time": "0:19:03"}
	{"current_steps": 126, "total_steps": 132, "loss": null, "eval_loss": 0.7398449778556824, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.7611940298507465, "percentage": 95.45, "elapsed_time": "6:40:09", "remaining_time": "0:19:03"}
	{"current_steps": 132, "total_steps": 132, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.9402985074626864, "percentage": 100.0, "elapsed_time": "6:57:46", "remaining_time": "0:00:00"}
	{"current_steps": 4, "total_steps": 4, "loss": null, "eval_loss": 0.7400416135787964, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.9402985074626864, "percentage": 100.0, "elapsed_time": "7:06:05", "remaining_time": "0:00:00"}