Instructions to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with Transformers:

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

pipe = pipeline("text-generation", model="code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt")
model = AutoModelForCausalLM.from_pretrained("code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt", 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 code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt

SGLang

How to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt 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 "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt" \
    --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": "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt",
		"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 "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt" \
        --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": "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with Docker Model Runner:
```
docker model run hf.co/code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt
```

Qwen3-8B-Critic-SFT-Detailed-Prompt / trainer_log.jsonl

shubhamrgandhi

Initial upload: Detailed-prompt ablation critic — Qwen3-8B SFT'd on detailed-prompt critiques over CWM trajectories. 3,135 training samples.

70f9666 verified 3 months ago

Raw

History Blame Contribute Delete

23 kB

	{"current_steps": 10, "total_steps": 1176, "loss": 0.8792, "lr": 3.813559322033899e-07, "epoch": 0.025510204081632654, "percentage": 0.85, "elapsed_time": "0:09:53", "remaining_time": "19:13:30"}
	{"current_steps": 20, "total_steps": 1176, "loss": 0.8689, "lr": 8.050847457627118e-07, "epoch": 0.05102040816326531, "percentage": 1.7, "elapsed_time": "0:19:38", "remaining_time": "18:55:21"}
	{"current_steps": 30, "total_steps": 1176, "loss": 0.8211, "lr": 1.228813559322034e-06, "epoch": 0.07653061224489796, "percentage": 2.55, "elapsed_time": "0:29:23", "remaining_time": "18:42:46"}
	{"current_steps": 40, "total_steps": 1176, "loss": 0.7512, "lr": 1.652542372881356e-06, "epoch": 0.10204081632653061, "percentage": 3.4, "elapsed_time": "0:39:09", "remaining_time": "18:32:15"}
	{"current_steps": 50, "total_steps": 1176, "loss": 0.6971, "lr": 2.076271186440678e-06, "epoch": 0.12755102040816327, "percentage": 4.25, "elapsed_time": "0:48:42", "remaining_time": "18:16:47"}
	{"current_steps": 60, "total_steps": 1176, "loss": 0.6312, "lr": 2.5e-06, "epoch": 0.15306122448979592, "percentage": 5.1, "elapsed_time": "0:58:24", "remaining_time": "18:06:25"}
	{"current_steps": 70, "total_steps": 1176, "loss": 0.6424, "lr": 2.9237288135593224e-06, "epoch": 0.17857142857142858, "percentage": 5.95, "elapsed_time": "1:08:08", "remaining_time": "17:56:36"}
	{"current_steps": 80, "total_steps": 1176, "loss": 0.614, "lr": 3.347457627118644e-06, "epoch": 0.20408163265306123, "percentage": 6.8, "elapsed_time": "1:17:39", "remaining_time": "17:43:59"}
	{"current_steps": 90, "total_steps": 1176, "loss": 0.6052, "lr": 3.7711864406779664e-06, "epoch": 0.22959183673469388, "percentage": 7.65, "elapsed_time": "1:27:21", "remaining_time": "17:34:02"}
	{"current_steps": 100, "total_steps": 1176, "loss": 0.5939, "lr": 4.1949152542372886e-06, "epoch": 0.25510204081632654, "percentage": 8.5, "elapsed_time": "1:37:00", "remaining_time": "17:23:47"}
	{"current_steps": 110, "total_steps": 1176, "loss": 0.5806, "lr": 4.618644067796611e-06, "epoch": 0.28061224489795916, "percentage": 9.35, "elapsed_time": "1:46:35", "remaining_time": "17:12:58"}
	{"current_steps": 120, "total_steps": 1176, "loss": 0.5516, "lr": 4.99998897856601e-06, "epoch": 0.30612244897959184, "percentage": 10.2, "elapsed_time": "1:56:09", "remaining_time": "17:02:14"}
	{"current_steps": 130, "total_steps": 1176, "loss": 0.554, "lr": 4.998666524068091e-06, "epoch": 0.33163265306122447, "percentage": 11.05, "elapsed_time": "2:05:34", "remaining_time": "16:50:26"}
	{"current_steps": 140, "total_steps": 1176, "loss": 0.5455, "lr": 4.995141118770565e-06, "epoch": 0.35714285714285715, "percentage": 11.9, "elapsed_time": "2:15:13", "remaining_time": "16:40:42"}
	{"current_steps": 150, "total_steps": 1176, "loss": 0.5624, "lr": 4.9894158708490694e-06, "epoch": 0.3826530612244898, "percentage": 12.76, "elapsed_time": "2:25:03", "remaining_time": "16:32:10"}
	{"current_steps": 160, "total_steps": 1176, "loss": 0.5336, "lr": 4.98149582797178e-06, "epoch": 0.40816326530612246, "percentage": 13.61, "elapsed_time": "2:34:46", "remaining_time": "16:22:49"}
	{"current_steps": 170, "total_steps": 1176, "loss": 0.5282, "lr": 4.9713879728491196e-06, "epoch": 0.4336734693877551, "percentage": 14.46, "elapsed_time": "2:44:33", "remaining_time": "16:13:45"}
	{"current_steps": 180, "total_steps": 1176, "loss": 0.5457, "lr": 4.9591012170774605e-06, "epoch": 0.45918367346938777, "percentage": 15.31, "elapsed_time": "2:54:15", "remaining_time": "16:04:11"}
	{"current_steps": 190, "total_steps": 1176, "loss": 0.52, "lr": 4.9446463932822e-06, "epoch": 0.4846938775510204, "percentage": 16.16, "elapsed_time": "3:03:44", "remaining_time": "15:53:30"}
	{"current_steps": 200, "total_steps": 1176, "loss": 0.5115, "lr": 4.928036245567176e-06, "epoch": 0.5102040816326531, "percentage": 17.01, "elapsed_time": "3:13:22", "remaining_time": "15:43:42"}
	{"current_steps": 210, "total_steps": 1176, "loss": 0.5345, "lr": 4.909285418278818e-06, "epoch": 0.5357142857142857, "percentage": 17.86, "elapsed_time": "3:23:04", "remaining_time": "15:34:08"}
	{"current_steps": 220, "total_steps": 1176, "loss": 0.5136, "lr": 4.888410443094951e-06, "epoch": 0.5612244897959183, "percentage": 18.71, "elapsed_time": "3:32:45", "remaining_time": "15:24:29"}
	{"current_steps": 230, "total_steps": 1176, "loss": 0.5226, "lr": 4.865429724449632e-06, "epoch": 0.5867346938775511, "percentage": 19.56, "elapsed_time": "3:42:35", "remaining_time": "15:15:30"}
	{"current_steps": 240, "total_steps": 1176, "loss": 0.5273, "lr": 4.840363523306871e-06, "epoch": 0.6122448979591837, "percentage": 20.41, "elapsed_time": "3:52:05", "remaining_time": "15:05:07"}
	{"current_steps": 250, "total_steps": 1176, "loss": 0.5054, "lr": 4.8132339392975384e-06, "epoch": 0.6377551020408163, "percentage": 21.26, "elapsed_time": "4:01:33", "remaining_time": "14:54:45"}
	{"current_steps": 260, "total_steps": 1176, "loss": 0.5106, "lr": 4.784064891235212e-06, "epoch": 0.6632653061224489, "percentage": 22.11, "elapsed_time": "4:11:07", "remaining_time": "14:44:42"}
	{"current_steps": 270, "total_steps": 1176, "loss": 0.5003, "lr": 4.752882096028146e-06, "epoch": 0.6887755102040817, "percentage": 22.96, "elapsed_time": "4:20:42", "remaining_time": "14:34:49"}
	{"current_steps": 280, "total_steps": 1176, "loss": 0.5062, "lr": 4.7197130460059385e-06, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "4:30:20", "remaining_time": "14:25:05"}
	{"current_steps": 290, "total_steps": 1176, "loss": 0.5085, "lr": 4.684586984680904e-06, "epoch": 0.7397959183673469, "percentage": 24.66, "elapsed_time": "4:39:54", "remaining_time": "14:15:08"}
	{"current_steps": 300, "total_steps": 1176, "loss": 0.4909, "lr": 4.647534880965515e-06, "epoch": 0.7653061224489796, "percentage": 25.51, "elapsed_time": "4:49:44", "remaining_time": "14:06:01"}
	{"current_steps": 310, "total_steps": 1176, "loss": 0.4673, "lr": 4.6085894018686435e-06, "epoch": 0.7908163265306123, "percentage": 26.36, "elapsed_time": "4:59:29", "remaining_time": "13:56:38"}
	{"current_steps": 320, "total_steps": 1176, "loss": 0.4776, "lr": 4.567784883694671e-06, "epoch": 0.8163265306122449, "percentage": 27.21, "elapsed_time": "5:09:15", "remaining_time": "13:47:15"}
	{"current_steps": 330, "total_steps": 1176, "loss": 0.5074, "lr": 4.525157301770865e-06, "epoch": 0.8418367346938775, "percentage": 28.06, "elapsed_time": "5:18:54", "remaining_time": "13:37:34"}
	{"current_steps": 340, "total_steps": 1176, "loss": 0.5055, "lr": 4.4807442387297145e-06, "epoch": 0.8673469387755102, "percentage": 28.91, "elapsed_time": "5:28:37", "remaining_time": "13:28:00"}
	{"current_steps": 350, "total_steps": 1176, "loss": 0.489, "lr": 4.434584851374176e-06, "epoch": 0.8928571428571429, "percentage": 29.76, "elapsed_time": "5:38:19", "remaining_time": "13:18:26"}
	{"current_steps": 360, "total_steps": 1176, "loss": 0.4792, "lr": 4.38671983615506e-06, "epoch": 0.9183673469387755, "percentage": 30.61, "elapsed_time": "5:47:47", "remaining_time": "13:08:19"}
	{"current_steps": 370, "total_steps": 1176, "loss": 0.477, "lr": 4.337191393290975e-06, "epoch": 0.9438775510204082, "percentage": 31.46, "elapsed_time": "5:57:26", "remaining_time": "12:58:37"}
	{"current_steps": 380, "total_steps": 1176, "loss": 0.5063, "lr": 4.286043189562487e-06, "epoch": 0.9693877551020408, "percentage": 32.31, "elapsed_time": "6:07:08", "remaining_time": "12:49:04"}
	{"current_steps": 390, "total_steps": 1176, "loss": 0.4818, "lr": 4.233320319813271e-06, "epoch": 0.9948979591836735, "percentage": 33.16, "elapsed_time": "6:16:45", "remaining_time": "12:39:18"}
	{"current_steps": 400, "total_steps": 1176, "loss": 0.4184, "lr": 4.1790692671922205e-06, "epoch": 1.0204081632653061, "percentage": 34.01, "elapsed_time": "6:27:36", "remaining_time": "12:31:57"}
	{"current_steps": 410, "total_steps": 1176, "loss": 0.366, "lr": 4.12333786217155e-06, "epoch": 1.0459183673469388, "percentage": 34.86, "elapsed_time": "6:37:16", "remaining_time": "12:22:13"}
	{"current_steps": 420, "total_steps": 1176, "loss": 0.4001, "lr": 4.06617524037703e-06, "epoch": 1.0714285714285714, "percentage": 35.71, "elapsed_time": "6:46:57", "remaining_time": "12:12:31"}
	{"current_steps": 430, "total_steps": 1176, "loss": 0.3906, "lr": 4.007631799267536e-06, "epoch": 1.096938775510204, "percentage": 36.56, "elapsed_time": "6:56:46", "remaining_time": "12:03:02"}
	{"current_steps": 440, "total_steps": 1176, "loss": 0.3783, "lr": 3.947759153702097e-06, "epoch": 1.1224489795918366, "percentage": 37.41, "elapsed_time": "7:06:16", "remaining_time": "11:53:01"}
	{"current_steps": 450, "total_steps": 1176, "loss": 0.3764, "lr": 3.88661009043363e-06, "epoch": 1.1479591836734695, "percentage": 38.27, "elapsed_time": "7:15:49", "remaining_time": "11:43:08"}
	{"current_steps": 460, "total_steps": 1176, "loss": 0.3766, "lr": 3.824238521569462e-06, "epoch": 1.1734693877551021, "percentage": 39.12, "elapsed_time": "7:25:34", "remaining_time": "11:33:33"}
	{"current_steps": 470, "total_steps": 1176, "loss": 0.3896, "lr": 3.7606994370396947e-06, "epoch": 1.1989795918367347, "percentage": 39.97, "elapsed_time": "7:35:18", "remaining_time": "11:23:56"}
	{"current_steps": 480, "total_steps": 1176, "loss": 0.3838, "lr": 3.696048856115294e-06, "epoch": 1.2244897959183674, "percentage": 40.82, "elapsed_time": "7:45:02", "remaining_time": "11:14:17"}
	{"current_steps": 490, "total_steps": 1176, "loss": 0.3854, "lr": 3.6303437780186745e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "7:54:38", "remaining_time": "11:04:30"}
	{"current_steps": 500, "total_steps": 1176, "loss": 0.3617, "lr": 3.5636421316702975e-06, "epoch": 1.2755102040816326, "percentage": 42.52, "elapsed_time": "8:03:55", "remaining_time": "10:54:16"}
	{"current_steps": 510, "total_steps": 1176, "loss": 0.3852, "lr": 3.4960027246156043e-06, "epoch": 1.3010204081632653, "percentage": 43.37, "elapsed_time": "8:13:28", "remaining_time": "10:44:24"}
	{"current_steps": 520, "total_steps": 1176, "loss": 0.3831, "lr": 3.427485191177311e-06, "epoch": 1.3265306122448979, "percentage": 44.22, "elapsed_time": "8:23:06", "remaining_time": "10:34:41"}
	{"current_steps": 530, "total_steps": 1176, "loss": 0.3756, "lr": 3.358149939878772e-06, "epoch": 1.3520408163265305, "percentage": 45.07, "elapsed_time": "8:32:53", "remaining_time": "10:25:08"}
	{"current_steps": 540, "total_steps": 1176, "loss": 0.3799, "lr": 3.288058100184772e-06, "epoch": 1.3775510204081631, "percentage": 45.92, "elapsed_time": "8:42:18", "remaining_time": "10:15:09"}
	{"current_steps": 550, "total_steps": 1176, "loss": 0.3767, "lr": 3.217271468606694e-06, "epoch": 1.403061224489796, "percentage": 46.77, "elapsed_time": "8:51:51", "remaining_time": "10:05:21"}
	{"current_steps": 560, "total_steps": 1176, "loss": 0.3591, "lr": 3.1458524542195932e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "9:01:35", "remaining_time": "9:55:45"}
	{"current_steps": 570, "total_steps": 1176, "loss": 0.3904, "lr": 3.073864023639197e-06, "epoch": 1.4540816326530612, "percentage": 48.47, "elapsed_time": "9:10:53", "remaining_time": "9:45:40"}
	{"current_steps": 580, "total_steps": 1176, "loss": 0.3729, "lr": 3.0013696455073504e-06, "epoch": 1.4795918367346939, "percentage": 49.32, "elapsed_time": "9:20:28", "remaining_time": "9:35:56"}
	{"current_steps": 590, "total_steps": 1176, "loss": 0.3748, "lr": 2.9284332345348554e-06, "epoch": 1.5051020408163265, "percentage": 50.17, "elapsed_time": "9:30:07", "remaining_time": "9:26:15"}
	{"current_steps": 600, "total_steps": 1176, "loss": 0.3891, "lr": 2.8551190951510225e-06, "epoch": 1.5306122448979593, "percentage": 51.02, "elapsed_time": "9:39:44", "remaining_time": "9:16:33"}
	{"current_steps": 610, "total_steps": 1176, "loss": 0.3609, "lr": 2.7814918648096408e-06, "epoch": 1.556122448979592, "percentage": 51.87, "elapsed_time": "9:49:21", "remaining_time": "9:06:50"}
	{"current_steps": 620, "total_steps": 1176, "loss": 0.3775, "lr": 2.707616457001321e-06, "epoch": 1.5816326530612246, "percentage": 52.72, "elapsed_time": "9:58:59", "remaining_time": "8:57:10"}
	{"current_steps": 630, "total_steps": 1176, "loss": 0.3734, "lr": 2.633558004022484e-06, "epoch": 1.6071428571428572, "percentage": 53.57, "elapsed_time": "10:08:39", "remaining_time": "8:47:29"}
	{"current_steps": 640, "total_steps": 1176, "loss": 0.3649, "lr": 2.559381799551433e-06, "epoch": 1.6326530612244898, "percentage": 54.42, "elapsed_time": "10:17:53", "remaining_time": "8:37:29"}
	{"current_steps": 650, "total_steps": 1176, "loss": 0.363, "lr": 2.4851532410821415e-06, "epoch": 1.6581632653061225, "percentage": 55.27, "elapsed_time": "10:27:28", "remaining_time": "8:27:46"}
	{"current_steps": 660, "total_steps": 1176, "loss": 0.3683, "lr": 2.4109377722665175e-06, "epoch": 1.683673469387755, "percentage": 56.12, "elapsed_time": "10:37:09", "remaining_time": "8:18:08"}
	{"current_steps": 670, "total_steps": 1176, "loss": 0.3733, "lr": 2.3368008252159673e-06, "epoch": 1.7091836734693877, "percentage": 56.97, "elapsed_time": "10:46:44", "remaining_time": "8:08:25"}
	{"current_steps": 680, "total_steps": 1176, "loss": 0.3604, "lr": 2.262807762813137e-06, "epoch": 1.7346938775510203, "percentage": 57.82, "elapsed_time": "10:56:36", "remaining_time": "7:58:56"}
	{"current_steps": 690, "total_steps": 1176, "loss": 0.3624, "lr": 2.189023821084689e-06, "epoch": 1.760204081632653, "percentage": 58.67, "elapsed_time": "11:06:11", "remaining_time": "7:49:13"}
	{"current_steps": 700, "total_steps": 1176, "loss": 0.3632, "lr": 2.1155140516859228e-06, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "11:15:52", "remaining_time": "7:39:36"}
	{"current_steps": 710, "total_steps": 1176, "loss": 0.3718, "lr": 2.042343264547941e-06, "epoch": 1.8112244897959182, "percentage": 60.37, "elapsed_time": "11:25:37", "remaining_time": "7:30:00"}
	{"current_steps": 720, "total_steps": 1176, "loss": 0.3683, "lr": 1.9695759707379406e-06, "epoch": 1.836734693877551, "percentage": 61.22, "elapsed_time": "11:35:24", "remaining_time": "7:20:25"}
	{"current_steps": 730, "total_steps": 1176, "loss": 0.381, "lr": 1.8972763255829876e-06, "epoch": 1.8622448979591837, "percentage": 62.07, "elapsed_time": "11:45:17", "remaining_time": "7:10:54"}
	{"current_steps": 740, "total_steps": 1176, "loss": 0.3782, "lr": 1.8255080721074391e-06, "epoch": 1.8877551020408163, "percentage": 62.93, "elapsed_time": "11:54:51", "remaining_time": "7:01:11"}
	{"current_steps": 750, "total_steps": 1176, "loss": 0.3574, "lr": 1.7543344848338705e-06, "epoch": 1.913265306122449, "percentage": 63.78, "elapsed_time": "12:03:55", "remaining_time": "6:51:11"}
	{"current_steps": 760, "total_steps": 1176, "loss": 0.3731, "lr": 1.6838183139970494e-06, "epoch": 1.9387755102040818, "percentage": 64.63, "elapsed_time": "12:13:28", "remaining_time": "6:41:28"}
	{"current_steps": 770, "total_steps": 1176, "loss": 0.3604, "lr": 1.614021730220161e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "12:23:10", "remaining_time": "6:31:51"}
	{"current_steps": 780, "total_steps": 1176, "loss": 0.3762, "lr": 1.5450062697020362e-06, "epoch": 1.989795918367347, "percentage": 66.33, "elapsed_time": "12:32:49", "remaining_time": "6:22:12"}
	{"current_steps": 790, "total_steps": 1176, "loss": 0.3237, "lr": 1.4768327799637314e-06, "epoch": 2.0153061224489797, "percentage": 67.18, "elapsed_time": "12:45:21", "remaining_time": "6:13:57"}
	{"current_steps": 800, "total_steps": 1176, "loss": 0.2731, "lr": 1.4095613662022722e-06, "epoch": 2.0408163265306123, "percentage": 68.03, "elapsed_time": "12:55:06", "remaining_time": "6:04:18"}
	{"current_steps": 810, "total_steps": 1176, "loss": 0.2794, "lr": 1.3432513382988726e-06, "epoch": 2.066326530612245, "percentage": 68.88, "elapsed_time": "13:04:42", "remaining_time": "5:54:34"}
	{"current_steps": 820, "total_steps": 1176, "loss": 0.2642, "lr": 1.2779611585283442e-06, "epoch": 2.0918367346938775, "percentage": 69.73, "elapsed_time": "13:14:20", "remaining_time": "5:44:51"}
	{"current_steps": 830, "total_steps": 1176, "loss": 0.2638, "lr": 1.2137483900157964e-06, "epoch": 2.11734693877551, "percentage": 70.58, "elapsed_time": "13:23:56", "remaining_time": "5:35:08"}
	{"current_steps": 840, "total_steps": 1176, "loss": 0.266, "lr": 1.1506696459860744e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "13:33:35", "remaining_time": "5:25:26"}
	{"current_steps": 850, "total_steps": 1176, "loss": 0.2623, "lr": 1.0887805398506757e-06, "epoch": 2.1683673469387754, "percentage": 72.28, "elapsed_time": "13:43:16", "remaining_time": "5:15:45"}
	{"current_steps": 860, "total_steps": 1176, "loss": 0.2768, "lr": 1.0281356361761539e-06, "epoch": 2.193877551020408, "percentage": 73.13, "elapsed_time": "13:52:47", "remaining_time": "5:06:00"}
	{"current_steps": 870, "total_steps": 1176, "loss": 0.2592, "lr": 9.687884025772364e-07, "epoch": 2.2193877551020407, "percentage": 73.98, "elapsed_time": "14:02:20", "remaining_time": "4:56:16"}
	{"current_steps": 880, "total_steps": 1176, "loss": 0.2654, "lr": 9.107911625770718e-07, "epoch": 2.2448979591836733, "percentage": 74.83, "elapsed_time": "14:11:49", "remaining_time": "4:46:31"}
	{"current_steps": 890, "total_steps": 1176, "loss": 0.2655, "lr": 8.541950494761633e-07, "epoch": 2.270408163265306, "percentage": 75.68, "elapsed_time": "14:21:34", "remaining_time": "4:36:51"}
	{"current_steps": 900, "total_steps": 1176, "loss": 0.2658, "lr": 7.99049961270666e-07, "epoch": 2.295918367346939, "percentage": 76.53, "elapsed_time": "14:31:11", "remaining_time": "4:27:10"}
	{"current_steps": 910, "total_steps": 1176, "loss": 0.2751, "lr": 7.454045166597884e-07, "epoch": 2.3214285714285716, "percentage": 77.38, "elapsed_time": "14:40:51", "remaining_time": "4:17:28"}
	{"current_steps": 920, "total_steps": 1176, "loss": 0.258, "lr": 6.933060121810886e-07, "epoch": 2.3469387755102042, "percentage": 78.23, "elapsed_time": "14:50:31", "remaining_time": "4:07:47"}
	{"current_steps": 930, "total_steps": 1176, "loss": 0.2557, "lr": 6.428003805114544e-07, "epoch": 2.372448979591837, "percentage": 79.08, "elapsed_time": "15:00:15", "remaining_time": "3:58:07"}
	{"current_steps": 940, "total_steps": 1176, "loss": 0.2713, "lr": 5.939321499705311e-07, "epoch": 2.3979591836734695, "percentage": 79.93, "elapsed_time": "15:09:41", "remaining_time": "3:48:23"}
	{"current_steps": 950, "total_steps": 1176, "loss": 0.2513, "lr": 5.467444052623034e-07, "epoch": 2.423469387755102, "percentage": 80.78, "elapsed_time": "15:19:25", "remaining_time": "3:38:43"}
	{"current_steps": 960, "total_steps": 1176, "loss": 0.2835, "lr": 5.0127874948944e-07, "epoch": 2.4489795918367347, "percentage": 81.63, "elapsed_time": "15:29:02", "remaining_time": "3:29:01"}
	{"current_steps": 970, "total_steps": 1176, "loss": 0.2544, "lr": 4.5757526747389506e-07, "epoch": 2.4744897959183674, "percentage": 82.48, "elapsed_time": "15:38:45", "remaining_time": "3:19:21"}
	{"current_steps": 980, "total_steps": 1176, "loss": 0.271, "lr": 4.156724904161008e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "15:48:28", "remaining_time": "3:09:41"}
	{"current_steps": 990, "total_steps": 1176, "loss": 0.2578, "lr": 3.7560736192391174e-07, "epoch": 2.5255102040816326, "percentage": 84.18, "elapsed_time": "15:58:02", "remaining_time": "2:59:59"}
	{"current_steps": 1000, "total_steps": 1176, "loss": 0.2596, "lr": 3.3741520544125243e-07, "epoch": 2.5510204081632653, "percentage": 85.03, "elapsed_time": "16:07:38", "remaining_time": "2:50:18"}
	{"current_steps": 1010, "total_steps": 1176, "loss": 0.2641, "lr": 3.011296931051813e-07, "epoch": 2.576530612244898, "percentage": 85.88, "elapsed_time": "16:17:17", "remaining_time": "2:40:37"}
	{"current_steps": 1020, "total_steps": 1176, "loss": 0.2624, "lr": 2.6678281605883206e-07, "epoch": 2.6020408163265305, "percentage": 86.73, "elapsed_time": "16:26:20", "remaining_time": "2:30:51"}
	{"current_steps": 1030, "total_steps": 1176, "loss": 0.2717, "lr": 2.3440485624640325e-07, "epoch": 2.627551020408163, "percentage": 87.59, "elapsed_time": "16:36:07", "remaining_time": "2:21:11"}
	{"current_steps": 1040, "total_steps": 1176, "loss": 0.2767, "lr": 2.040243597150654e-07, "epoch": 2.6530612244897958, "percentage": 88.44, "elapsed_time": "16:45:50", "remaining_time": "2:11:32"}
	{"current_steps": 1050, "total_steps": 1176, "loss": 0.2622, "lr": 1.7566811144732076e-07, "epoch": 2.678571428571429, "percentage": 89.29, "elapsed_time": "16:55:33", "remaining_time": "2:01:51"}
	{"current_steps": 1060, "total_steps": 1176, "loss": 0.2707, "lr": 1.4936111174600808e-07, "epoch": 2.704081632653061, "percentage": 90.14, "elapsed_time": "17:05:19", "remaining_time": "1:52:12"}
	{"current_steps": 1070, "total_steps": 1176, "loss": 0.264, "lr": 1.2512655419277152e-07, "epoch": 2.729591836734694, "percentage": 90.99, "elapsed_time": "17:15:02", "remaining_time": "1:42:32"}
	{"current_steps": 1080, "total_steps": 1176, "loss": 0.2663, "lr": 1.0298580519942536e-07, "epoch": 2.7551020408163263, "percentage": 91.84, "elapsed_time": "17:24:46", "remaining_time": "1:32:52"}
	{"current_steps": 1090, "total_steps": 1176, "loss": 0.255, "lr": 8.29583851702448e-08, "epoch": 2.7806122448979593, "percentage": 92.69, "elapsed_time": "17:34:15", "remaining_time": "1:23:10"}
	{"current_steps": 1100, "total_steps": 1176, "loss": 0.2662, "lr": 6.506195129179021e-08, "epoch": 2.806122448979592, "percentage": 93.54, "elapsed_time": "17:43:51", "remaining_time": "1:13:30"}
	{"current_steps": 1110, "total_steps": 1176, "loss": 0.2616, "lr": 4.931228196543847e-08, "epoch": 2.8316326530612246, "percentage": 94.39, "elapsed_time": "17:53:27", "remaining_time": "1:03:49"}
	{"current_steps": 1120, "total_steps": 1176, "loss": 0.2637, "lr": 3.572326289634415e-08, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "18:02:43", "remaining_time": "0:54:08"}
	{"current_steps": 1130, "total_steps": 1176, "loss": 0.2702, "lr": 2.4306874851103834e-08, "epoch": 2.88265306122449, "percentage": 96.09, "elapsed_time": "18:12:26", "remaining_time": "0:44:28"}
	{"current_steps": 1140, "total_steps": 1176, "loss": 0.2748, "lr": 1.5073183094901632e-08, "epoch": 2.9081632653061225, "percentage": 96.94, "elapsed_time": "18:22:08", "remaining_time": "0:34:48"}
	{"current_steps": 1150, "total_steps": 1176, "loss": 0.279, "lr": 8.03032851746488e-09, "epoch": 2.933673469387755, "percentage": 97.79, "elapsed_time": "18:31:45", "remaining_time": "0:25:08"}
	{"current_steps": 1160, "total_steps": 1176, "loss": 0.2869, "lr": 3.184520455642992e-09, "epoch": 2.9591836734693877, "percentage": 98.64, "elapsed_time": "18:41:21", "remaining_time": "0:15:28"}
	{"current_steps": 1170, "total_steps": 1176, "loss": 0.2537, "lr": 5.400312189426937e-10, "epoch": 2.9846938775510203, "percentage": 99.49, "elapsed_time": "18:51:06", "remaining_time": "0:05:48"}
	{"current_steps": 1176, "total_steps": 1176, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "18:58:04", "remaining_time": "0:00:00"}