Instructions to use elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan with Transformers:

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

pipe = pipeline("text-generation", model="elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan")
model = AutoModelForMultimodalLM.from_pretrained("elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan

SGLang

How to use elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan 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 "elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan" \
    --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": "elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan",
		"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 "elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan" \
        --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": "elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan",
    max_seq_length=2048,
)

Docker Model Runner
How to use elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan with Docker Model Runner:
```
docker model run hf.co/elsvastika/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_wary_orangutan
```

elsvastika commited on Jun 25, 2025

Commit

652faf1

verified ·

1 Parent(s): dc66667

End of training

Browse files

Files changed (4) hide show

adapter_model.safetensors +1 -1
all_results.json +4 -4
train_results.json +4 -4
trainer_state.json +162 -162

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac147abf08f0c58d3d4a440c1e183645baf6775d3d8135bcf4b2be6d1d7afd5
 size 35237104

 version https://git-lfs.github.com/spec/v1
+oid sha256:a43e31a0353c6a26011bf956975e628e90fd893c3a429e5782503121755a3159
 size 35237104

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 8.595042357531687e-05,
-    "train_runtime": 399.0994,
     "train_samples": 24,
-    "train_samples_per_second": 1.203,
-    "train_steps_per_second": 0.075
 }

 {
     "total_flos": 0.0,
+    "train_loss": 7.583472033729776e-05,
+    "train_runtime": 406.4207,
     "train_samples": 24,
+    "train_samples_per_second": 1.181,
+    "train_steps_per_second": 0.074
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 8.595042357531687e-05,
-    "train_runtime": 399.0994,
     "train_samples": 24,
-    "train_samples_per_second": 1.203,
-    "train_steps_per_second": 0.075
 }

 {
     "total_flos": 0.0,
+    "train_loss": 7.583472033729776e-05,
+    "train_runtime": 406.4207,
     "train_samples": 24,
+    "train_samples_per_second": 1.181,
+    "train_steps_per_second": 0.074
 }

trainer_state.json CHANGED Viewed

@@ -9,298 +9,298 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 278.59375,
       "epoch": 0.3333333333333333,
-      "grad_norm": 4.248319625854492,
-      "kl": 0.062184418085962534,
       "learning_rate": 4.985344892885899e-07,
       "loss": 0.0001,
-      "reward": 1.2006410881876945,
-      "reward_std": 0.7796880286186934,
-      "rewards/concensus_correctness_reward_func": 0.05999999865889549,
-      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.43642234429717064,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.4542187452316284,
       "step": 2
     },
     {
-      "completion_length": 333.75,
       "epoch": 0.6666666666666666,
-      "grad_norm": 1.6703503131866455,
-      "kl": 0.08404640504159033,
       "learning_rate": 4.869132927957006e-07,
       "loss": 0.0001,
-      "reward": 1.2025500014424324,
-      "reward_std": 1.4545036181807518,
-      "rewards/concensus_correctness_reward_func": 0.17999999970197678,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.3974562222138047,
-      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3594687506556511,
       "step": 4
     },
     {
-      "completion_length": 313.1875,
       "epoch": 1.0,
-      "grad_norm": 1.9751163721084595,
-      "kl": 0.06685617857147008,
       "learning_rate": 4.642142940418973e-07,
       "loss": 0.0001,
-      "reward": 1.5069561153650284,
-      "reward_std": 1.225994199514389,
-      "rewards/concensus_correctness_reward_func": 0.17675000056624413,
       "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.5378936156630516,
-      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5423124926164746,
       "step": 6
     },
     {
-      "completion_length": 273.28125,
       "epoch": 1.3333333333333333,
-      "grad_norm": 2.66338849067688,
-      "kl": 0.07679323526099324,
       "learning_rate": 4.314988729807827e-07,
       "loss": 0.0001,
-      "reward": 1.2865665704011917,
-      "reward_std": 0.9947356805205345,
-      "rewards/concensus_correctness_reward_func": 0.08837499842047691,
-      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.38912907242774963,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.6215625032782555,
       "step": 8
     },
     {
-      "completion_length": 346.5625,
       "epoch": 1.6666666666666665,
-      "grad_norm": 2.080303192138672,
-      "kl": 0.09345827554352582,
       "learning_rate": 3.902967663405956e-07,
       "loss": 0.0001,
-      "reward": 0.9881881810724735,
-      "reward_std": 0.808600801974535,
-      "rewards/concensus_correctness_reward_func": 0.05999999865889549,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.45118817314505577,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.41449999436736107,
       "step": 10
     },
     {
-      "completion_length": 260.15625,
       "epoch": 2.0,
-      "grad_norm": 2.335561990737915,
-      "kl": 0.11228820122778416,
       "learning_rate": 3.4253453883497864e-07,
       "loss": 0.0001,
-      "reward": 1.4716908484697342,
-      "reward_std": 0.9072064962238073,
-      "rewards/concensus_correctness_reward_func": 0.05925000086426735,
-      "rewards/consensus_reward_func": 0.3125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.5689721070230007,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.46846875874325633,
       "step": 12
     },
     {
-      "completion_length": 275.40625,
       "epoch": 2.3333333333333335,
-      "grad_norm": 2.283569812774658,
-      "kl": 0.0807511885650456,
       "learning_rate": 2.9044549913819124e-07,
       "loss": 0.0001,
-      "reward": 1.4714765325188637,
-      "reward_std": 1.2690498754382133,
-      "rewards/concensus_correctness_reward_func": 0.22462500259280205,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.444101526401937,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5527500081807375,
       "step": 14
     },
     {
-      "completion_length": 260.40625,
       "epoch": 2.6666666666666665,
-      "grad_norm": 2.5871284008026123,
-      "kl": 0.10271162493154407,
       "learning_rate": 2.3646527285364563e-07,
       "loss": 0.0001,
-      "reward": 1.3442683182656765,
-      "reward_std": 0.9297836944460869,
-      "rewards/concensus_correctness_reward_func": 0.12006250023841858,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.42564334720373154,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5485624969005585,
       "step": 16
     },
     {
-      "completion_length": 318.0,
       "epoch": 3.0,
-      "grad_norm": 1.7845288515090942,
-      "kl": 0.0853050671867095,
       "learning_rate": 1.8311791536769483e-07,
-      "loss": 0.0001,
-      "reward": 1.3152423985302448,
-      "reward_std": 0.9182680658996105,
-      "rewards/concensus_correctness_reward_func": 0.0572500005364418,
       "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.40921113081276417,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5987812504172325,
       "step": 18
     },
     {
-      "completion_length": 315.25,
       "epoch": 3.3333333333333335,
-      "grad_norm": 2.773048162460327,
-      "kl": 0.09285748400725424,
       "learning_rate": 1.328978898250525e-07,
       "loss": 0.0001,
-      "reward": 1.4348187409341335,
-      "reward_std": 1.0947183221578598,
-      "rewards/concensus_correctness_reward_func": 0.17412499710917473,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.34678749134764075,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.6014062613248825,
       "step": 20
     },
     {
-      "completion_length": 368.03125,
       "epoch": 3.6666666666666665,
-      "grad_norm": 2.1002964973449707,
-      "kl": 0.07862667454173788,
       "learning_rate": 8.81534288045431e-08,
       "loss": 0.0001,
-      "reward": 1.1409763768315315,
-      "reward_std": 1.543092556297779,
-      "rewards/concensus_correctness_reward_func": 0.1486249975860119,
       "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.4632575991563499,
-      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.15409374702721834,
       "step": 22
     },
     {
-      "completion_length": 300.75,
       "epoch": 4.0,
-      "grad_norm": 2.0321006774902344,
-      "kl": 0.06688157061580569,
       "learning_rate": 5.097673357358906e-08,
       "loss": 0.0001,
-      "reward": 1.4997591599822044,
-      "reward_std": 0.9334132596850395,
-      "rewards/concensus_correctness_reward_func": 0.11949999630451202,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.5131966844201088,
-      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.6170624904334545,
       "step": 24
     },
     {
-      "completion_length": 332.21875,
       "epoch": 4.333333333333333,
-      "grad_norm": 3.189197063446045,
-      "kl": 0.09957290720194578,
       "learning_rate": 2.3106145082260774e-08,
-      "loss": 0.0001,
-      "reward": 1.3270634859800339,
-      "reward_std": 0.8615294434130192,
-      "rewards/concensus_correctness_reward_func": 0.0886249989271164,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.4339072136208415,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.663906242698431,
       "step": 26
     },
     {
-      "completion_length": 302.71875,
       "epoch": 4.666666666666667,
-      "grad_norm": 1.7814644575119019,
-      "kl": 0.09857317211572081,
       "learning_rate": 5.844861072478335e-09,
       "loss": 0.0001,
-      "reward": 1.804719053208828,
-      "reward_std": 1.6982894986867905,
-      "rewards/concensus_correctness_reward_func": 0.32387499511241913,
-      "rewards/consensus_reward_func": 0.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.4871565429493785,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5561874881386757,
       "step": 28
     },
     {
-      "completion_length": 294.5625,
       "epoch": 5.0,
-      "grad_norm": 2.199143171310425,
-      "kl": 0.08833435061387718,
       "learning_rate": 0.0,
-      "loss": 0.0001,
-      "reward": 1.6715077757835388,
-      "reward_std": 1.1938673481345177,
-      "rewards/concensus_correctness_reward_func": 0.17875000089406967,
-      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.5682889893651009,
-      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.6588437482714653,
       "step": 30
     },
     {
       "epoch": 5.0,
       "step": 30,
       "total_flos": 0.0,
-      "train_loss": 8.595042357531687e-05,
-      "train_runtime": 399.0994,
-      "train_samples_per_second": 1.203,
-      "train_steps_per_second": 0.075
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 281.53125,
       "epoch": 0.3333333333333333,
+      "grad_norm": 2.773542642593384,
+      "kl": 0.0580324565526098,
       "learning_rate": 4.985344892885899e-07,
       "loss": 0.0001,
+      "reward": 2.4544273018836975,
+      "reward_std": 2.3720036819577217,
+      "rewards/concensus_correctness_reward_func": 0.8223749995231628,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.4375,
+      "rewards/question_recreation_reward_func": 0.5142397312447429,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5553124938160181,
       "step": 2
     },
     {
+      "completion_length": 271.28125,
       "epoch": 0.6666666666666666,
+      "grad_norm": 2.0007011890411377,
+      "kl": 0.07696286379359663,
       "learning_rate": 4.869132927957006e-07,
       "loss": 0.0001,
+      "reward": 1.217789612710476,
+      "reward_std": 1.0034673381596804,
+      "rewards/concensus_correctness_reward_func": 0.0598750002682209,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.36272712517529726,
+      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6076875105500221,
       "step": 4
     },
     {
+      "completion_length": 303.25,
       "epoch": 1.0,
+      "grad_norm": 6.666475772857666,
+      "kl": 0.0992446473101154,
       "learning_rate": 4.642142940418973e-07,
       "loss": 0.0001,
+      "reward": 1.2962229549884796,
+      "reward_std": 1.3163017462939024,
+      "rewards/concensus_correctness_reward_func": 0.10431249998509884,
       "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.42141042836010456,
+      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.3798749968409538,
       "step": 6
     },
     {
+      "completion_length": 256.21875,
       "epoch": 1.3333333333333333,
+      "grad_norm": 2.719036340713501,
+      "kl": 0.08407116535818204,
       "learning_rate": 4.314988729807827e-07,
       "loss": 0.0001,
+      "reward": 1.9946057051420212,
+      "reward_std": 1.059820756316185,
+      "rewards/concensus_correctness_reward_func": 0.3334375023841858,
+      "rewards/consensus_reward_func": 0.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.4136994816362858,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.684968750923872,
       "step": 8
     },
     {
+      "completion_length": 321.0,
       "epoch": 1.6666666666666665,
+      "grad_norm": 2.027712821960449,
+      "kl": 0.10444008558988571,
       "learning_rate": 3.902967663405956e-07,
       "loss": 0.0001,
+      "reward": 2.8985730558633804,
+      "reward_std": 2.1391075775027275,
+      "rewards/concensus_correctness_reward_func": 0.9828124903142452,
+      "rewards/consensus_reward_func": 0.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.6192605346441269,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6715000197291374,
       "step": 10
     },
     {
+      "completion_length": 289.78125,
       "epoch": 2.0,
+      "grad_norm": 3.4199697971343994,
+      "kl": 0.06481281516607851,
       "learning_rate": 3.4253453883497864e-07,
       "loss": 0.0001,
+      "reward": 2.0985126718878746,
+      "reward_std": 1.588769018650055,
+      "rewards/concensus_correctness_reward_func": 0.3907500021159649,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.5,
+      "rewards/question_recreation_reward_func": 0.5003876239061356,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6448750030249357,
       "step": 12
     },
     {
+      "completion_length": 322.65625,
       "epoch": 2.3333333333333335,
+      "grad_norm": 1.4510133266448975,
+      "kl": 0.09526054270099849,
       "learning_rate": 2.9044549913819124e-07,
       "loss": 0.0001,
+      "reward": 1.6081246063113213,
+      "reward_std": 1.3514070957899094,
+      "rewards/concensus_correctness_reward_func": 0.26324999891221523,
+      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.3845308255404234,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5228437595069408,
       "step": 14
     },
     {
+      "completion_length": 300.875,
       "epoch": 2.6666666666666665,
+      "grad_norm": 32.19089126586914,
+      "kl": 0.08323089242912829,
       "learning_rate": 2.3646527285364563e-07,
       "loss": 0.0001,
+      "reward": 2.5157083868980408,
+      "reward_std": 3.12582578510046,
+      "rewards/concensus_correctness_reward_func": 1.4086875282227993,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.39945833198726177,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.45756249502301216,
       "step": 16
     },
     {
+      "completion_length": 367.65625,
       "epoch": 3.0,
+      "grad_norm": 2.201923131942749,
+      "kl": 0.040471521380823106,
       "learning_rate": 1.8311791536769483e-07,
+      "loss": 0.0,
+      "reward": 1.7202124670147896,
+      "reward_std": 1.1163596734404564,
+      "rewards/concensus_correctness_reward_func": 0.15918750315904617,
       "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.4375,
+      "rewards/question_recreation_reward_func": 0.5503374617546797,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.43256248952820897,
       "step": 18
     },
     {
+      "completion_length": 298.71875,
       "epoch": 3.3333333333333335,
+      "grad_norm": 5.080014705657959,
+      "kl": 0.1327864183112979,
       "learning_rate": 1.328978898250525e-07,
       "loss": 0.0001,
+      "reward": 2.0473050475120544,
+      "reward_std": 1.830180624499917,
+      "rewards/concensus_correctness_reward_func": 0.684749998152256,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.38293003430590034,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.7296250090003014,
       "step": 20
     },
     {
+      "completion_length": 321.9375,
       "epoch": 3.6666666666666665,
+      "grad_norm": 1.9241300821304321,
+      "kl": 0.07197530311532319,
       "learning_rate": 8.81534288045431e-08,
       "loss": 0.0001,
+      "reward": 1.3912755213677883,
+      "reward_std": 0.9820459727197886,
+      "rewards/concensus_correctness_reward_func": 0.10918749868869781,
       "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.4397130124270916,
+      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5142499897629023,
       "step": 22
     },
     {
+      "completion_length": 347.75,
       "epoch": 4.0,
+      "grad_norm": 2.118330240249634,
+      "kl": 0.051218974171206355,
       "learning_rate": 5.097673357358906e-08,
       "loss": 0.0001,
+      "reward": 2.470015749335289,
+      "reward_std": 3.3017385974526405,
+      "rewards/concensus_correctness_reward_func": 0.9248749949038029,
+      "rewards/consensus_reward_func": 0.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.5278282500803471,
+      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.251687491312623,
       "step": 24
     },
     {
+      "completion_length": 399.5625,
       "epoch": 4.333333333333333,
+      "grad_norm": 1.9072325229644775,
+      "kl": 0.042736936593428254,
       "learning_rate": 2.3106145082260774e-08,
+      "loss": 0.0,
+      "reward": 2.27708288282156,
+      "reward_std": 2.7430423460900784,
+      "rewards/concensus_correctness_reward_func": 0.8621874898672104,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.5607079211622477,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2291874964721501,
       "step": 26
     },
     {
+      "completion_length": 354.09375,
       "epoch": 4.666666666666667,
+      "grad_norm": 2.1720738410949707,
+      "kl": 0.08552559395320714,
       "learning_rate": 5.844861072478335e-09,
       "loss": 0.0001,
+      "reward": 1.2497381269931793,
+      "reward_std": 1.0915438868105412,
+      "rewards/concensus_correctness_reward_func": 0.14025000110268593,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.44089438393712044,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.5279687470756471,
       "step": 28
     },
     {
+      "completion_length": 294.125,
       "epoch": 5.0,
+      "grad_norm": 1.8672877550125122,
+      "kl": 0.04691072192508727,
       "learning_rate": 0.0,
+      "loss": 0.0,
+      "reward": 1.9176766276359558,
+      "reward_std": 1.8577748499810696,
+      "rewards/concensus_correctness_reward_func": 0.338749997317791,
+      "rewards/consensus_reward_func": 0.3125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.5273328814655542,
+      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5515937563031912,
       "step": 30
     },
     {
       "epoch": 5.0,
       "step": 30,
       "total_flos": 0.0,
+      "train_loss": 7.583472033729776e-05,
+      "train_runtime": 406.4207,
+      "train_samples_per_second": 1.181,
+      "train_steps_per_second": 0.074
     }
   ],
   "logging_steps": 2,