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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay")
model = AutoModelForCausalLM.from_pretrained("Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay", 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 Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay

SGLang

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

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

Oberhaus commited on Jun 25, 2025

Commit

25068c1

verified ·

1 Parent(s): f703fdc

End of training

Browse files

Files changed (4) hide show

all_results.json +5 -5
model.safetensors +1 -1
train_results.json +5 -5
trainer_state.json +103 -103

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.028352425899356604,
-    "train_runtime": 545.2417,
-    "train_samples": 56,
-    "train_samples_per_second": 0.073,
-    "train_steps_per_second": 0.018
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.0025116026401519774,
+    "train_runtime": 799.9489,
+    "train_samples": 2,
+    "train_samples_per_second": 0.05,
+    "train_steps_per_second": 0.013
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5156f8ccde4ea8ade1b56ba7ed0da5b87f5834c07e92ae9de58cfc9e9c06254d
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:9a3158ccaf4cbb037a69a564fb85739b375d4a19acc624a9a1c79f01fe6f025a
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.028352425899356604,
-    "train_runtime": 545.2417,
-    "train_samples": 56,
-    "train_samples_per_second": 0.073,
-    "train_steps_per_second": 0.018
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.0025116026401519774,
+    "train_runtime": 799.9489,
+    "train_samples": 2,
+    "train_samples_per_second": 0.05,
+    "train_steps_per_second": 0.013
 }

trainer_state.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35714285714285715,
   "eval_steps": 500,
   "global_step": 10,
   "is_hyper_param_search": false,
@@ -15,22 +15,22 @@
       "clip_ratio/low_mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
-      "completions/clipped_ratio": 0.125,
-      "completions/max_length": 132.0,
-      "completions/max_terminated_length": 9.0,
-      "completions/mean_length": 36.875,
-      "completions/mean_terminated_length": 5.833333253860474,
-      "completions/min_length": 3.0,
-      "completions/min_terminated_length": 3.0,
-      "epoch": 0.07142857142857142,
-      "frac_reward_zero_std": 0.25,
-      "grad_norm": 232.2954559326172,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": 0.2416,
-      "num_tokens": 1319.0,
-      "reward": 0.010858007706701756,
-      "reward_std": 0.0022637367947027087,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -39,13 +39,13 @@
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.010858007706701756,
-      "rewards/question_recreation_reward_func/std": 0.006170675391331315,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.0,
       "rewards/xmlcount_reward_func/std": 0.0,
       "step": 2
     },
@@ -56,37 +56,37 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 53.5,
-      "completions/max_terminated_length": 53.5,
-      "completions/mean_length": 27.75,
-      "completions/mean_terminated_length": 27.75,
-      "completions/min_length": 2.0,
-      "completions/min_terminated_length": 2.0,
-      "epoch": 0.14285714285714285,
-      "frac_reward_zero_std": 0.75,
-      "grad_norm": 10.14072322845459,
-      "kl": 0.024721616529859602,
       "learning_rate": 4.415111107797445e-07,
-      "loss": -0.0008,
-      "num_tokens": 2565.0,
-      "reward": 0.5038116172654554,
-      "reward_std": 0.0010011033155024052,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
-      "rewards/consensus_reward_func/mean": 0.5,
-      "rewards/consensus_reward_func/std": 0.5773502588272095,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.003811617265455425,
-      "rewards/question_recreation_reward_func/std": 0.00466481177136302,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.0,
-      "rewards/xmlcount_reward_func/std": 0.0,
       "step": 4
     },
     {
@@ -96,21 +96,21 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 6.5,
-      "completions/max_terminated_length": 6.5,
-      "completions/mean_length": 4.625,
-      "completions/mean_terminated_length": 4.625,
-      "completions/min_length": 4.0,
-      "completions/min_terminated_length": 4.0,
-      "epoch": 0.21428571428571427,
-      "frac_reward_zero_std": 0.75,
-      "grad_norm": 107.62983703613281,
-      "kl": 0.3900044709444046,
       "learning_rate": 2.934120444167326e-07,
-      "loss": -0.0674,
-      "num_tokens": 3626.0,
-      "reward": 0.020857041236013174,
-      "reward_std": 0.008684505708515644,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -119,13 +119,13 @@
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.020857041236013174,
-      "rewards/question_recreation_reward_func/std": 0.012281744740903378,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.0,
       "rewards/xmlcount_reward_func/std": 0.0,
       "step": 6
     },
@@ -136,37 +136,37 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 13.0,
-      "completions/max_terminated_length": 13.0,
-      "completions/mean_length": 6.375,
-      "completions/mean_terminated_length": 6.375,
-      "completions/min_length": 3.0,
-      "completions/min_terminated_length": 3.0,
-      "epoch": 0.2857142857142857,
       "frac_reward_zero_std": 0.25,
-      "grad_norm": 263.4653015136719,
-      "kl": 0.24183760397136211,
       "learning_rate": 1.2500000000000005e-07,
-      "loss": -0.0388,
-      "num_tokens": 4701.0,
-      "reward": 2.9058620259165764,
-      "reward_std": 3.8985570166260004,
-      "rewards/concensus_correctness_reward_func/mean": 2.5,
-      "rewards/concensus_correctness_reward_func/std": 5.0,
-      "rewards/consensus_reward_func/mean": 0.25,
-      "rewards/consensus_reward_func/std": 0.5,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.15586218982934952,
-      "rewards/question_recreation_reward_func/std": 0.1081569567322731,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.0,
-      "rewards/xmlcount_reward_func/std": 0.0,
       "step": 8
     },
     {
@@ -176,53 +176,53 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 9.0,
-      "completions/max_terminated_length": 9.0,
-      "completions/mean_length": 7.0,
-      "completions/mean_terminated_length": 7.0,
-      "completions/min_length": 5.0,
-      "completions/min_terminated_length": 5.0,
-      "epoch": 0.35714285714285715,
       "frac_reward_zero_std": 0.25,
-      "grad_norm": 73.97364807128906,
-      "kl": 0.039292252622544765,
       "learning_rate": 1.507684480352292e-08,
-      "loss": 0.0072,
-      "num_tokens": 5781.0,
-      "reward": 5.586721681058407,
-      "reward_std": 0.011698897695168853,
-      "rewards/concensus_correctness_reward_func/mean": 5.0,
-      "rewards/concensus_correctness_reward_func/std": 5.773502826690674,
-      "rewards/consensus_reward_func/mean": 0.5,
-      "rewards/consensus_reward_func/std": 0.5773502588272095,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.08672151062637568,
-      "rewards/question_recreation_reward_func/std": 0.014588925987482071,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.0,
       "rewards/xmlcount_reward_func/std": 0.0,
       "step": 10
     },
     {
-      "epoch": 0.35714285714285715,
       "step": 10,
       "total_flos": 0.0,
-      "train_loss": 0.028352425899356604,
-      "train_runtime": 545.2417,
-      "train_samples_per_second": 0.073,
-      "train_steps_per_second": 0.018
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
-  "num_input_tokens_seen": 5781,
-  "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 10.0,
   "eval_steps": 500,
   "global_step": 10,
   "is_hyper_param_search": false,
       "clip_ratio/low_mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 69.0,
+      "completions/max_terminated_length": 69.0,
+      "completions/mean_length": 64.875,
+      "completions/mean_terminated_length": 64.875,
+      "completions/min_length": 62.0,
+      "completions/min_terminated_length": 62.0,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 6.228816032409668,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": 0.0046,
+      "num_tokens": 1543.0,
+      "reward": 0.6934062242507935,
+      "reward_std": 0.06088415801059455,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
+      "rewards/question_recreation_reward_func/mean": 0.199406236410141,
+      "rewards/question_recreation_reward_func/std": 0.20537260174751282,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.49399998784065247,
       "rewards/xmlcount_reward_func/std": 0.0,
       "step": 2
     },
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 95.0,
+      "completions/max_terminated_length": 95.0,
+      "completions/mean_length": 71.0,
+      "completions/mean_terminated_length": 71.0,
+      "completions/min_length": 62.0,
+      "completions/min_terminated_length": 62.0,
+      "epoch": 4.0,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 14.296950340270996,
+      "kl": 0.008060061466267143,
       "learning_rate": 4.415111107797445e-07,
+      "loss": 0.0558,
+      "num_tokens": 3135.0,
+      "reward": 0.6558665037155151,
+      "reward_std": 0.09568738762754947,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
+      "rewards/consensus_reward_func/mean": 0.0,
+      "rewards/consensus_reward_func/std": 0.0,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
+      "rewards/question_recreation_reward_func/mean": 0.22361651808023453,
+      "rewards/question_recreation_reward_func/std": 0.20930995047092438,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.4322499930858612,
+      "rewards/xmlcount_reward_func/std": 0.12349999696016312,
       "step": 4
     },
     {
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 65.5,
+      "completions/max_terminated_length": 65.5,
+      "completions/mean_length": 63.25,
+      "completions/mean_terminated_length": 63.25,
+      "completions/min_length": 61.0,
+      "completions/min_terminated_length": 61.0,
+      "epoch": 6.0,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 7.470577716827393,
+      "kl": 0.021054526325315237,
       "learning_rate": 2.934120444167326e-07,
+      "loss": -0.0026,
+      "num_tokens": 4665.0,
+      "reward": 0.7195066809654236,
+      "reward_std": 0.007645343546755612,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
+      "rewards/question_recreation_reward_func/mean": 0.22550669312477112,
+      "rewards/question_recreation_reward_func/std": 0.20679625123739243,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.49399998784065247,
       "rewards/xmlcount_reward_func/std": 0.0,
       "step": 6
     },
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 64.5,
+      "completions/max_terminated_length": 64.5,
+      "completions/mean_length": 59.75,
+      "completions/mean_terminated_length": 59.75,
+      "completions/min_length": 49.0,
+      "completions/min_terminated_length": 49.0,
+      "epoch": 8.0,
       "frac_reward_zero_std": 0.25,
+      "grad_norm": 12.293351173400879,
+      "kl": 0.05089123750803992,
       "learning_rate": 1.2500000000000005e-07,
+      "loss": -0.0458,
+      "num_tokens": 6167.0,
+      "reward": 0.6569569408893585,
+      "reward_std": 0.09472145570907742,
+      "rewards/concensus_correctness_reward_func/mean": 0.0,
+      "rewards/concensus_correctness_reward_func/std": 0.0,
+      "rewards/consensus_reward_func/mean": 0.0,
+      "rewards/consensus_reward_func/std": 0.0,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
+      "rewards/question_recreation_reward_func/mean": 0.22470694035291672,
+      "rewards/question_recreation_reward_func/std": 0.20819812268018723,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.4322499930858612,
+      "rewards/xmlcount_reward_func/std": 0.12349999696016312,
       "step": 8
     },
     {
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 65.5,
+      "completions/max_terminated_length": 65.5,
+      "completions/mean_length": 63.0,
+      "completions/mean_terminated_length": 63.0,
+      "completions/min_length": 61.0,
+      "completions/min_terminated_length": 61.0,
+      "epoch": 10.0,
       "frac_reward_zero_std": 0.25,
+      "grad_norm": 14.979830741882324,
+      "kl": 0.10098545905202627,
       "learning_rate": 1.507684480352292e-08,
+      "loss": 0.0006,
+      "num_tokens": 7695.0,
+      "reward": 0.7237494587898254,
+      "reward_std": 0.002912905707489699,
+      "rewards/concensus_correctness_reward_func/mean": 0.0,
+      "rewards/concensus_correctness_reward_func/std": 0.0,
+      "rewards/consensus_reward_func/mean": 0.0,
+      "rewards/consensus_reward_func/std": 0.0,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
+      "rewards/question_recreation_reward_func/mean": 0.22974946349859238,
+      "rewards/question_recreation_reward_func/std": 0.2142425775527954,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.49399998784065247,
       "rewards/xmlcount_reward_func/std": 0.0,
       "step": 10
     },
     {
+      "epoch": 10.0,
       "step": 10,
       "total_flos": 0.0,
+      "train_loss": 0.0025116026401519774,
+      "train_runtime": 799.9489,
+      "train_samples_per_second": 0.05,
+      "train_steps_per_second": 0.013
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
+  "num_input_tokens_seen": 7695,
+  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {