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 20, 2025

Commit

fd7b7b0

verified ·

1 Parent(s): aeef55a

End of training

Browse files

Files changed (6) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
all_results.json +5 -5
train_results.json +5 -5
trainer_state.json +178 -368
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
-    "down_proj",
     "o_proj",
     "q_proj",
-    "v_proj",
-    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "o_proj",
     "q_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead40382b37ef28866c5216b320811ecf7182ed340ceccf63d8e53db5fc12a0d
 size 35237104

 version https://git-lfs.github.com/spec/v1
+oid sha256:c946f7d79d87a58ad003239290ea9ef4833a06139b16c006a7e622a4004f1aa4
 size 35237104

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.602725280667073e-06,
-    "train_runtime": 1884.3714,
-    "train_samples": 36,
-    "train_samples_per_second": 0.425,
-    "train_steps_per_second": 0.027
 }

 {
     "total_flos": 0.0,
+    "train_loss": 3.2592993572203946e-06,
+    "train_runtime": 1944.3016,
+    "train_samples": 24,
+    "train_samples_per_second": 0.247,
+    "train_steps_per_second": 0.015
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.602725280667073e-06,
-    "train_runtime": 1884.3714,
-    "train_samples": 36,
-    "train_samples_per_second": 0.425,
-    "train_steps_per_second": 0.027
 }

 {
     "total_flos": 0.0,
+    "train_loss": 3.2592993572203946e-06,
+    "train_runtime": 1944.3016,
+    "train_samples": 24,
+    "train_samples_per_second": 0.247,
+    "train_steps_per_second": 0.015
 }

trainer_state.json CHANGED Viewed

@@ -1,502 +1,312 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.555555555555555,
   "eval_steps": 500,
-  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 254.0,
-      "epoch": 0.2222222222222222,
-      "grad_norm": 2.455533266067505,
-      "kl": 0.0016071582067525014,
-      "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 0.8821750227361917,
-      "reward_std": 0.7979278466664255,
-      "rewards/concensus_correctness_reward_func": 0.049937501549720764,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.26773752458393574,
-      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.1895000054500997,
       "step": 2
     },
     {
-      "completion_length": 369.3125,
-      "epoch": 0.4444444444444444,
-      "grad_norm": 2.520486354827881,
-      "kl": 0.0038820735207991675,
-      "learning_rate": 4.978612153434526e-07,
       "loss": 0.0,
-      "reward": 0.3699257434345782,
-      "reward_std": 0.5709783472120762,
-      "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.19958198571112007,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.17034375481307507,
       "step": 4
     },
     {
-      "completion_length": 467.875,
-      "epoch": 0.6666666666666666,
-      "grad_norm": 1.3698705434799194,
-      "kl": 0.0013275225574034266,
-      "learning_rate": 4.91481456572267e-07,
       "loss": 0.0,
-      "reward": 0.6990349255502224,
-      "reward_std": 0.9675047248601913,
-      "rewards/concensus_correctness_reward_func": 0.046875,
-      "rewards/consensus_reward_func": 0.0625,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.33225369080901146,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.19490624405443668,
-      "step": 6
-    },
-    {
-      "completion_length": 323.34375,
-      "epoch": 0.8888888888888888,
-      "grad_norm": 2.7056479454040527,
-      "kl": 0.00173920994711807,
-      "learning_rate": 4.809698831278217e-07,
-      "loss": 0.0,
-      "reward": 0.5385207324288785,
-      "reward_std": 0.8355418732389808,
-      "rewards/concensus_correctness_reward_func": 0.02787500061094761,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.2965519982390106,
-      "rewards/soft_format_reward_func": 0.015625,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.07346874848008156,
-      "step": 8
-    },
-    {
-      "completion_length": 276.09375,
-      "epoch": 1.1111111111111112,
-      "grad_norm": 3.8186511993408203,
-      "kl": 0.0028932989152963273,
-      "learning_rate": 4.6650635094610966e-07,
-      "loss": 0.0,
-      "reward": 1.1083624437451363,
-      "reward_std": 1.7071605939418077,
-      "rewards/concensus_correctness_reward_func": 0.625,
-      "rewards/consensus_reward_func": 0.0,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.25786245451308787,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.03799999970942736,
-      "step": 10
     },
     {
-      "completion_length": 255.59375,
       "epoch": 1.3333333333333333,
-      "grad_norm": 34.07455062866211,
-      "kl": 0.0037407633935799822,
-      "learning_rate": 4.483383350728088e-07,
-      "loss": 0.0,
-      "reward": 1.2880361340939999,
-      "reward_std": 1.625240983441472,
-      "rewards/concensus_correctness_reward_func": 0.625,
-      "rewards/consensus_reward_func": 0.0625,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.32416112907230854,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.15137499663978815,
-      "step": 12
-    },
-    {
-      "completion_length": 285.21875,
-      "epoch": 1.5555555555555556,
-      "grad_norm": 3.052701234817505,
-      "kl": 0.002863182016881183,
-      "learning_rate": 4.2677669529663686e-07,
       "loss": 0.0,
-      "reward": 0.607268082909286,
-      "reward_std": 0.6088872440159321,
-      "rewards/concensus_correctness_reward_func": 0.022187499329447746,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.38814307004213333,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.19693750143051147,
-      "step": 14
     },
     {
-      "completion_length": 347.65625,
-      "epoch": 1.7777777777777777,
-      "grad_norm": 5.15467643737793,
-      "kl": 0.0014800850040046498,
-      "learning_rate": 4.0219035725218013e-07,
       "loss": 0.0,
-      "reward": 0.1809218251146376,
-      "reward_std": 0.7999278882052749,
-      "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.2310780775733292,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.112656245008111,
-      "step": 16
     },
     {
-      "completion_length": 441.25,
       "epoch": 2.0,
-      "grad_norm": 4.815533638000488,
-      "kl": 0.0013374313130043447,
-      "learning_rate": 3.75e-07,
       "loss": 0.0,
-      "reward": 0.5386425573378801,
-      "reward_std": 0.6832009451463819,
-      "rewards/concensus_correctness_reward_func": 0.046875,
-      "rewards/consensus_reward_func": 0.0625,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.23683004680788144,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.19243750348687172,
-      "step": 18
-    },
-    {
-      "completion_length": 437.25,
-      "epoch": 2.2222222222222223,
-      "grad_norm": 2.5218758583068848,
-      "kl": 0.0015388188403449021,
-      "learning_rate": 3.4567085809127245e-07,
-      "loss": 0.0,
-      "reward": 0.7281985133886337,
-      "reward_std": 0.6127606704831123,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.45726102218031883,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.2709374986588955,
-      "step": 20
     },
     {
-      "completion_length": 387.75,
-      "epoch": 2.4444444444444446,
-      "grad_norm": 1.3259650468826294,
-      "kl": 0.0036219921821611933,
-      "learning_rate": 3.147047612756302e-07,
       "loss": 0.0,
-      "reward": 0.2731318287551403,
-      "reward_std": 0.2530765999108553,
-      "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.20441308384761214,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.06871875282377005,
-      "step": 22
     },
     {
-      "completion_length": 447.09375,
       "epoch": 2.6666666666666665,
-      "grad_norm": 6.329639434814453,
-      "kl": 0.0021589112002402544,
-      "learning_rate": 2.826315480550129e-07,
       "loss": 0.0,
-      "reward": 1.2416966576129198,
-      "reward_std": 2.0539041608572006,
-      "rewards/concensus_correctness_reward_func": 0.625,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.3013216257095337,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.1278750030323863,
-      "step": 24
     },
     {
-      "completion_length": 301.875,
-      "epoch": 2.888888888888889,
-      "grad_norm": 4.056438446044922,
-      "kl": 0.0024828215537127107,
-      "learning_rate": 2.5e-07,
       "loss": 0.0,
-      "reward": 0.2829342377372086,
-      "reward_std": 0.33365900977514684,
-      "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.1184342410415411,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.16449999809265137,
-      "step": 26
-    },
-    {
-      "completion_length": 341.15625,
-      "epoch": 3.111111111111111,
-      "grad_norm": 2.550891876220703,
-      "kl": 0.002100169222103432,
-      "learning_rate": 2.1736845194498716e-07,
-      "loss": 0.0,
-      "reward": 0.3925126292742789,
-      "reward_std": 0.7323208572342992,
-      "rewards/concensus_correctness_reward_func": 0.014562499709427357,
-      "rewards/consensus_reward_func": 0.0625,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.29879387514665723,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.016656249528750777,
-      "step": 28
     },
     {
-      "completion_length": 388.03125,
       "epoch": 3.3333333333333335,
-      "grad_norm": 1.4323590993881226,
-      "kl": 0.004696541313023772,
-      "learning_rate": 1.8529523872436977e-07,
       "loss": 0.0,
-      "reward": 0.05710854474455118,
-      "reward_std": 0.5547531270422041,
-      "rewards/concensus_correctness_reward_func": 0.0078125,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.19385854969732463,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.20706249913200736,
-      "step": 30
     },
     {
-      "completion_length": 352.90625,
-      "epoch": 3.5555555555555554,
-      "grad_norm": 2.221634864807129,
-      "kl": 0.002907156704168301,
-      "learning_rate": 1.5432914190872756e-07,
       "loss": 0.0,
-      "reward": 0.3871938968077302,
-      "reward_std": 0.3934658619109541,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.2629126524552703,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.1242812555283308,
-      "step": 32
-    },
-    {
-      "completion_length": 384.375,
-      "epoch": 3.7777777777777777,
-      "grad_norm": 2.7794787883758545,
-      "kl": 0.001867200349806808,
-      "learning_rate": 1.2500000000000005e-07,
-      "loss": 0.0,
-      "reward": 0.9573859982192516,
-      "reward_std": 1.0359943909570575,
-      "rewards/concensus_correctness_reward_func": 0.11443750280886889,
-      "rewards/consensus_reward_func": 0.1875,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.3830109708942473,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.20993749890476465,
-      "step": 34
     },
     {
-      "completion_length": 361.375,
       "epoch": 4.0,
-      "grad_norm": 3.378568172454834,
-      "kl": 0.0019658175588119775,
-      "learning_rate": 9.780964274781983e-08,
-      "loss": 0.0,
-      "reward": 0.550561910495162,
-      "reward_std": 0.5597149441018701,
-      "rewards/concensus_correctness_reward_func": 0.03125,
-      "rewards/consensus_reward_func": 0.0,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.27071817917749286,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.12359375134110451,
-      "step": 36
-    },
-    {
-      "completion_length": 282.96875,
-      "epoch": 4.222222222222222,
-      "grad_norm": 4.209115505218506,
-      "kl": 0.0013284565284266137,
-      "learning_rate": 7.322330470336313e-08,
       "loss": 0.0,
-      "reward": 1.8079969780519605,
-      "reward_std": 2.005708161741495,
-      "rewards/concensus_correctness_reward_func": 1.268062500283122,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.20130947075085714,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.08862500544637442,
-      "step": 38
     },
     {
-      "completion_length": 431.4375,
-      "epoch": 4.444444444444445,
-      "grad_norm": 29.043092727661133,
-      "kl": 0.003590297739719972,
-      "learning_rate": 5.166166492719124e-08,
       "loss": 0.0,
-      "reward": 0.5267084827646613,
-      "reward_std": 0.684504278935492,
       "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.35548973828554153,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.10871875286102295,
-      "step": 40
-    },
-    {
-      "completion_length": 384.59375,
-      "epoch": 4.666666666666667,
-      "grad_norm": 29.70347785949707,
-      "kl": 0.001960429195605684,
-      "learning_rate": 3.349364905389032e-08,
-      "loss": 0.0,
-      "reward": 1.234227987471968,
-      "reward_std": 1.9329941319301724,
-      "rewards/concensus_correctness_reward_func": 0.6629374995827675,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.257196772727184,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.12659375229850411,
-      "step": 42
-    },
-    {
-      "completion_length": 364.0625,
-      "epoch": 4.888888888888889,
-      "grad_norm": 55.00151062011719,
-      "kl": 0.002629825277836062,
-      "learning_rate": 1.9030116872178314e-08,
-      "loss": 0.0,
-      "reward": 0.5272765271365643,
-      "reward_std": 0.8430194035172462,
-      "rewards/concensus_correctness_reward_func": 0.01837499998509884,
-      "rewards/consensus_reward_func": 0.0,
-      "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.31580778677016497,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.13059375621378422,
-      "step": 44
     },
     {
-      "completion_length": 304.40625,
-      "epoch": 5.111111111111111,
-      "grad_norm": 42.15534973144531,
-      "kl": 0.005508741844096221,
-      "learning_rate": 8.518543427732949e-09,
       "loss": 0.0,
-      "reward": 0.4785704296082258,
-      "reward_std": 0.8159382930025458,
-      "rewards/concensus_correctness_reward_func": 0.01837499998509884,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.33713291585445404,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.06056249886751175,
-      "step": 46
-    },
-    {
-      "completion_length": 353.375,
-      "epoch": 5.333333333333333,
-      "grad_norm": 6.933172225952148,
-      "kl": 0.002127421241311822,
-      "learning_rate": 2.1387846565474044e-09,
-      "loss": 0.0,
-      "reward": 0.6708917245268822,
-      "reward_std": 0.9302016571164131,
-      "rewards/concensus_correctness_reward_func": 0.006812499836087227,
-      "rewards/consensus_reward_func": 0.0,
-      "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.2251729667186737,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.1264062523841858,
-      "step": 48
     },
     {
-      "completion_length": 346.9375,
-      "epoch": 5.555555555555555,
-      "grad_norm": 7.681344985961914,
-      "kl": 0.0038058556092437357,
       "learning_rate": 0.0,
       "loss": 0.0,
-      "reward": 0.41686041094362736,
-      "reward_std": 0.7147915656678379,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.2795791446696967,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.13728125765919685,
-      "step": 50
     },
     {
-      "epoch": 5.555555555555555,
-      "step": 50,
       "total_flos": 0.0,
-      "train_loss": 2.602725280667073e-06,
-      "train_runtime": 1884.3714,
-      "train_samples_per_second": 0.425,
-      "train_steps_per_second": 0.027
     }
   ],
   "logging_steps": 2,
-  "max_steps": 50,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 5.0,
   "eval_steps": 500,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 311.9375,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.2533836364746094,
+      "kl": 0.0024804054301057477,
+      "learning_rate": 4.985344892885899e-07,
       "loss": 0.0,
+      "reward": 0.6862528233905323,
+      "reward_std": 0.8880199125269428,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.3277840710361488,
+      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.030343750026077032,
       "step": 2
     },
     {
+      "completion_length": 314.40625,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 4.825911045074463,
+      "kl": 0.0020024704354000278,
+      "learning_rate": 4.869132927957006e-07,
       "loss": 0.0,
+      "reward": 0.5271140232216567,
+      "reward_std": 0.5235589223448187,
+      "rewards/concensus_correctness_reward_func": 0.07243750058114529,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.3320827658753842,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.12259375443682075,
       "step": 4
     },
     {
+      "completion_length": 382.9375,
+      "epoch": 1.0,
+      "grad_norm": 2.1020917892456055,
+      "kl": 0.0017269225791096687,
+      "learning_rate": 4.642142940418973e-07,
       "loss": 0.0,
+      "reward": 0.7331130523234606,
+      "reward_std": 0.7579053556546569,
+      "rewards/concensus_correctness_reward_func": 0.03125,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.386425550095737,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.19043749384582043,
+      "step": 6
     },
     {
+      "completion_length": 298.71875,
       "epoch": 1.3333333333333333,
+      "grad_norm": 2.3231563568115234,
+      "kl": 0.011588757915887982,
+      "learning_rate": 4.314988729807827e-07,
       "loss": 0.0,
+      "reward": 0.960457656532526,
+      "reward_std": 0.9214519280940294,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.458113893866539,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18984374217689037,
+      "step": 8
     },
     {
+      "completion_length": 343.65625,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 12.242687225341797,
+      "kl": 0.0029063843467156403,
+      "learning_rate": 3.902967663405956e-07,
       "loss": 0.0,
+      "reward": 0.7999913152307272,
+      "reward_std": 0.7998636066913605,
+      "rewards/concensus_correctness_reward_func": 0.0625,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.37349133379757404,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.2702499981969595,
+      "step": 10
     },
     {
+      "completion_length": 387.0625,
       "epoch": 2.0,
+      "grad_norm": 4.154313087463379,
+      "kl": 0.003268745364039205,
+      "learning_rate": 3.4253453883497864e-07,
       "loss": 0.0,
+      "reward": 0.38145725440699607,
+      "reward_std": 0.7882596589624882,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.24976976320613176,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.006687496788799763,
+      "step": 12
     },
     {
+      "completion_length": 337.4375,
+      "epoch": 2.3333333333333335,
+      "grad_norm": 5.914424419403076,
+      "kl": 0.0017011765885399655,
+      "learning_rate": 2.9044549913819124e-07,
       "loss": 0.0,
+      "reward": 0.5687886712839827,
+      "reward_std": 0.7552150477422401,
+      "rewards/concensus_correctness_reward_func": 0.14237500727176666,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.2534136431058869,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.11049999855458736,
+      "step": 14
     },
     {
+      "completion_length": 382.96875,
       "epoch": 2.6666666666666665,
+      "grad_norm": 3.6555304527282715,
+      "kl": 0.002678310018382035,
+      "learning_rate": 2.3646527285364563e-07,
       "loss": 0.0,
+      "reward": 0.5685348343104124,
+      "reward_std": 0.7404244616627693,
+      "rewards/concensus_correctness_reward_func": 0.03125,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.2857223302125931,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.126562493853271,
+      "step": 16
     },
     {
+      "completion_length": 356.0,
+      "epoch": 3.0,
+      "grad_norm": 9.670379638671875,
+      "kl": 0.002987725820275955,
+      "learning_rate": 1.8311791536769483e-07,
       "loss": 0.0,
+      "reward": 1.5724409651011229,
+      "reward_std": 1.7105311714112759,
+      "rewards/concensus_correctness_reward_func": 0.65625,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.4052846720442176,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.19840626372024417,
+      "step": 18
     },
     {
+      "completion_length": 354.96875,
       "epoch": 3.3333333333333335,
+      "grad_norm": 2.7042019367218018,
+      "kl": 0.0031882738694548607,
+      "learning_rate": 1.328978898250525e-07,
       "loss": 0.0,
+      "reward": 0.5442854713182896,
+      "reward_std": 0.4820221420377493,
+      "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.3049104630481452,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.1768750064074993,
+      "step": 20
     },
     {
+      "completion_length": 305.6875,
+      "epoch": 3.6666666666666665,
+      "grad_norm": 1.809343934059143,
+      "kl": 0.004354253404017072,
+      "learning_rate": 8.81534288045431e-08,
       "loss": 0.0,
+      "reward": 0.6040084585547447,
+      "reward_std": 0.7027890784665942,
+      "rewards/concensus_correctness_reward_func": 0.03125,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.3406959716230631,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.16956250369548798,
+      "step": 22
     },
     {
+      "completion_length": 341.59375,
       "epoch": 4.0,
+      "grad_norm": 2.9913904666900635,
+      "kl": 0.0018703212990658358,
+      "learning_rate": 5.097673357358906e-08,
       "loss": 0.0,
+      "reward": 0.7669433043338358,
+      "reward_std": 0.7492063250392675,
+      "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.2261932883411646,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2907500099390745,
+      "step": 24
     },
     {
+      "completion_length": 330.8125,
+      "epoch": 4.333333333333333,
+      "grad_norm": 2.7992258071899414,
+      "kl": 0.0020362258510431275,
+      "learning_rate": 2.3106145082260774e-08,
       "loss": 0.0,
+      "reward": 0.8596324669197202,
+      "reward_std": 0.7516352757811546,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.447476205881685,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2871562447398901,
+      "step": 26
     },
     {
+      "completion_length": 280.90625,
+      "epoch": 4.666666666666667,
+      "grad_norm": 4.421070098876953,
+      "kl": 0.0036720147472806275,
+      "learning_rate": 5.844861072478335e-09,
       "loss": 0.0,
+      "reward": 0.7156252432614565,
+      "reward_std": 0.6206880370154977,
+      "rewards/concensus_correctness_reward_func": 0.03125,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.35737523529678583,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.13949999772012234,
+      "step": 28
     },
     {
+      "completion_length": 392.6875,
+      "epoch": 5.0,
+      "grad_norm": 2.573320150375366,
+      "kl": 0.002341544590308331,
       "learning_rate": 0.0,
       "loss": 0.0,
+      "reward": 0.289842139929533,
+      "reward_std": 0.8682990339584649,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.22246714239008725,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.05762500315904617,
+      "step": 30
     },
     {
+      "epoch": 5.0,
+      "step": 30,
       "total_flos": 0.0,
+      "train_loss": 3.2592993572203946e-06,
+      "train_runtime": 1944.3016,
+      "train_samples_per_second": 0.247,
+      "train_steps_per_second": 0.015
     }
   ],
   "logging_steps": 2,
+  "max_steps": 30,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917faed80e8f0d32c7a502f8387188ce0f22101cba52b5ab4837cce72832a98f
 size 5944

 version https://git-lfs.github.com/spec/v1
+oid sha256:c6738a9deb710effecf6a6117a558fe1d30598f3c1804870a6a1ddc1103b3f35
 size 5944