Instructions to use moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret with Transformers:

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

pipe = pipeline("text-generation", model="moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret")
model = AutoModelForCausalLM.from_pretrained("moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret", 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 moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret

SGLang

How to use moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret 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 "moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret" \
    --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": "moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret",
		"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 "moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret" \
        --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": "moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret 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 moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret 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 moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret",
    max_seq_length=2048,
)

Docker Model Runner
How to use moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret with Docker Model Runner:
```
docker model run hf.co/moscowx21/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-giant_pale_ferret
```

aawwssdddwdwd commited on Apr 14, 2025

Commit

177c659

verified ·

1 Parent(s): 50c668d

End of training

Browse files

Files changed (8) hide show

README.md +1 -1
all_results.json +5 -5
config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1
train_results.json +5 -5
trainer_state.json +128 -128
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -38,7 +38,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 ### Framework versions
 - TRL: 0.15.2
-- Transformers: 4.50.3
 - Pytorch: 2.5.1
 - Datasets: 3.5.0
 - Tokenizers: 0.21.1

 ### Framework versions
 - TRL: 0.15.2
+- Transformers: 4.51.3
 - Pytorch: 2.5.1
 - Datasets: 3.5.0
 - Tokenizers: 0.21.1

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.1765008568763733e-06,
-    "train_runtime": 389.9144,
-    "train_samples": 160,
-    "train_samples_per_second": 0.821,
-    "train_steps_per_second": 0.051
 }

 {
     "total_flos": 0.0,
+    "train_loss": 4.3076954852949715e-06,
+    "train_runtime": 535.5837,
+    "train_samples": 104,
+    "train_samples_per_second": 0.597,
+    "train_steps_per_second": 0.037
 }

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json CHANGED Viewed

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.50.3"
 }

   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
+  "transformers_version": "4.51.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce55caf9b32891b1be461781f4025f8943aa70196c8974e5d2b9ac4cc7a61a97
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:7b628e031b7b0f2dceb08abad5826a1cd769a637820ca38d014570674461496b
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.1765008568763733e-06,
-    "train_runtime": 389.9144,
-    "train_samples": 160,
-    "train_samples_per_second": 0.821,
-    "train_steps_per_second": 0.051
 }

 {
     "total_flos": 0.0,
+    "train_loss": 4.3076954852949715e-06,
+    "train_runtime": 535.5837,
+    "train_samples": 104,
+    "train_samples_per_second": 0.597,
+    "train_steps_per_second": 0.037
 }

trainer_state.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -10,209 +10,209 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 358.8125,
-      "epoch": 0.1,
-      "grad_norm": 5.128148078918457,
       "kl": 0.0,
-      "learning_rate": 4.965903258506806e-07,
-      "loss": 0.0,
-      "reward": 1.920902309473604,
-      "reward_std": 1.5184391534421593,
-      "rewards/concensus_correctness_reward_func": 0.3513750033453107,
-      "rewards/consensus_reward_func": 0.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.41521482449024916,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.466812496073544,
       "step": 2
     },
     {
-      "completion_length": 326.90625,
-      "epoch": 0.2,
-      "grad_norm": 4.2698469161987305,
-      "kl": 0.0012383201719785575,
-      "learning_rate": 4.698684378016222e-07,
       "loss": 0.0,
-      "reward": 1.7122610099613667,
-      "reward_std": 1.1609715959639288,
-      "rewards/concensus_correctness_reward_func": 0.23168749827891588,
-      "rewards/consensus_reward_func": 0.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.5111047318205237,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3444687547162175,
       "step": 4
     },
     {
-      "completion_length": 418.59375,
-      "epoch": 0.3,
-      "grad_norm": 5.097483158111572,
-      "kl": 0.0015109705473150825,
-      "learning_rate": 4.193203929064353e-07,
       "loss": 0.0,
-      "reward": 1.2479718840913847,
-      "reward_std": 0.6527503429970238,
-      "rewards/concensus_correctness_reward_func": 0.07975000143051147,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.4569093860918656,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3988124942407012,
       "step": 6
     },
     {
-      "completion_length": 396.53125,
-      "epoch": 0.4,
-      "grad_norm": 4.257869243621826,
-      "kl": 0.0019715054659172893,
-      "learning_rate": 3.5042385616324236e-07,
       "loss": 0.0,
-      "reward": 1.635931245982647,
-      "reward_std": 1.020388813689351,
-      "rewards/concensus_correctness_reward_func": 0.14943750109523535,
-      "rewards/consensus_reward_func": 0.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.48218128900043666,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3793124984949827,
       "step": 8
     },
     {
-      "completion_length": 419.875,
-      "epoch": 0.5,
-      "grad_norm": 3.371570110321045,
-      "kl": 0.00194889300109935,
-      "learning_rate": 2.706448363680831e-07,
       "loss": 0.0,
-      "reward": 2.2834888957440853,
-      "reward_std": 1.2663272079080343,
-      "rewards/concensus_correctness_reward_func": 0.40874999947845936,
-      "rewards/consensus_reward_func": 0.375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.5105513697490096,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.7391874864697456,
       "step": 10
     },
     {
-      "completion_length": 422.03125,
-      "epoch": 0.6,
-      "grad_norm": 4.007848739624023,
-      "kl": 0.0029282994655659422,
-      "learning_rate": 1.886286282148002e-07,
       "loss": 0.0,
-      "reward": 1.628133011981845,
-      "reward_std": 1.141701115295291,
-      "rewards/concensus_correctness_reward_func": 0.2252500019967556,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.5204767659306526,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.507406250697386,
       "step": 12
     },
     {
-      "completion_length": 453.9375,
-      "epoch": 0.7,
-      "grad_norm": 3.688523054122925,
-      "kl": 0.0023045147099765018,
-      "learning_rate": 1.1326296046939333e-07,
       "loss": 0.0,
-      "reward": 1.8677344880998135,
-      "reward_std": 1.1840693070553243,
-      "rewards/concensus_correctness_reward_func": 0.3175625018775463,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.6593594700098038,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.45331250689923763,
       "step": 14
     },
     {
-      "completion_length": 345.3125,
-      "epoch": 0.8,
-      "grad_norm": 4.259862899780273,
-      "kl": 0.002908603215473704,
-      "learning_rate": 5.271487265090163e-08,
       "loss": 0.0,
-      "reward": 2.4872301314026117,
-      "reward_std": 2.5430639277910814,
-      "rewards/concensus_correctness_reward_func": 0.8553749984130263,
-      "rewards/consensus_reward_func": 0.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.5011364271049388,
-      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.47446875739842653,
       "step": 16
     },
     {
-      "completion_length": 343.9375,
-      "epoch": 0.9,
-      "grad_norm": 4.737185955047607,
-      "kl": 0.00293535369928577,
-      "learning_rate": 1.3545689574841341e-08,
       "loss": 0.0,
-      "reward": 1.9544069655239582,
-      "reward_std": 0.9897497426718473,
-      "rewards/concensus_correctness_reward_func": 0.20006249845027924,
-      "rewards/consensus_reward_func": 0.3125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.43893826520070434,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.7529062535613775,
       "step": 18
     },
     {
-      "completion_length": 290.25,
-      "epoch": 1.0,
-      "grad_norm": 4.982654094696045,
-      "kl": 0.0030415507935686037,
-      "learning_rate": 0.0,
       "loss": 0.0,
-      "reward": 2.1933444906026125,
-      "reward_std": 1.347527216479648,
-      "rewards/concensus_correctness_reward_func": 0.4152499958872795,
-      "rewards/consensus_reward_func": 0.375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.5650007203221321,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.6505937650799751,
       "step": 20
     },
     {
-      "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 2.1765008568763733e-06,
-      "train_runtime": 389.9144,
-      "train_samples_per_second": 0.821,
-      "train_steps_per_second": 0.051
     }
   ],
   "logging_steps": 2,
   "max_steps": 20,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 1.5384615384615383,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 335.125,
+      "epoch": 0.15384615384615385,
+      "grad_norm": 113.76084899902344,
       "kl": 0.0,
+      "learning_rate": 5e-07,
+      "loss": -0.0,
+      "reward": 0.5326231555081904,
+      "reward_std": 0.39712623693048954,
+      "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": 0.28109190798568306,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18903125426732004,
       "step": 2
     },
     {
+      "completion_length": 222.0625,
+      "epoch": 0.3076923076923077,
+      "grad_norm": 167.0595245361328,
+      "kl": 0.0030416610734391725,
+      "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 0.2555721157696098,
+      "reward_std": 0.3549694743414875,
+      "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": 0.1653533645439893,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.02771875075995922,
       "step": 4
     },
     {
+      "completion_length": 354.625,
+      "epoch": 0.46153846153846156,
+      "grad_norm": 6.337334156036377,
+      "kl": 0.0010862785820791032,
+      "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
+      "reward": 0.11460426822304726,
+      "reward_std": 0.7663493577274494,
+      "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": 0.19647929281927645,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.14437501080101356,
       "step": 6
     },
     {
+      "completion_length": 286.375,
+      "epoch": 0.6153846153846154,
+      "grad_norm": 14.78044319152832,
+      "kl": 0.0018513284521759488,
+      "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
+      "reward": 0.5740392594598234,
+      "reward_std": 0.5501163068693131,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.2515392726054415,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.11937499977648258,
       "step": 8
     },
     {
+      "completion_length": 322.875,
+      "epoch": 0.7692307692307693,
+      "grad_norm": 23.10611343383789,
+      "kl": 0.0021936903613095637,
+      "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
+      "reward": 0.21336799208074808,
+      "reward_std": 0.44811401196056977,
+      "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": 0.258524238714017,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.045156255131587386,
       "step": 10
     },
     {
+      "completion_length": 305.875,
+      "epoch": 0.9230769230769231,
+      "grad_norm": 13.471948623657227,
+      "kl": 0.0015927579770504963,
+      "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
+      "reward": 0.25780566956382245,
+      "reward_std": 0.5996597472112626,
+      "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": 0.19636816903948784,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.06356249563395977,
       "step": 12
     },
     {
+      "completion_length": 356.90625,
+      "epoch": 1.0769230769230769,
+      "grad_norm": 7.529191970825195,
+      "kl": 0.005199393173825229,
+      "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
+      "reward": 0.5008027306757867,
+      "reward_std": 0.6540710940025747,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.2908964797388762,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.02240624837577343,
       "step": 14
     },
     {
+      "completion_length": 282.46875,
+      "epoch": 1.2307692307692308,
+      "grad_norm": 11.132549285888672,
+      "kl": 0.0023966655353433453,
+      "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
+      "reward": 0.4687036501709372,
+      "reward_std": 0.495733046438545,
+      "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": 0.26454739971086383,
+      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.12603125057648867,
       "step": 16
     },
     {
+      "completion_length": 169.96875,
+      "epoch": 1.3846153846153846,
+      "grad_norm": 34.29732131958008,
+      "kl": 0.0047469171695411205,
+      "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
+      "reward": 0.3130655135028064,
+      "reward_std": 0.3251972365542315,
+      "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": 0.17259676140383817,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0779687506146729,
       "step": 18
     },
     {
+      "completion_length": 305.9375,
+      "epoch": 1.5384615384615383,
+      "grad_norm": 66.23303985595703,
+      "kl": 0.021018446917878464,
+      "learning_rate": 3.4096741493194193e-09,
       "loss": 0.0,
+      "reward": 0.21660699727362953,
+      "reward_std": 0.2998809102573432,
+      "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": 0.14573199834558181,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.07087500323541462,
       "step": 20
     },
     {
+      "epoch": 1.5384615384615383,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 4.3076954852949715e-06,
+      "train_runtime": 535.5837,
+      "train_samples_per_second": 0.597,
+      "train_steps_per_second": 0.037
     }
   ],
   "logging_steps": 2,
   "max_steps": 20,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4591d867a8fa7315cfbd122d0fc772738fe97893db9e19c17c8ef3d5ac990d
-size 6008

 version https://git-lfs.github.com/spec/v1
+oid sha256:f0c5a3fafa9d09ed82a2894e2a76e52e3e3c219a83ca4c86615bf3934872d12a
+size 5944