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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/sergisimi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-timid_enormous_eel

SGLang

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

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

sergisimi commited on Apr 23, 2025

Commit

a030675

verified ·

1 Parent(s): 8ba3f7b

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 +124 -124
training_args.bin +1 -1

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: 4.51.0
 - 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": 2.5179237127304076e-06,
-    "train_runtime": 1425.2641,
-    "train_samples": 40,
-    "train_samples_per_second": 0.225,
-    "train_steps_per_second": 0.014
 }

 {
     "total_flos": 0.0,
+    "train_loss": 4.036165773868561e-06,
+    "train_runtime": 203.1494,
+    "train_samples": 28,
+    "train_samples_per_second": 1.575,
+    "train_steps_per_second": 0.098
 }

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.0",
   "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": "4.51.0"
 }

   "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:ef6f8fd882018c2029ed9817c1fe3c188df890b2bfcb39f1ef9a84f855449f8c
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:2a39febe3f60d310eff0a5798a7b17b97a8078c436d4acaf77cbeacaf30e6ed9
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.5179237127304076e-06,
-    "train_runtime": 1425.2641,
-    "train_samples": 40,
-    "train_samples_per_second": 0.225,
-    "train_steps_per_second": 0.014
 }

 {
     "total_flos": 0.0,
+    "train_loss": 4.036165773868561e-06,
+    "train_runtime": 203.1494,
+    "train_samples": 28,
+    "train_samples_per_second": 1.575,
+    "train_steps_per_second": 0.098
 }

trainer_state.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -10,209 +10,209 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 376.78125,
-      "epoch": 0.4,
-      "grad_norm": 9.419937133789062,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": 0.0,
-      "reward": 0.8982328362762928,
-      "reward_std": 0.8957028803415596,
-      "rewards/concensus_correctness_reward_func": 0.12150000035762787,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.28982658532913774,
-      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.36190625093877316,
       "step": 2
     },
     {
-      "completion_length": 303.0625,
-      "epoch": 0.8,
-      "grad_norm": 16.360496520996094,
-      "kl": 0.0018617127680045087,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
-      "reward": 1.9974666351918131,
-      "reward_std": 2.0806010872038314,
-      "rewards/concensus_correctness_reward_func": 0.8354999963194132,
-      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.40974785340949893,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.03125,
-      "rewards/xmlcount_reward_func": 0.40846874634735286,
       "step": 4
     },
     {
-      "completion_length": 338.5625,
-      "epoch": 1.2,
-      "grad_norm": 11.249113082885742,
-      "kl": 0.0014679385494673625,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
-      "reward": 1.0521508090896532,
-      "reward_std": 0.8584795482747722,
-      "rewards/concensus_correctness_reward_func": 0.14687499776482582,
-      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.33327579603064805,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.03125,
-      "rewards/xmlcount_reward_func": 0.35324999620206654,
       "step": 6
     },
     {
-      "completion_length": 375.09375,
-      "epoch": 1.6,
-      "grad_norm": 5.771604537963867,
-      "kl": 0.001528985405457206,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
-      "reward": 1.6449143970385194,
-      "reward_std": 1.950113006751053,
-      "rewards/concensus_correctness_reward_func": 0.7482500001788139,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.4411331639857963,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.03125,
-      "rewards/xmlcount_reward_func": 0.1742812478914857,
       "step": 8
     },
     {
-      "completion_length": 337.65625,
-      "epoch": 2.0,
-      "grad_norm": 8.124749183654785,
-      "kl": 0.004178064547886606,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
-      "reward": 1.1003415104933083,
-      "reward_std": 0.8792835858184844,
-      "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": 0.3608102686703205,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.6014062347821891,
       "step": 10
     },
     {
-      "completion_length": 344.0625,
-      "epoch": 2.4,
-      "grad_norm": 8.546586990356445,
-      "kl": 0.004825560077733826,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
-      "reward": 0.5016123706009239,
-      "reward_std": 0.663908442016691,
-      "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": 0.3652373746735975,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.1363750018645078,
       "step": 12
     },
     {
-      "completion_length": 383.625,
-      "epoch": 2.8,
-      "grad_norm": 4.618159294128418,
-      "kl": 0.0030358081712620333,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
-      "reward": 0.4713071408914402,
-      "reward_std": 0.42544175022339914,
-      "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": 0.2834946505026892,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.17218750156462193,
       "step": 14
     },
     {
-      "completion_length": 370.90625,
-      "epoch": 3.2,
-      "grad_norm": 7.157219886779785,
-      "kl": 0.003981857269536704,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
-      "reward": 1.6145572238601744,
-      "reward_std": 1.8933260106496164,
-      "rewards/concensus_correctness_reward_func": 0.7465000003576279,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.37758851423859596,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3029687451198697,
       "step": 16
     },
     {
-      "completion_length": 393.28125,
-      "epoch": 3.6,
-      "grad_norm": 5.100037097930908,
-      "kl": 0.002306824164406862,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
-      "reward": 1.2386403833515942,
-      "reward_std": 1.3317663265625015,
-      "rewards/concensus_correctness_reward_func": 0.625,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.2853903556242585,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.3126249979250133,
       "step": 18
     },
     {
-      "completion_length": 438.71875,
-      "epoch": 4.0,
-      "grad_norm": 6.435215950012207,
-      "kl": 0.002064306852844311,
       "learning_rate": 3.4096741493194193e-09,
       "loss": 0.0,
-      "reward": 1.010270037688315,
-      "reward_std": 1.0351053967606276,
-      "rewards/concensus_correctness_reward_func": 0.12162499874830246,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.4003325153607875,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.1758125089108944,
       "step": 20
     },
     {
-      "epoch": 4.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 2.5179237127304076e-06,
-      "train_runtime": 1425.2641,
-      "train_samples_per_second": 0.225,
-      "train_steps_per_second": 0.014
     }
   ],
   "logging_steps": 2,
   "max_steps": 20,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 5.0,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 344.03125,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 6.132088661193848,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": -0.0,
+      "reward": 2.487778352573514,
+      "reward_std": 2.006606017239392,
+      "rewards/concensus_correctness_reward_func": 0.8620624975301325,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.6062783699599095,
+      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5038125060964376,
       "step": 2
     },
     {
+      "completion_length": 341.0,
+      "epoch": 1.0,
+      "grad_norm": 3.1462059020996094,
+      "kl": 0.0008595892310646983,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 1.8018831710020702,
+      "reward_std": 1.0011655843506257,
+      "rewards/concensus_correctness_reward_func": 0.23699999849001566,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.6140498152623574,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5341666688521703,
       "step": 4
     },
     {
+      "completion_length": 297.71875,
+      "epoch": 1.5714285714285714,
+      "grad_norm": 6.190745830535889,
+      "kl": 0.0016320943250320852,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
+      "reward": 1.9226003549993038,
+      "reward_std": 1.0635974742472172,
+      "rewards/concensus_correctness_reward_func": 0.24456249782815576,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.5560690779238939,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6844687629491091,
       "step": 6
     },
     {
+      "completion_length": 314.9166666666667,
+      "epoch": 2.0,
+      "grad_norm": 3.6605167388916016,
+      "kl": 0.0024019686485795924,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
+      "reward": 2.3699574917554855,
+      "reward_std": 1.2540641278028488,
+      "rewards/concensus_correctness_reward_func": 0.5460833261410395,
+      "rewards/consensus_reward_func": 0.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3333333333333333,
+      "rewards/question_recreation_reward_func": 0.5782075046251217,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5790000098447005,
       "step": 8
     },
     {
+      "completion_length": 311.96875,
+      "epoch": 2.571428571428571,
+      "grad_norm": 4.422511100769043,
+      "kl": 0.004271938196325209,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
+      "reward": 2.2210648357868195,
+      "reward_std": 1.0689412193605676,
+      "rewards/concensus_correctness_reward_func": 0.41612499207258224,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.5958773451857269,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6465625241398811,
       "step": 10
     },
     {
+      "completion_length": 269.7083333333333,
+      "epoch": 3.0,
+      "grad_norm": 4.302887439727783,
+      "kl": 0.006312902851883943,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
+      "reward": 1.8300592303276062,
+      "reward_std": 1.2033961129685242,
+      "rewards/concensus_correctness_reward_func": 0.2336666683355967,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.5991008977095286,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6639583297073841,
       "step": 12
     },
     {
+      "completion_length": 314.96875,
+      "epoch": 3.571428571428571,
+      "grad_norm": 4.885258197784424,
+      "kl": 0.005343124037608504,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
+      "reward": 3.495531538501382,
+      "reward_std": 0.7231066498789005,
+      "rewards/concensus_correctness_reward_func": 1.6215624958276749,
+      "rewards/consensus_reward_func": 0.4375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.6186253735795617,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6928437631577253,
       "step": 14
     },
     {
+      "completion_length": 323.0416666666667,
+      "epoch": 4.0,
+      "grad_norm": 3.448960542678833,
+      "kl": 0.004590911810131122,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
+      "reward": 1.647290966163079,
+      "reward_std": 1.4142502636338274,
+      "rewards/concensus_correctness_reward_func": 0.23466667036215463,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.6292909507950147,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.3666666764765978,
       "step": 16
     },
     {
+      "completion_length": 273.0,
+      "epoch": 4.571428571428571,
+      "grad_norm": 5.234982013702393,
+      "kl": 0.013104470373946242,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
+      "reward": 2.2405245900154114,
+      "reward_std": 0.7255052882392192,
+      "rewards/concensus_correctness_reward_func": 0.23793749883770943,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.5015558530576527,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.876031257212162,
       "step": 18
     },
     {
+      "completion_length": 259.5833333333333,
+      "epoch": 5.0,
+      "grad_norm": 3.524683952331543,
+      "kl": 0.00839625116592894,
       "learning_rate": 3.4096741493194193e-09,
       "loss": 0.0,
+      "reward": 2.6440209125479064,
+      "reward_std": 1.0717806244889896,
+      "rewards/concensus_correctness_reward_func": 0.6558333337306976,
+      "rewards/consensus_reward_func": 0.6666666666666666,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.5464792400598526,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6917083462079366,
       "step": 20
     },
     {
+      "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 4.036165773868561e-06,
+      "train_runtime": 203.1494,
+      "train_samples_per_second": 1.575,
+      "train_steps_per_second": 0.098
     }
   ],
   "logging_steps": 2,
   "max_steps": 20,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dfd42996f571fced0bd9932b34fefd526e57445bd43e3f78356d7c98ac62d26
 size 5944

 version https://git-lfs.github.com/spec/v1
+oid sha256:e71e89f0307a35f08070224668f1f70ed2bded98f9b9c06c83a9fb840307084f
 size 5944