Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
rl-swarm
grpo
gensyn
I am durable woolly antelope
unsloth
trl
genrl-swarm
I am durable_woolly_antelope
conversational
text-generation-inference
Instructions to use whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope") model = AutoModelForCausalLM.from_pretrained("whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope", 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 whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope
- SGLang
How to use whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope 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 "whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope" \ --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": "whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope", "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 "whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope" \ --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": "whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope 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 whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope 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 whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope", max_seq_length=2048, ) - Docker Model Runner
How to use whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope with Docker Model Runner:
docker model run hf.co/whodisidk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-durable_woolly_antelope
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.097560975609756, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "completion_length": 170.46875, | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 6.099827289581299, | |
| "kl": 0.5973675912246108, | |
| "learning_rate": 1.6666666666666665e-07, | |
| "loss": 0.0006, | |
| "reward": 2.4682722240686417, | |
| "reward_std": 0.4695738647133112, | |
| "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": 0.7388660460710526, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.166906252503395, | |
| "step": 2 | |
| }, | |
| { | |
| "completion_length": 114.125, | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 5.554270267486572, | |
| "kl": 1.5984905734658241, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0016, | |
| "reward": 2.225109323859215, | |
| "reward_std": 0.6870723395841196, | |
| "rewards/concensus_correctness_reward_func": 0.06012500077486038, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.5827342979609966, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.390625, | |
| "rewards/xmlcount_reward_func": 1.1291249990463257, | |
| "step": 4 | |
| }, | |
| { | |
| "completion_length": 148.15625, | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 5.069469451904297, | |
| "kl": 3.3319540731608868, | |
| "learning_rate": 4.994757065594279e-07, | |
| "loss": 0.0033, | |
| "reward": 4.637000426650047, | |
| "reward_std": 2.4823005218058825, | |
| "rewards/concensus_correctness_reward_func": 1.4928749948740005, | |
| "rewards/consensus_reward_func": 0.1875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.875, | |
| "rewards/question_recreation_reward_func": 0.7499066442251205, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.328125, | |
| "rewards/xmlcount_reward_func": 1.0035937614738941, | |
| "step": 6 | |
| }, | |
| { | |
| "completion_length": 159.59375, | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 22.011062622070312, | |
| "kl": 5.900226164609194, | |
| "learning_rate": 4.979050253066063e-07, | |
| "loss": 0.0059, | |
| "reward": 2.358607694506645, | |
| "reward_std": 0.5496477753622457, | |
| "rewards/concensus_correctness_reward_func": 0.06012500077486038, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7734514437615871, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.296875, | |
| "rewards/xmlcount_reward_func": 1.1656562685966492, | |
| "step": 8 | |
| }, | |
| { | |
| "completion_length": 175.625, | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 4.487865447998047, | |
| "kl": 0.8899677954614162, | |
| "learning_rate": 4.952945442245597e-07, | |
| "loss": 0.0009, | |
| "reward": 2.114151880145073, | |
| "reward_std": 0.5495768673717976, | |
| "rewards/concensus_correctness_reward_func": 0.0598750002682209, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.5913393385708332, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.1504375040531158, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 137.7, | |
| "epoch": 1.0975609756097562, | |
| "grad_norm": 5.117649078369141, | |
| "kl": 0.46071633845567705, | |
| "learning_rate": 4.916552125781528e-07, | |
| "loss": 0.0003, | |
| "reward": 3.7879202365875244, | |
| "reward_std": 1.7626623034477233, | |
| "rewards/concensus_correctness_reward_func": 0.4884000062942505, | |
| "rewards/consensus_reward_func": 0.3, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.8, | |
| "rewards/question_recreation_reward_func": 0.7498702496290207, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3, | |
| "rewards/xmlcount_reward_func": 1.1496500015258788, | |
| "step": 12 | |
| }, | |
| { | |
| "completion_length": 174.71875, | |
| "epoch": 1.2926829268292683, | |
| "grad_norm": 4.460564136505127, | |
| "kl": 0.9902181550860405, | |
| "learning_rate": 4.870022949890676e-07, | |
| "loss": 0.001, | |
| "reward": 2.211259737610817, | |
| "reward_std": 0.41652211552718654, | |
| "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": 0.7058847844600677, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.328125, | |
| "rewards/xmlcount_reward_func": 1.1772499978542328, | |
| "step": 14 | |
| }, | |
| { | |
| "completion_length": 121.15625, | |
| "epoch": 1.4878048780487805, | |
| "grad_norm": 5.077511787414551, | |
| "kl": 2.23406695201993, | |
| "learning_rate": 4.81355307410676e-07, | |
| "loss": 0.0022, | |
| "reward": 4.244883641600609, | |
| "reward_std": 2.1680759941227734, | |
| "rewards/concensus_correctness_reward_func": 1.4302500039339066, | |
| "rewards/consensus_reward_func": 0.1875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.9261960908770561, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.28125, | |
| "rewards/xmlcount_reward_func": 1.1696875020861626, | |
| "step": 16 | |
| }, | |
| { | |
| "completion_length": 183.53125, | |
| "epoch": 1.6829268292682928, | |
| "grad_norm": 5.903010845184326, | |
| "kl": 2.295085714198649, | |
| "learning_rate": 4.747379352713488e-07, | |
| "loss": 0.0023, | |
| "reward": 2.392599403858185, | |
| "reward_std": 0.9273251239210367, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.792318120598793, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.1875, | |
| "rewards/xmlcount_reward_func": 0.9127812534570694, | |
| "step": 18 | |
| }, | |
| { | |
| "completion_length": 142.8125, | |
| "epoch": 1.8780487804878048, | |
| "grad_norm": 1.9898862838745117, | |
| "kl": 0.6429034024477005, | |
| "learning_rate": 4.6717793412953776e-07, | |
| "loss": 0.0006, | |
| "reward": 2.9371677935123444, | |
| "reward_std": 0.8608561623841524, | |
| "rewards/concensus_correctness_reward_func": 0.12025000154972076, | |
| "rewards/consensus_reward_func": 0.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.6914178244769573, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.34375, | |
| "rewards/xmlcount_reward_func": 1.1567500084638596, | |
| "step": 20 | |
| }, | |
| { | |
| "completion_length": 217.05, | |
| "epoch": 2.0, | |
| "grad_norm": 1.1733369827270508, | |
| "kl": 4.470386900007725, | |
| "learning_rate": 4.5870701325731773e-07, | |
| "loss": 0.0028, | |
| "reward": 2.0891710042953493, | |
| "reward_std": 0.5484436511993408, | |
| "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": 0.7873210072517395, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.0518500089645386, | |
| "step": 22 | |
| }, | |
| { | |
| "completion_length": 139.375, | |
| "epoch": 2.1951219512195124, | |
| "grad_norm": 4.537793159484863, | |
| "kl": 0.816438952460885, | |
| "learning_rate": 4.4936070264068016e-07, | |
| "loss": 0.0008, | |
| "reward": 2.3938701897859573, | |
| "reward_std": 0.34673458884935826, | |
| "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": 0.6716827414929867, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.296875, | |
| "rewards/xmlcount_reward_func": 1.1753125041723251, | |
| "step": 24 | |
| }, | |
| { | |
| "completion_length": 245.0, | |
| "epoch": 2.3902439024390243, | |
| "grad_norm": 3.754828929901123, | |
| "kl": 2.14161329343915, | |
| "learning_rate": 4.391782039544238e-07, | |
| "loss": 0.0021, | |
| "reward": 4.017070218920708, | |
| "reward_std": 2.1269510723650455, | |
| "rewards/concensus_correctness_reward_func": 1.9351250007748604, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.5311014428734779, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.28125, | |
| "rewards/xmlcount_reward_func": 0.9570937529206276, | |
| "step": 26 | |
| }, | |
| { | |
| "completion_length": 188.6875, | |
| "epoch": 2.5853658536585367, | |
| "grad_norm": 4.370049476623535, | |
| "kl": 41.1987736299634, | |
| "learning_rate": 4.282022261367073e-07, | |
| "loss": 0.0412, | |
| "reward": 3.2786895185709, | |
| "reward_std": 2.1890580281615257, | |
| "rewards/concensus_correctness_reward_func": 0.8053750023245811, | |
| "rewards/consensus_reward_func": 0.1875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.1875, | |
| "rewards/question_recreation_reward_func": 0.7307832725346088, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.265625, | |
| "rewards/xmlcount_reward_func": 1.1019062548875809, | |
| "step": 28 | |
| }, | |
| { | |
| "completion_length": 201.25, | |
| "epoch": 2.7804878048780486, | |
| "grad_norm": 3.327321767807007, | |
| "kl": 0.41819524113088846, | |
| "learning_rate": 4.1647880625292027e-07, | |
| "loss": 0.0004, | |
| "reward": 2.4246954917907715, | |
| "reward_std": 0.5871567726135254, | |
| "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": 0.6943517699837685, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.34375, | |
| "rewards/xmlcount_reward_func": 1.136593759059906, | |
| "step": 30 | |
| }, | |
| { | |
| "completion_length": 130.5625, | |
| "epoch": 2.975609756097561, | |
| "grad_norm": 4.2605109214782715, | |
| "kl": 1.8532675383612514, | |
| "learning_rate": 4.040571164002318e-07, | |
| "loss": 0.0019, | |
| "reward": 3.6226596236228943, | |
| "reward_std": 2.205760184675455, | |
| "rewards/concensus_correctness_reward_func": 0.8050000034272671, | |
| "rewards/consensus_reward_func": 0.1875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.4375, | |
| "rewards/question_recreation_reward_func": 0.7430970743298531, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.1370624974370003, | |
| "step": 32 | |
| }, | |
| { | |
| "completion_length": 104.65, | |
| "epoch": 3.097560975609756, | |
| "grad_norm": 5.712991237640381, | |
| "kl": 0.6544200539588928, | |
| "learning_rate": 3.909892574627266e-07, | |
| "loss": 0.0004, | |
| "reward": 1.9994364500045776, | |
| "reward_std": 0.34640331044793127, | |
| "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": 0.6102864652872085, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.225, | |
| "rewards/xmlcount_reward_func": 1.1641499996185303, | |
| "step": 34 | |
| }, | |
| { | |
| "completion_length": 164.625, | |
| "epoch": 3.292682926829268, | |
| "grad_norm": 3.5782923698425293, | |
| "kl": 0.47456978261470795, | |
| "learning_rate": 3.773300405821908e-07, | |
| "loss": 0.0005, | |
| "reward": 2.4073937088251114, | |
| "reward_std": 0.8083425159566104, | |
| "rewards/concensus_correctness_reward_func": 0.12012499943375587, | |
| "rewards/consensus_reward_func": 0.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7384249614551663, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.265625, | |
| "rewards/xmlcount_reward_func": 1.1582187488675117, | |
| "step": 36 | |
| }, | |
| { | |
| "completion_length": 145.4375, | |
| "epoch": 3.4878048780487805, | |
| "grad_norm": 3.6999077796936035, | |
| "kl": 0.7185129821300507, | |
| "learning_rate": 3.6313675726113475e-07, | |
| "loss": 0.0007, | |
| "reward": 3.2990617603063583, | |
| "reward_std": 1.678582351654768, | |
| "rewards/concensus_correctness_reward_func": 0.625, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.6626242846250534, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.359375, | |
| "rewards/xmlcount_reward_func": 1.1520625054836273, | |
| "step": 38 | |
| }, | |
| { | |
| "completion_length": 219.40625, | |
| "epoch": 3.682926829268293, | |
| "grad_norm": 3.1566965579986572, | |
| "kl": 0.7571137994527817, | |
| "learning_rate": 3.484689390623218e-07, | |
| "loss": 0.0008, | |
| "reward": 4.262388929724693, | |
| "reward_std": 1.6960864844731987, | |
| "rewards/concensus_correctness_reward_func": 1.875, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.7855764981359243, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.296875, | |
| "rewards/xmlcount_reward_func": 1.0549375042319298, | |
| "step": 40 | |
| }, | |
| { | |
| "completion_length": 124.125, | |
| "epoch": 3.8780487804878048, | |
| "grad_norm": 5.992835998535156, | |
| "kl": 4.541106943972409, | |
| "learning_rate": 3.3338810791270517e-07, | |
| "loss": 0.0045, | |
| "reward": 3.2296720147132874, | |
| "reward_std": 1.5638214345090091, | |
| "rewards/concensus_correctness_reward_func": 0.625, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.7207032516598701, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.40625, | |
| "rewards/xmlcount_reward_func": 1.2277187556028366, | |
| "step": 42 | |
| }, | |
| { | |
| "completion_length": 143.7, | |
| "epoch": 4.0, | |
| "grad_norm": 1.4582439661026, | |
| "kl": 13.396405771374702, | |
| "learning_rate": 3.179575180590857e-07, | |
| "loss": 0.0084, | |
| "reward": 5.374096298217774, | |
| "reward_std": 3.2581148982048034, | |
| "rewards/concensus_correctness_reward_func": 2.1923000037670137, | |
| "rewards/consensus_reward_func": 0.2, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.8, | |
| "rewards/question_recreation_reward_func": 0.8091962337493896, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.122599995136261, | |
| "step": 44 | |
| }, | |
| { | |
| "completion_length": 160.03125, | |
| "epoch": 4.195121951219512, | |
| "grad_norm": 4.867384910583496, | |
| "kl": 1.008437397889793, | |
| "learning_rate": 3.022418907578188e-07, | |
| "loss": 0.001, | |
| "reward": 3.2849575728178024, | |
| "reward_std": 1.9591746106743813, | |
| "rewards/concensus_correctness_reward_func": 0.6851250007748604, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.746645025908947, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.40625, | |
| "rewards/xmlcount_reward_func": 1.1344375163316727, | |
| "step": 46 | |
| }, | |
| { | |
| "completion_length": 168.625, | |
| "epoch": 4.390243902439025, | |
| "grad_norm": 5.173135280609131, | |
| "kl": 0.954070495441556, | |
| "learning_rate": 2.863071428113726e-07, | |
| "loss": 0.001, | |
| "reward": 3.638337269425392, | |
| "reward_std": 1.8555740788578987, | |
| "rewards/concensus_correctness_reward_func": 1.25, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.6886498406529427, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.328125, | |
| "rewards/xmlcount_reward_func": 1.1215624958276749, | |
| "step": 48 | |
| }, | |
| { | |
| "completion_length": 147.625, | |
| "epoch": 4.585365853658536, | |
| "grad_norm": 3.766300678253174, | |
| "kl": 1.248833647929132, | |
| "learning_rate": 2.7022011009035107e-07, | |
| "loss": 0.0012, | |
| "reward": 2.902125522494316, | |
| "reward_std": 0.7541704792529345, | |
| "rewards/concensus_correctness_reward_func": 0.12250000238418579, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.8029379919171333, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.265625, | |
| "rewards/xmlcount_reward_func": 1.1485625207424164, | |
| "step": 50 | |
| }, | |
| { | |
| "completion_length": 221.5625, | |
| "epoch": 4.780487804878049, | |
| "grad_norm": 42.74195098876953, | |
| "kl": 19.366400617174804, | |
| "learning_rate": 2.540482672006254e-07, | |
| "loss": 0.0194, | |
| "reward": 2.4607008695602417, | |
| "reward_std": 0.582477293908596, | |
| "rewards/concensus_correctness_reward_func": 0.06012500077486038, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.7755759283900261, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.234375, | |
| "rewards/xmlcount_reward_func": 1.0781250149011612, | |
| "step": 52 | |
| }, | |
| { | |
| "completion_length": 121.65625, | |
| "epoch": 4.975609756097561, | |
| "grad_norm": 4.044496059417725, | |
| "kl": 1.2229662016034126, | |
| "learning_rate": 2.37859444471388e-07, | |
| "loss": 0.0012, | |
| "reward": 3.0761840641498566, | |
| "reward_std": 1.7169672884047031, | |
| "rewards/concensus_correctness_reward_func": 0.6851250007748604, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.6576527766883373, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.296875, | |
| "rewards/xmlcount_reward_func": 1.1240312531590462, | |
| "step": 54 | |
| }, | |
| { | |
| "completion_length": 190.15, | |
| "epoch": 5.097560975609756, | |
| "grad_norm": 2.5054287910461426, | |
| "kl": 0.40689231753349303, | |
| "learning_rate": 2.2172154345117894e-07, | |
| "loss": 0.0003, | |
| "reward": 2.3544807910919188, | |
| "reward_std": 0.4992034614086151, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.4, | |
| "rewards/question_recreation_reward_func": 0.6489308118820191, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.175, | |
| "rewards/xmlcount_reward_func": 1.130550003051758, | |
| "step": 56 | |
| }, | |
| { | |
| "completion_length": 167.46875, | |
| "epoch": 5.2926829268292686, | |
| "grad_norm": 4.939743518829346, | |
| "kl": 1.0670354459434748, | |
| "learning_rate": 2.0570225210519433e-07, | |
| "loss": 0.0011, | |
| "reward": 2.940119907259941, | |
| "reward_std": 0.5183741468936205, | |
| "rewards/concensus_correctness_reward_func": 0.06012500077486038, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.7578699514269829, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.375, | |
| "rewards/xmlcount_reward_func": 1.1846249997615814, | |
| "step": 58 | |
| }, | |
| { | |
| "completion_length": 129.78125, | |
| "epoch": 5.487804878048781, | |
| "grad_norm": 14.262602806091309, | |
| "kl": 6.911861918866634, | |
| "learning_rate": 1.8986876090843664e-07, | |
| "loss": 0.0069, | |
| "reward": 2.512383133172989, | |
| "reward_std": 0.6689571645110846, | |
| "rewards/concensus_correctness_reward_func": 0.06012500077486038, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.7206018827855587, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.1691562682390213, | |
| "step": 60 | |
| }, | |
| { | |
| "completion_length": 153.84375, | |
| "epoch": 5.682926829268292, | |
| "grad_norm": 4.040970802307129, | |
| "kl": 1.8997416272759438, | |
| "learning_rate": 1.7428748102551234e-07, | |
| "loss": 0.0019, | |
| "reward": 4.094300732016563, | |
| "reward_std": 3.2450541853904724, | |
| "rewards/concensus_correctness_reward_func": 1.3101250007748604, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.7321133241057396, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.359375, | |
| "rewards/xmlcount_reward_func": 1.130187500268221, | |
| "step": 62 | |
| }, | |
| { | |
| "completion_length": 149.0, | |
| "epoch": 5.878048780487805, | |
| "grad_norm": 4.407651424407959, | |
| "kl": 1.1698362613096833, | |
| "learning_rate": 1.5902376575912814e-07, | |
| "loss": 0.0012, | |
| "reward": 2.2420406192541122, | |
| "reward_std": 0.5333225438371301, | |
| "rewards/concensus_correctness_reward_func": 0.0598750002682209, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.792165607213974, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.21875, | |
| "rewards/xmlcount_reward_func": 1.1087500154972076, | |
| "step": 64 | |
| }, | |
| { | |
| "completion_length": 112.15, | |
| "epoch": 6.0, | |
| "grad_norm": 3.1488583087921143, | |
| "kl": 0.7777493536472321, | |
| "learning_rate": 1.4414163643562753e-07, | |
| "loss": 0.0005, | |
| "reward": 2.53222017288208, | |
| "reward_std": 0.6459437549114228, | |
| "rewards/concensus_correctness_reward_func": 0.09580000042915345, | |
| "rewards/consensus_reward_func": 0.1, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7860701441764831, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.35, | |
| "rewards/xmlcount_reward_func": 1.2003499746322632, | |
| "step": 66 | |
| }, | |
| { | |
| "completion_length": 136.46875, | |
| "epoch": 6.195121951219512, | |
| "grad_norm": 5.8898539543151855, | |
| "kl": 1.8731475602835417, | |
| "learning_rate": 1.2970351387729872e-07, | |
| "loss": 0.0019, | |
| "reward": 2.372854396700859, | |
| "reward_std": 0.46924145889352076, | |
| "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": 0.6067919060587883, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.34375, | |
| "rewards/xmlcount_reward_func": 1.1723125129938126, | |
| "step": 68 | |
| }, | |
| { | |
| "completion_length": 162.78125, | |
| "epoch": 6.390243902439025, | |
| "grad_norm": 6.582674026489258, | |
| "kl": 1.30052063241601, | |
| "learning_rate": 1.1576995658775404e-07, | |
| "loss": 0.0013, | |
| "reward": 4.535748735070229, | |
| "reward_std": 1.4339275071397424, | |
| "rewards/concensus_correctness_reward_func": 2.05774999409914, | |
| "rewards/consensus_reward_func": 0.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.6988736353814602, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.1541250050067902, | |
| "step": 70 | |
| }, | |
| { | |
| "completion_length": 108.125, | |
| "epoch": 6.585365853658536, | |
| "grad_norm": 6.37650728225708, | |
| "kl": 0.5360646117478609, | |
| "learning_rate": 1.0239940674851941e-07, | |
| "loss": 0.0005, | |
| "reward": 3.5589722096920013, | |
| "reward_std": 1.8011039877310395, | |
| "rewards/concensus_correctness_reward_func": 0.6851250007748604, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.7731909388676286, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.2256562411785126, | |
| "step": 72 | |
| }, | |
| { | |
| "completion_length": 138.21875, | |
| "epoch": 6.780487804878049, | |
| "grad_norm": 4.734973430633545, | |
| "kl": 3.8659601393155754, | |
| "learning_rate": 8.964794509221507e-08, | |
| "loss": 0.0039, | |
| "reward": 2.692448616027832, | |
| "reward_std": 0.35131036676466465, | |
| "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": 0.8613236248493195, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.359375, | |
| "rewards/xmlcount_reward_func": 1.221750020980835, | |
| "step": 74 | |
| }, | |
| { | |
| "completion_length": 151.0625, | |
| "epoch": 6.975609756097561, | |
| "grad_norm": 5.129486560821533, | |
| "kl": 1.5537091912701726, | |
| "learning_rate": 7.756905568047392e-08, | |
| "loss": 0.0016, | |
| "reward": 2.6046862453222275, | |
| "reward_std": 0.7406165972352028, | |
| "rewards/concensus_correctness_reward_func": 0.12250000238418579, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.6871863044798374, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.1699999868869781, | |
| "step": 76 | |
| }, | |
| { | |
| "completion_length": 131.7, | |
| "epoch": 7.097560975609756, | |
| "grad_norm": 3.7079029083251953, | |
| "kl": 1.5399453818798066, | |
| "learning_rate": 6.621340157319996e-08, | |
| "loss": 0.001, | |
| "reward": 2.7136191368103026, | |
| "reward_std": 0.9075609683990479, | |
| "rewards/concensus_correctness_reward_func": 0.09620000123977661, | |
| "rewards/consensus_reward_func": 0.1, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.3, | |
| "rewards/question_recreation_reward_func": 0.7861691594123841, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.18125, | |
| "step": 78 | |
| }, | |
| { | |
| "completion_length": 181.09375, | |
| "epoch": 7.2926829268292686, | |
| "grad_norm": 6.1535162925720215, | |
| "kl": 0.573518211953342, | |
| "learning_rate": 5.5628612330087724e-08, | |
| "loss": 0.0006, | |
| "reward": 3.8459194749593735, | |
| "reward_std": 1.7336784086655825, | |
| "rewards/concensus_correctness_reward_func": 1.25, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.8142632357776165, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.34375, | |
| "rewards/xmlcount_reward_func": 1.1879062503576279, | |
| "step": 80 | |
| }, | |
| { | |
| "completion_length": 152.875, | |
| "epoch": 7.487804878048781, | |
| "grad_norm": 6.165317535400391, | |
| "kl": 2.319924622774124, | |
| "learning_rate": 4.5859084235697235e-08, | |
| "loss": 0.0023, | |
| "reward": 2.0710987001657486, | |
| "reward_std": 0.751331745646894, | |
| "rewards/concensus_correctness_reward_func": 0.06012500077486038, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.55609873495996, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.265625, | |
| "rewards/xmlcount_reward_func": 1.1267500072717667, | |
| "step": 82 | |
| }, | |
| { | |
| "completion_length": 174.9375, | |
| "epoch": 7.682926829268292, | |
| "grad_norm": 5.046776294708252, | |
| "kl": 2.245447961613536, | |
| "learning_rate": 3.6945794086007705e-08, | |
| "loss": 0.0022, | |
| "reward": 2.5292265713214874, | |
| "reward_std": 1.143988709896803, | |
| "rewards/concensus_correctness_reward_func": 0.24050000309944153, | |
| "rewards/consensus_reward_func": 0.25, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.6357265987899154, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.0905000045895576, | |
| "step": 84 | |
| }, | |
| { | |
| "completion_length": 164.0, | |
| "epoch": 7.878048780487805, | |
| "grad_norm": 3.5354819297790527, | |
| "kl": 0.5519012669101357, | |
| "learning_rate": 2.892612731749414e-08, | |
| "loss": 0.0006, | |
| "reward": 3.282635271549225, | |
| "reward_std": 1.7596494741737843, | |
| "rewards/concensus_correctness_reward_func": 0.625, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.375, | |
| "rewards/question_recreation_reward_func": 0.807010255753994, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.328125, | |
| "rewards/xmlcount_reward_func": 1.1475000083446503, | |
| "step": 86 | |
| }, | |
| { | |
| "completion_length": 108.4, | |
| "epoch": 8.0, | |
| "grad_norm": 2.0044972896575928, | |
| "kl": 0.35757209062576295, | |
| "learning_rate": 2.183372119961499e-08, | |
| "loss": 0.0002, | |
| "reward": 6.687426805496216, | |
| "reward_std": 4.642478483915329, | |
| "rewards/concensus_correctness_reward_func": 3.388399910926819, | |
| "rewards/consensus_reward_func": 0.3, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.8, | |
| "rewards/question_recreation_reward_func": 0.6740266382694244, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3, | |
| "rewards/xmlcount_reward_func": 1.225, | |
| "step": 88 | |
| }, | |
| { | |
| "completion_length": 120.59375, | |
| "epoch": 8.195121951219512, | |
| "grad_norm": 3.868396520614624, | |
| "kl": 2.700576603412628, | |
| "learning_rate": 1.5698323748414122e-08, | |
| "loss": 0.0027, | |
| "reward": 3.760663390159607, | |
| "reward_std": 2.0940339118242264, | |
| "rewards/concensus_correctness_reward_func": 0.9279374964535236, | |
| "rewards/consensus_reward_func": 0.25, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.8017571456730366, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.328125, | |
| "rewards/xmlcount_reward_func": 1.202843725681305, | |
| "step": 90 | |
| }, | |
| { | |
| "completion_length": 203.96875, | |
| "epoch": 8.390243902439025, | |
| "grad_norm": 4.034110069274902, | |
| "kl": 3.7330283680930734, | |
| "learning_rate": 1.054566895300324e-08, | |
| "loss": 0.0037, | |
| "reward": 3.24531951546669, | |
| "reward_std": 1.75903601013124, | |
| "rewards/concensus_correctness_reward_func": 0.8073750026524067, | |
| "rewards/consensus_reward_func": 0.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.6574131920933723, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.28125, | |
| "rewards/xmlcount_reward_func": 1.1242812499403954, | |
| "step": 92 | |
| }, | |
| { | |
| "completion_length": 113.84375, | |
| "epoch": 8.585365853658537, | |
| "grad_norm": 3.601546287536621, | |
| "kl": 2.1267421934753656, | |
| "learning_rate": 6.397368838268496e-09, | |
| "loss": 0.0021, | |
| "reward": 2.7754287719726562, | |
| "reward_std": 0.6228232402354479, | |
| "rewards/concensus_correctness_reward_func": 0.05999999865889549, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.8581162914633751, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.359375, | |
| "rewards/xmlcount_reward_func": 1.1854375004768372, | |
| "step": 94 | |
| }, | |
| { | |
| "completion_length": 198.03125, | |
| "epoch": 8.78048780487805, | |
| "grad_norm": 3.0875630378723145, | |
| "kl": 0.6049554403871298, | |
| "learning_rate": 3.2708228165273244e-09, | |
| "loss": 0.0006, | |
| "reward": 4.5220272690057755, | |
| "reward_std": 1.8342011701315641, | |
| "rewards/concensus_correctness_reward_func": 1.9952500015497208, | |
| "rewards/consensus_reward_func": 0.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.7617147043347359, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.28125, | |
| "rewards/xmlcount_reward_func": 1.1088124960660934, | |
| "step": 96 | |
| }, | |
| { | |
| "completion_length": 147.875, | |
| "epoch": 8.975609756097562, | |
| "grad_norm": 6.384603977203369, | |
| "kl": 2.2161214109510183, | |
| "learning_rate": 1.1791447083465133e-09, | |
| "loss": 0.0022, | |
| "reward": 2.5484085381031036, | |
| "reward_std": 0.6816056333482265, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.5684084966778755, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.375, | |
| "rewards/xmlcount_reward_func": 1.1050000041723251, | |
| "step": 98 | |
| }, | |
| { | |
| "completion_length": 105.9, | |
| "epoch": 9.097560975609756, | |
| "grad_norm": 3.4388906955718994, | |
| "kl": 0.5531518459320068, | |
| "learning_rate": 1.3110773862126667e-10, | |
| "loss": 0.0003, | |
| "reward": 2.561092567443848, | |
| "reward_std": 0.5468424066901207, | |
| "rewards/concensus_correctness_reward_func": 0.09610000252723694, | |
| "rewards/consensus_reward_func": 0.1, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.6962425768375397, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.45, | |
| "rewards/xmlcount_reward_func": 1.21875, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.097560975609756, | |
| "step": 100, | |
| "total_flos": 0.0, | |
| "train_loss": 0.0029315173596842214, | |
| "train_runtime": 554.1656, | |
| "train_samples_per_second": 2.887, | |
| "train_steps_per_second": 0.18 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |