Model: XlHoWcLGeuQ/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-burrowing_voracious_bear Source: Original Platform
234 lines
7.8 KiB
JSON
234 lines
7.8 KiB
JSON
{
|
|
"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_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"completion_length": 4.84375,
|
|
"epoch": 0.5714285714285714,
|
|
"grad_norm": 0.0,
|
|
"kl": 0.0,
|
|
"learning_rate": 5e-07,
|
|
"loss": 0.0,
|
|
"reward": 4.339183732867241,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.293749988079071,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.045433690887875855,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 2
|
|
},
|
|
{
|
|
"completion_length": 4.875,
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.0,
|
|
"kl": 0.0,
|
|
"learning_rate": 4.864543104251586e-07,
|
|
"loss": 0.0,
|
|
"reward": 4.804217894872029,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.7550000150998435,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.049217987223528326,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 4
|
|
},
|
|
{
|
|
"completion_length": 4.90625,
|
|
"epoch": 1.5714285714285714,
|
|
"grad_norm": 0.0,
|
|
"kl": 0.0,
|
|
"learning_rate": 4.472851273490984e-07,
|
|
"loss": 0.0,
|
|
"reward": 4.591571539640427,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.5454999953508377,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.04607159286388196,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 6
|
|
},
|
|
{
|
|
"completion_length": 4.958333333333333,
|
|
"epoch": 2.0,
|
|
"grad_norm": 0.0,
|
|
"kl": 0.0,
|
|
"learning_rate": 3.867370395306068e-07,
|
|
"loss": 0.0,
|
|
"reward": 4.467700819174449,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.419333338737488,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.04836745125552019,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 8
|
|
},
|
|
{
|
|
"completion_length": 4.8125,
|
|
"epoch": 2.571428571428571,
|
|
"grad_norm": 1.103065727647845e-07,
|
|
"kl": 0.0,
|
|
"learning_rate": 3.1137137178519977e-07,
|
|
"loss": 0.0,
|
|
"reward": 4.5833591520786285,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.544749990105629,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.038609186274698004,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"completion_length": 4.958333333333333,
|
|
"epoch": 3.0,
|
|
"grad_norm": 0.00027077828417532146,
|
|
"kl": 3.912548284764246e-06,
|
|
"learning_rate": 2.2935516363191693e-07,
|
|
"loss": 0.0,
|
|
"reward": 4.478650669256846,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.4203333457310996,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.05831732670776546,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 12
|
|
},
|
|
{
|
|
"completion_length": 4.90625,
|
|
"epoch": 3.571428571428571,
|
|
"grad_norm": 0.0040213121101260185,
|
|
"kl": 0.0005166871660620131,
|
|
"learning_rate": 1.4957614383675767e-07,
|
|
"loss": 0.0,
|
|
"reward": 4.469981402158737,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.4215000048279762,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.04848141656839289,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 14
|
|
},
|
|
{
|
|
"completion_length": 4.791666666666667,
|
|
"epoch": 4.0,
|
|
"grad_norm": 0.002309721428900957,
|
|
"kl": 0.01312202648659877,
|
|
"learning_rate": 8.067960709356478e-08,
|
|
"loss": 0.0,
|
|
"reward": 4.629821002483368,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.5846666594346366,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.04515435298283895,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 16
|
|
},
|
|
{
|
|
"completion_length": 4.875,
|
|
"epoch": 4.571428571428571,
|
|
"grad_norm": 0.003946145065128803,
|
|
"kl": 0.00024977270566783893,
|
|
"learning_rate": 3.013156219837776e-08,
|
|
"loss": 0.0,
|
|
"reward": 4.725700348615646,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.6704999953508377,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.05520035425433889,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 18
|
|
},
|
|
{
|
|
"completion_length": 5.0,
|
|
"epoch": 5.0,
|
|
"grad_norm": 0.00013875184231437743,
|
|
"kl": 0.00012967785560391576,
|
|
"learning_rate": 3.4096741493194193e-09,
|
|
"loss": 0.0,
|
|
"reward": 4.288862407207489,
|
|
"reward_std": 0.0,
|
|
"rewards/concensus_correctness_reward_func": 2.2526666720708213,
|
|
"rewards/consensus_reward_func": 2.0,
|
|
"rewards/cumulative_reward_2": 0.0,
|
|
"rewards/final_correctness_reward_func": 0.0,
|
|
"rewards/question_recreation_reward_func": 0.036195769401577614,
|
|
"rewards/soft_format_reward_func": 0.0,
|
|
"rewards/strict_format_reward_func": 0.0,
|
|
"rewards/xmlcount_reward_func": 0.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 5.0,
|
|
"step": 20,
|
|
"total_flos": 0.0,
|
|
"train_loss": 1.0708173929341314e-06,
|
|
"train_runtime": 1770.9442,
|
|
"train_samples_per_second": 0.181,
|
|
"train_steps_per_second": 0.011
|
|
}
|
|
],
|
|
"logging_steps": 2,
|
|
"max_steps": 20,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 7,
|
|
"save_steps": 25,
|
|
"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": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|