yfMcjUwtgy/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-shaggy_dextrous_pheasant
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
0722b57293005bb9cfa942a76a23f62efb134f2d
Qwen2.5-0.5B-Instruct-Gensy…/trainer_state.json
ModelHub XC 0722b57293 初始化项目，由ModelHub XC社区提供模型 
Model: yfMcjUwtgy/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-shaggy_dextrous_pheasant
Source: Original Platform
2026-05-28 05:20:17 +08:00

234 lines
7.6 KiB
JSON
Raw Blame History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.666666666666667,
"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": 4.875,
"epoch": 0.6666666666666666,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 5e-07,
"loss": 0.0,
"reward": 0.5985739265743177,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.3127500116825104,
"rewards/consensus_reward_func": 0.25,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.03582396401907317,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 2
},
{
"completion_length": 4.8125,
"epoch": 1.3333333333333333,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 4.864543104251586e-07,
"loss": 0.0,
"reward": 0.8712688222294673,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.46912501752376556,
"rewards/consensus_reward_func": 0.375,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.027143868734128773,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 4
},
{
"completion_length": 4.9375,
"epoch": 2.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 4.472851273490984e-07,
"loss": 0.0,
"reward": 0.3170446450531017,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.1563750058412552,
"rewards/consensus_reward_func": 0.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.03566965411300771,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 6
},
{
"completion_length": 4.8125,
"epoch": 2.6666666666666665,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.867370395306068e-07,
"loss": 0.0,
"reward": 0.883054888836341,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.46912501752376556,
"rewards/consensus_reward_func": 0.375,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.03892993534100242,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 8
},
{
"completion_length": 4.9375,
"epoch": 3.3333333333333335,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.1137137178519977e-07,
"loss": 0.0,
"reward": 0.3093900743406266,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.1563750058412552,
"rewards/consensus_reward_func": 0.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.028015083400532603,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 10
},
{
"completion_length": 4.875,
"epoch": 4.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 2.2935516363191693e-07,
"loss": 0.0,
"reward": 0.5944424306799192,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.3127500116825104,
"rewards/consensus_reward_func": 0.25,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.03169246812467463,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 12
},
{
"completion_length": 4.9375,
"epoch": 4.666666666666667,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 1.4957614383675767e-07,
"loss": 0.0,
"reward": 0.3156137435871642,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.1563750058412552,
"rewards/consensus_reward_func": 0.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.03423876172746532,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 14
},
{
"completion_length": 4.75,
"epoch": 5.333333333333333,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 8.067960709356478e-08,
"loss": 0.0,
"reward": 1.1601923258858733,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.6255000233650208,
"rewards/consensus_reward_func": 0.5,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.034692391694989055,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 16
},
{
"completion_length": 4.9375,
"epoch": 6.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.013156219837776e-08,
"loss": 0.0,
"reward": 0.3110813243838493,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.1563750058412552,
"rewards/consensus_reward_func": 0.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.029706333443755284,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 18
},
{
"completion_length": 4.875,
"epoch": 6.666666666666667,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.4096741493194193e-09,
"loss": 0.0,
"reward": 0.592974122177111,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 0.3127500116825104,
"rewards/consensus_reward_func": 0.25,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.0302241493773181,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0,
"step": 20
},
{
"epoch": 6.666666666666667,
"step": 20,
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 1345.2593,
"train_samples_per_second": 0.238,
"train_steps_per_second": 0.015
}
],
"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
}
Reference in New Issue View Git Blame Copy Permalink