bubbleboy14/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-clawed_aquatic_trout
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
Qwen2.5-0.5B-Instruct-Gensy…/trainer_state.json
ModelHub XC f97c48098f 初始化项目，由ModelHub XC社区提供模型 
Model: bubbleboy14/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-clawed_aquatic_trout
Source: Original Platform
2026-05-22 10:16:18 +08:00

234 lines
8.1 KiB
JSON
Raw Permalink Blame History

{
"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,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"completion_length": 224.65625,
"epoch": 0.1,
"grad_norm": 59.62317657470703,
"kl": 0.0,
"learning_rate": 5e-07,
"loss": -0.0,
"reward": 3.6561741777695715,
"reward_std": 0.6636041095043765,
"rewards/concensus_correctness_reward_func": 1.0819374918937683,
"rewards/consensus_reward_func": 1.0625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.6466429487627465,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.046875,
"rewards/xmlcount_reward_func": 0.6932187350466847,
"step": 2
},
{
"completion_length": 178.40625,
"epoch": 0.2,
"grad_norm": 137.7733154296875,
"kl": 4.928524229326285,
"learning_rate": 4.864543104251586e-07,
"loss": 0.0049,
"reward": 5.914174601435661,
"reward_std": 0.6810445789305959,
"rewards/concensus_correctness_reward_func": 1.8054999746382236,
"rewards/consensus_reward_func": 1.625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.8789871465414762,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.234375,
"rewards/xmlcount_reward_func": 1.1203124932944775,
"step": 4
},
{
"completion_length": 204.78125,
"epoch": 0.3,
"grad_norm": 59.5778923034668,
"kl": 908572.1892776145,
"learning_rate": 4.472851273490984e-07,
"loss": 908.5719,
"reward": 5.643219739198685,
"reward_std": 0.653852166607976,
"rewards/concensus_correctness_reward_func": 1.6814374923706055,
"rewards/consensus_reward_func": 1.75,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.873594731092453,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.125,
"rewards/xmlcount_reward_func": 1.0881875045597553,
"step": 6
},
{
"completion_length": 182.75,
"epoch": 0.4,
"grad_norm": 56.64072799682617,
"kl": 5.842966626398265,
"learning_rate": 3.867370395306068e-07,
"loss": 0.0059,
"reward": 6.156492739915848,
"reward_std": 0.4257756451097521,
"rewards/concensus_correctness_reward_func": 2.047500006854534,
"rewards/consensus_reward_func": 1.75,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.1875,
"rewards/question_recreation_reward_func": 0.8617740124464035,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.203125,
"rewards/xmlcount_reward_func": 1.1065937541425228,
"step": 8
},
{
"completion_length": 153.8125,
"epoch": 0.5,
"grad_norm": 594.0848388671875,
"kl": 31.691469689714722,
"learning_rate": 3.1137137178519977e-07,
"loss": 0.0317,
"reward": 6.4002659767866135,
"reward_std": 0.7855745942797512,
"rewards/concensus_correctness_reward_func": 1.923249989748001,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.3125,
"rewards/question_recreation_reward_func": 0.9359847418963909,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.1875,
"rewards/xmlcount_reward_func": 1.1660312414169312,
"step": 10
},
{
"completion_length": 158.3125,
"epoch": 0.6,
"grad_norm": 212805.625,
"kl": 6287.006970646675,
"learning_rate": 2.2935516363191693e-07,
"loss": 6.287,
"reward": 6.026919096708298,
"reward_std": 0.41921286657452583,
"rewards/concensus_correctness_reward_func": 1.8424374796450138,
"rewards/consensus_reward_func": 1.8125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.8207003455609083,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.25,
"rewards/xmlcount_reward_func": 1.176281251013279,
"step": 12
},
{
"completion_length": 170.46875,
"epoch": 0.7,
"grad_norm": 9543.67578125,
"kl": 226.30980851501226,
"learning_rate": 1.4957614383675767e-07,
"loss": 0.2263,
"reward": 6.866821527481079,
"reward_std": 0.5666069679864449,
"rewards/concensus_correctness_reward_func": 2.2304999977350235,
"rewards/consensus_reward_func": 1.9375,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.4375,
"rewards/question_recreation_reward_func": 0.9430402554571629,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.171875,
"rewards/xmlcount_reward_func": 1.1464062482118607,
"step": 14
},
{
"completion_length": 154.40625,
"epoch": 0.8,
"grad_norm": 5537198.5,
"kl": 102431.51840936067,
"learning_rate": 8.067960709356478e-08,
"loss": 102.4315,
"reward": 6.177701383829117,
"reward_std": 0.5931377406523097,
"rewards/concensus_correctness_reward_func": 1.8484999909996986,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.1875,
"rewards/question_recreation_reward_func": 0.9565138779580593,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.15625,
"rewards/xmlcount_reward_func": 1.153937492519617,
"step": 16
},
{
"completion_length": 159.71875,
"epoch": 0.9,
"grad_norm": 394692.5625,
"kl": 6945.127022614703,
"learning_rate": 3.013156219837776e-08,
"loss": 6.9451,
"reward": 6.108283966779709,
"reward_std": 1.6806388410623185,
"rewards/concensus_correctness_reward_func": 2.3686874844133854,
"rewards/consensus_reward_func": 1.5625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.8324402524158359,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.15625,
"rewards/xmlcount_reward_func": 1.0634062550961971,
"step": 18
},
{
"completion_length": 146.25,
"epoch": 1.0,
"grad_norm": 2865.775390625,
"kl": 79.60710120433941,
"learning_rate": 3.4096741493194193e-09,
"loss": 0.0796,
"reward": 6.899527698755264,
"reward_std": 0.2347854689724045,
"rewards/concensus_correctness_reward_func": 2.1056249886751175,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.4375,
"rewards/question_recreation_reward_func": 0.9580277539789677,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.234375,
"rewards/xmlcount_reward_func": 1.1640000008046627,
"step": 20
},
{
"epoch": 1.0,
"step": 20,
"total_flos": 0.0,
"train_loss": 102.4583978814073,
"train_runtime": 161.7569,
"train_samples_per_second": 1.978,
"train_steps_per_second": 0.124
}
],
"logging_steps": 2,
"max_steps": 20,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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