vanshs613/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-soaring_dappled_hippo
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
a429fa20bce873efc25066d3a4a21bd5ccda7a13
Qwen2.5-0.5B-Instruct-Gensy…/trainer_state.json
ModelHub XC a429fa20bc 初始化项目，由ModelHub XC社区提供模型 
Model: vanshs613/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-soaring_dappled_hippo
Source: Original Platform
2026-09-03 07:54:18 +08:00

234 lines
8.1 KiB
JSON
Raw 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": 257.4375,
"epoch": 0.1,
"grad_norm": 42.85694885253906,
"kl": 0.0,
"learning_rate": 4.965903258506806e-07,
"loss": -0.0,
"reward": 3.9454924832098186,
"reward_std": 0.42792381439357996,
"rewards/concensus_correctness_reward_func": 1.140250001102686,
"rewards/consensus_reward_func": 1.0625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.6025862665846944,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.234375,
"rewards/xmlcount_reward_func": 0.7807812502142042,
"step": 2
},
{
"completion_length": 128.9375,
"epoch": 0.2,
"grad_norm": 29.040935516357422,
"kl": 0.5335751844104379,
"learning_rate": 4.698684378016222e-07,
"loss": 0.0005,
"reward": 6.755986243486404,
"reward_std": 0.613882417572313,
"rewards/concensus_correctness_reward_func": 2.0146249905228615,
"rewards/consensus_reward_func": 1.8125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.3125,
"rewards/question_recreation_reward_func": 0.9619550406932831,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.4375,
"rewards/xmlcount_reward_func": 1.2169062495231628,
"step": 4
},
{
"completion_length": 158.21875,
"epoch": 0.3,
"grad_norm": 106.23600006103516,
"kl": 5.85334307141602,
"learning_rate": 4.193203929064353e-07,
"loss": 0.0059,
"reward": 6.254412055015564,
"reward_std": 0.22973583391285501,
"rewards/concensus_correctness_reward_func": 1.7211249731481075,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.9672870673239231,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.359375,
"rewards/xmlcount_reward_func": 1.2066249996423721,
"step": 6
},
{
"completion_length": 132.40625,
"epoch": 0.4,
"grad_norm": 908.352294921875,
"kl": 31.59648933983408,
"learning_rate": 3.5042385616324236e-07,
"loss": 0.0316,
"reward": 6.495247453451157,
"reward_std": 0.32210062145168195,
"rewards/concensus_correctness_reward_func": 1.9354375074617565,
"rewards/consensus_reward_func": 1.8125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9586224667727947,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.390625,
"rewards/xmlcount_reward_func": 1.148062501102686,
"step": 8
},
{
"completion_length": 127.25,
"epoch": 0.5,
"grad_norm": 28.126314163208008,
"kl": 7.050176987890154,
"learning_rate": 2.706448363680831e-07,
"loss": 0.007,
"reward": 7.01416951417923,
"reward_std": 0.1968466019607149,
"rewards/concensus_correctness_reward_func": 2.168624997138977,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9477632120251656,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.4375,
"rewards/xmlcount_reward_func": 1.2102812454104424,
"step": 10
},
{
"completion_length": 133.96875,
"epoch": 0.6,
"grad_norm": 36.5333366394043,
"kl": 4.253114338440355,
"learning_rate": 1.886286282148002e-07,
"loss": 0.0043,
"reward": 5.7655471712350845,
"reward_std": 0.4229842454078607,
"rewards/concensus_correctness_reward_func": 1.6347499825060368,
"rewards/consensus_reward_func": 1.75,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.8757346980273724,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.359375,
"rewards/xmlcount_reward_func": 1.145687498152256,
"step": 12
},
{
"completion_length": 140.5,
"epoch": 0.7,
"grad_norm": 21.523326873779297,
"kl": 6.09225378325209,
"learning_rate": 1.1326296046939333e-07,
"loss": 0.0061,
"reward": 6.578316897153854,
"reward_std": 0.8162273239577189,
"rewards/concensus_correctness_reward_func": 1.9833124913275242,
"rewards/consensus_reward_func": 1.8125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9454732052981853,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.421875,
"rewards/xmlcount_reward_func": 1.1651562489569187,
"step": 14
},
{
"completion_length": 132.71875,
"epoch": 0.8,
"grad_norm": 209618192.0,
"kl": 11914987.063571038,
"learning_rate": 5.271487265090163e-08,
"loss": 11914.9883,
"reward": 6.235501676797867,
"reward_std": 0.6787745207548141,
"rewards/concensus_correctness_reward_func": 1.7827499955892563,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0625,
"rewards/question_recreation_reward_func": 0.9308142438530922,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.390625,
"rewards/xmlcount_reward_func": 1.1938124969601631,
"step": 16
},
{
"completion_length": 137.46875,
"epoch": 0.9,
"grad_norm": 56.26324462890625,
"kl": 8.98876704229042,
"learning_rate": 1.3545689574841341e-08,
"loss": 0.009,
"reward": 5.684117838740349,
"reward_std": 0.903291186405113,
"rewards/concensus_correctness_reward_func": 1.6847499907016754,
"rewards/consensus_reward_func": 1.5625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0625,
"rewards/question_recreation_reward_func": 0.9103366248309612,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.328125,
"rewards/xmlcount_reward_func": 1.1359062530100346,
"step": 18
},
{
"completion_length": 130.0,
"epoch": 1.0,
"grad_norm": 21.837852478027344,
"kl": 30.217751567950472,
"learning_rate": 0.0,
"loss": 0.0302,
"reward": 6.407116562128067,
"reward_std": 0.8622763247403782,
"rewards/concensus_correctness_reward_func": 1.8597499802708626,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.926741586998105,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.421875,
"rewards/xmlcount_reward_func": 1.1987500004470348,
"step": 20
},
{
"epoch": 1.0,
"step": 20,
"total_flos": 0.0,
"train_loss": 1191.5082876126398,
"train_runtime": 82.3672,
"train_samples_per_second": 3.885,
"train_steps_per_second": 0.243
}
],
"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