sychonix/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-foxy_squeaky_llama
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: sychonix/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-foxy_squeaky_llama
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-06 11:45:12 +08:00
commit 666a091c39
16 changed files with 152073 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

233
trainer_state.json Normal file
View File

@@ -0,0 +1,233 @@
{
"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": 297.5,
"epoch": 0.1,
"grad_norm": 9.432661056518555,
"kl": 0.0,
"learning_rate": 4.965903258506806e-07,
"loss": 0.0,
"reward": 3.730669429525733,
"reward_std": 0.4485799211252015,
"rewards/concensus_correctness_reward_func": 1.031874991953373,
"rewards/consensus_reward_func": 1.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.6952631510794163,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.21875,
"rewards/xmlcount_reward_func": 0.6597812538966537,
"step": 2
},
{
"completion_length": 192.65625,
"epoch": 0.2,
"grad_norm": 11.113174438476562,
"kl": 0.022198006248800084,
"learning_rate": 4.698684378016222e-07,
"loss": 0.0,
"reward": 6.275569885969162,
"reward_std": 0.6035314256441779,
"rewards/concensus_correctness_reward_func": 1.6479999981820583,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9113823771476746,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.375,
"rewards/xmlcount_reward_func": 1.2161874994635582,
"step": 4
},
{
"completion_length": 210.125,
"epoch": 0.3,
"grad_norm": 12.231167793273926,
"kl": 0.038603271124884486,
"learning_rate": 4.193203929064353e-07,
"loss": 0.0,
"reward": 6.966040924191475,
"reward_std": 1.2862182207463775,
"rewards/concensus_correctness_reward_func": 2.31531248614192,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.8696972597390413,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.421875,
"rewards/xmlcount_reward_func": 1.2341562509536743,
"step": 6
},
{
"completion_length": 194.28125,
"epoch": 0.4,
"grad_norm": 12.217857360839844,
"kl": 0.10087808885145932,
"learning_rate": 3.5042385616324236e-07,
"loss": 0.0001,
"reward": 6.28543047606945,
"reward_std": 0.40540230748592876,
"rewards/concensus_correctness_reward_func": 1.7122499970719218,
"rewards/consensus_reward_func": 1.75,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.3125,
"rewards/question_recreation_reward_func": 0.9208992421627045,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.375,
"rewards/xmlcount_reward_func": 1.214781254529953,
"step": 8
},
{
"completion_length": 168.125,
"epoch": 0.5,
"grad_norm": 10.86254596710205,
"kl": 0.10376646637450904,
"learning_rate": 2.706448363680831e-07,
"loss": 0.0001,
"reward": 6.665328234434128,
"reward_std": 1.7247313684783876,
"rewards/concensus_correctness_reward_func": 2.0438749976456165,
"rewards/consensus_reward_func": 1.625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.5625,
"rewards/question_recreation_reward_func": 0.8991720359772444,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.390625,
"rewards/xmlcount_reward_func": 1.1441562473773956,
"step": 10
},
{
"completion_length": 154.5625,
"epoch": 0.6,
"grad_norm": 12.82181167602539,
"kl": 72.64050495019183,
"learning_rate": 1.886286282148002e-07,
"loss": 0.0726,
"reward": 5.921443969011307,
"reward_std": 0.554531274465262,
"rewards/concensus_correctness_reward_func": 1.5525624938309193,
"rewards/consensus_reward_func": 1.875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.8766939491033554,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.421875,
"rewards/xmlcount_reward_func": 1.1953125,
"step": 12
},
{
"completion_length": 183.0625,
"epoch": 0.7,
"grad_norm": 14.391100883483887,
"kl": 0.3917471282184124,
"learning_rate": 1.1326296046939333e-07,
"loss": 0.0004,
"reward": 6.325738251209259,
"reward_std": 0.6296158700133674,
"rewards/concensus_correctness_reward_func": 1.902312494814396,
"rewards/consensus_reward_func": 1.8125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.1875,
"rewards/question_recreation_reward_func": 0.8708007447421551,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.34375,
"rewards/xmlcount_reward_func": 1.2088750004768372,
"step": 14
},
{
"completion_length": 179.71875,
"epoch": 0.8,
"grad_norm": 10.600848197937012,
"kl": 183.85747765313135,
"learning_rate": 5.271487265090163e-08,
"loss": 0.1838,
"reward": 7.16494807600975,
"reward_std": 0.8043542211962631,
"rewards/concensus_correctness_reward_func": 2.4575625024735928,
"rewards/consensus_reward_func": 1.9375,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9225105680525303,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.390625,
"rewards/xmlcount_reward_func": 1.206750001758337,
"step": 16
},
{
"completion_length": 180.46875,
"epoch": 0.9,
"grad_norm": 14.025286674499512,
"kl": 1.1980386194190942,
"learning_rate": 1.3545689574841341e-08,
"loss": 0.0012,
"reward": 6.26318684220314,
"reward_std": 0.7861611984917545,
"rewards/concensus_correctness_reward_func": 1.818812508136034,
"rewards/consensus_reward_func": 1.625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.375,
"rewards/question_recreation_reward_func": 0.8933743871748447,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.390625,
"rewards/xmlcount_reward_func": 1.160375002771616,
"step": 18
},
{
"completion_length": 171.03125,
"epoch": 1.0,
"grad_norm": 182.83685302734375,
"kl": 8.031980507308617,
"learning_rate": 0.0,
"loss": 0.008,
"reward": 6.142421722412109,
"reward_std": 1.0077090224949643,
"rewards/concensus_correctness_reward_func": 1.6790625005960464,
"rewards/consensus_reward_func": 1.6875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.94345298781991,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.390625,
"rewards/xmlcount_reward_func": 1.191781248897314,
"step": 20
},
{
"epoch": 1.0,
"step": 20,
"total_flos": 0.0,
"train_loss": 0.026637533630128017,
"train_runtime": 129.5179,
"train_samples_per_second": 2.471,
"train_steps_per_second": 0.154
}
],
"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
}