wmln/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-winged_large_owl
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: wmln/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-winged_large_owl
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-29 06:20:18 +08:00
commit 900f0aca35
15 changed files with 152059 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": 404.125,
"epoch": 0.1,
"grad_norm": 288.32666015625,
"kl": 0.0,
"learning_rate": 4.965903258506806e-07,
"loss": -0.0,
"reward": 4.772882015211508,
"reward_std": 2.1168917804025114,
"rewards/concensus_correctness_reward_func": 2.4540000036358833,
"rewards/consensus_reward_func": 1.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.426413350738585,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.046875,
"rewards/xmlcount_reward_func": 0.5955937458202243,
"step": 2
},
{
"completion_length": 410.34375,
"epoch": 0.2,
"grad_norm": 130.4783477783203,
"kl": 0.6658651278121397,
"learning_rate": 4.698684378016222e-07,
"loss": 0.0007,
"reward": 5.01509964466095,
"reward_std": 1.1631509650032967,
"rewards/concensus_correctness_reward_func": 1.5051249898970127,
"rewards/consensus_reward_func": 1.5,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.1875,
"rewards/question_recreation_reward_func": 0.561662147170864,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.1875,
"rewards/xmlcount_reward_func": 1.0733124986290932,
"step": 4
},
{
"completion_length": 534.71875,
"epoch": 0.3,
"grad_norm": 1552.3057861328125,
"kl": 58509.23574514594,
"learning_rate": 4.193203929064353e-07,
"loss": 58.5092,
"reward": 3.916074428707361,
"reward_std": 0.4645578390918672,
"rewards/concensus_correctness_reward_func": 1.2064999863505363,
"rewards/consensus_reward_func": 1.0625,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.1875,
"rewards/question_recreation_reward_func": 0.5143557151313871,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.078125,
"rewards/xmlcount_reward_func": 0.867093744687736,
"step": 6
},
{
"completion_length": 630.65625,
"epoch": 0.4,
"grad_norm": 1007.0711669921875,
"kl": 7.474598820823303,
"learning_rate": 3.5042385616324236e-07,
"loss": 0.0075,
"reward": 4.540738439653069,
"reward_std": 1.1158053932449548,
"rewards/concensus_correctness_reward_func": 1.5829999782145023,
"rewards/consensus_reward_func": 1.5,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0625,
"rewards/question_recreation_reward_func": 0.46458223345689476,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.09375,
"rewards/xmlcount_reward_func": 0.8369062561541796,
"step": 8
},
{
"completion_length": 394.09375,
"epoch": 0.5,
"grad_norm": 3072.351318359375,
"kl": 77.25303288397845,
"learning_rate": 2.706448363680831e-07,
"loss": 0.0773,
"reward": 5.141709133982658,
"reward_std": 1.8181919632479548,
"rewards/concensus_correctness_reward_func": 1.751937486231327,
"rewards/consensus_reward_func": 1.5,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.1875,
"rewards/question_recreation_reward_func": 0.595521615119651,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.140625,
"rewards/xmlcount_reward_func": 0.9661250039935112,
"step": 10
},
{
"completion_length": 473.34375,
"epoch": 0.6,
"grad_norm": 13994405.0,
"kl": 770595.972182367,
"learning_rate": 1.886286282148002e-07,
"loss": 770.5959,
"reward": 4.850805774331093,
"reward_std": 1.5860967373591848,
"rewards/concensus_correctness_reward_func": 1.5959374979138374,
"rewards/consensus_reward_func": 1.5,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.5817432389594615,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.125,
"rewards/xmlcount_reward_func": 0.9231249988079071,
"step": 12
},
{
"completion_length": 282.84375,
"epoch": 0.7,
"grad_norm": 462.19268798828125,
"kl": 13.494472346035764,
"learning_rate": 1.1326296046939333e-07,
"loss": 0.0135,
"reward": 5.08140666782856,
"reward_std": 1.355736733006779,
"rewards/concensus_correctness_reward_func": 1.8004374913871288,
"rewards/consensus_reward_func": 1.5,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.5359691851772368,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.109375,
"rewards/xmlcount_reward_func": 1.0106250047683716,
"step": 14
},
{
"completion_length": 433.15625,
"epoch": 0.8,
"grad_norm": 158.03749084472656,
"kl": 4.058037928305566,
"learning_rate": 5.271487265090163e-08,
"loss": 0.0041,
"reward": 6.036646455526352,
"reward_std": 1.2633073259785306,
"rewards/concensus_correctness_reward_func": 2.0585625022649765,
"rewards/consensus_reward_func": 1.75,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.375,
"rewards/question_recreation_reward_func": 0.6229589302092791,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.140625,
"rewards/xmlcount_reward_func": 1.0894999951124191,
"step": 16
},
{
"completion_length": 454.96875,
"epoch": 0.9,
"grad_norm": 41603817275392.0,
"kl": 426082304003.2566,
"learning_rate": 1.3545689574841341e-08,
"loss": 426082336.0,
"reward": 5.0858291164040565,
"reward_std": 0.7348921145312488,
"rewards/concensus_correctness_reward_func": 1.73599998280406,
"rewards/consensus_reward_func": 1.6875,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.44764173682779074,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.21875,
"rewards/xmlcount_reward_func": 0.9959375001490116,
"step": 18
},
{
"completion_length": 528.59375,
"epoch": 1.0,
"grad_norm": 24.856689453125,
"kl": 5.308833171497099,
"learning_rate": 0.0,
"loss": 0.0053,
"reward": 5.657240346074104,
"reward_std": 1.8041395582258701,
"rewards/concensus_correctness_reward_func": 1.989687506109476,
"rewards/consensus_reward_func": 1.75,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.523896655999124,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.140625,
"rewards/xmlcount_reward_func": 1.0030312538146973,
"step": 20
},
{
"epoch": 1.0,
"step": 20,
"total_flos": 0.0,
"train_loss": 42608316.52134633,
"train_runtime": 347.9451,
"train_samples_per_second": 0.92,
"train_steps_per_second": 0.057
}
],
"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
}