Dombilii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-yapping_dormant_chameleon
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: Dombilii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-yapping_dormant_chameleon
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-23 15:26:09 +08:00
commit 2fc2df2f28
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": 110.75,
"epoch": 0.1,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 5e-07,
"loss": 0.0,
"reward": 6.9197907745838165,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.296249993145466,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.375,
"rewards/question_recreation_reward_func": 0.9985408559441566,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.25,
"step": 2
},
{
"completion_length": 97.9375,
"epoch": 0.2,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 4.864543104251586e-07,
"loss": 0.0,
"reward": 6.529550611972809,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.169499985873699,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9381756756920367,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.171875,
"step": 4
},
{
"completion_length": 92.5,
"epoch": 0.3,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 4.472851273490984e-07,
"loss": 0.0,
"reward": 6.515597179532051,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.2962499856948853,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.8755971881037112,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.09375,
"step": 6
},
{
"completion_length": 105.25,
"epoch": 0.4,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.867370395306068e-07,
"loss": 0.0,
"reward": 7.031029492616653,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.421250008046627,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.5,
"rewards/question_recreation_reward_func": 0.9379045307578053,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.171875,
"step": 8
},
{
"completion_length": 104.375,
"epoch": 0.5,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.1137137178519977e-07,
"loss": 0.0,
"reward": 6.9214999079704285,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.296500012278557,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.375,
"rewards/question_recreation_reward_func": 1.0,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.25,
"step": 10
},
{
"completion_length": 98.3125,
"epoch": 0.6,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 2.2935516363191693e-07,
"loss": 0.0,
"reward": 6.530187487602234,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.170499972999096,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9378124999930151,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.171875,
"step": 12
},
{
"completion_length": 98.78125,
"epoch": 0.7,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 1.4957614383675767e-07,
"loss": 0.0,
"reward": 6.7810072004795074,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.295750007033348,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.375,
"rewards/question_recreation_reward_func": 0.9383823529351503,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.171875,
"step": 14
},
{
"completion_length": 88.5625,
"epoch": 0.8,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 8.067960709356478e-08,
"loss": 0.0,
"reward": 6.015406250953674,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.045999988913536,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.8756563392817043,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.09375,
"step": 16
},
{
"completion_length": 95.1875,
"epoch": 0.9,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.013156219837776e-08,
"loss": 0.0,
"reward": 6.531657084822655,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.1719999983906746,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.9377821670495905,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.171875,
"step": 18
},
{
"completion_length": 88.25,
"epoch": 1.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.4096741493194193e-09,
"loss": 0.0,
"reward": 7.139007061719894,
"reward_std": 0.0,
"rewards/concensus_correctness_reward_func": 2.5447500124573708,
"rewards/consensus_reward_func": 2.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.625,
"rewards/question_recreation_reward_func": 0.8755071678460808,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 1.09375,
"step": 20
},
{
"epoch": 1.0,
"step": 20,
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 3190.4054,
"train_samples_per_second": 0.1,
"train_steps_per_second": 0.006
}
],
"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
}