Hugging Face's logo

romero-p
/
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lumbering_grazing_antelope

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
rl-swarm
grpo
gensyn
I am lumbering grazing antelope
unsloth
trl
genrl-swarm
I am lumbering_grazing_antelope
conversational
text-generation-inference
Model card Files Community
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lumbering_grazing_antelope / trainer_state.json
romero-p's picture
romero-p
End of training
8016244 verified
raw
history blame contribute delete
8.3 kB
 {
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.7272727272727275,
"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": 403.75,
"epoch": 0.7272727272727273,
"grad_norm": 3.970888376235962,
"kl": 0.005167215786059387,
"learning_rate": 4.965903258506806e-07,
"loss": 0.0,
"reward": 0.22169073624536395,
"reward_std": 0.25420983415097,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.18103448837064207,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.0406562490388751,
"step": 2
},
{
"completion_length": 261.39285714285717,
"epoch": 1.3636363636363638,
"grad_norm": 2.4483261108398438,
"kl": 0.0020418226236610542,
"learning_rate": 4.698684378016222e-07,
"loss": 0.0,
"reward": 0.2050272130540439,
"reward_std": 0.15303353978587048,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.21884864036526,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": -0.013821429439953395,
"step": 4
},
{
"completion_length": 534.4642857142857,
"epoch": 2.0,
"grad_norm": 1.7611721754074097,
"kl": 0.0022382470488082618,
"learning_rate": 4.193203929064353e-07,
"loss": 0.0,
"reward": 0.0809648505278996,
"reward_std": 0.2677970698901585,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.11578627303242683,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": -0.03482142782637051,
"step": 6
},
{
"completion_length": 418.3125,
"epoch": 2.7272727272727275,
"grad_norm": 3.1874539852142334,
"kl": 0.0010583282964944374,
"learning_rate": 3.5042385616324236e-07,
"loss": 0.0,
"reward": 0.20330325327813625,
"reward_std": 0.14862288581207395,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.136990754166618,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.06631250027567148,
"step": 8
},
{
"completion_length": 491.17857142857144,
"epoch": 3.3636363636363638,
"grad_norm": 1.3593432903289795,
"kl": 0.0009767063727070177,
"learning_rate": 2.706448363680831e-07,
"loss": 0.0,
"reward": 0.2885110822639295,
"reward_std": 0.3179171798484666,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.24361823073455266,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.04489285711731229,
"step": 10
},
{
"completion_length": 446.75,
"epoch": 4.0,
"grad_norm": 7.3384690284729,
"kl": 0.005608834392790284,
"learning_rate": 1.886286282148002e-07,
"loss": 0.0,
"reward": 0.1894594750234059,
"reward_std": 0.1330836960779769,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.17763804750783102,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.01182142857994352,
"step": 12
},
{
"completion_length": 528.78125,
"epoch": 4.7272727272727275,
"grad_norm": 1.7135764360427856,
"kl": 0.008763544930843636,
"learning_rate": 1.1326296046939333e-07,
"loss": 0.0,
"reward": 0.26850552298128605,
"reward_std": 0.3617645651102066,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.18450552131980658,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.08399999886751175,
"step": 14
},
{
"completion_length": 530.2142857142857,
"epoch": 5.363636363636363,
"grad_norm": 1.8459399938583374,
"kl": 0.0011343328348760093,
"learning_rate": 5.271487265090163e-08,
"loss": 0.0,
"reward": 0.10405687774930682,
"reward_std": 0.5933887256043298,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.276485444179603,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": -0.1724285696234022,
"step": 16
},
{
"completion_length": 333.7142857142857,
"epoch": 6.0,
"grad_norm": 19.159759521484375,
"kl": 0.004357862751930952,
"learning_rate": 1.3545689574841341e-08,
"loss": 0.0,
"reward": 0.1733016637819154,
"reward_std": 0.3896802259343011,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.2131588054554803,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": -0.039857140609196255,
"step": 18
},
{
"completion_length": 466.09375,
"epoch": 6.7272727272727275,
"grad_norm": 1.175288438796997,
"kl": 0.001101651112549007,
"learning_rate": 0.0,
"loss": 0.0,
"reward": 0.14554962702095509,
"reward_std": 0.16441974096233025,
"rewards/concensus_correctness_reward_func": 0.0,
"rewards/consensus_reward_func": 0.0,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.0,
"rewards/question_recreation_reward_func": 0.11711212806403637,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.02843749988824129,
"step": 20
},
{
"epoch": 6.7272727272727275,
"step": 20,
"total_flos": 0.0,
"train_loss": 3.0343267155785726e-06,
"train_runtime": 855.5581,
"train_samples_per_second": 0.374,
"train_steps_per_second": 0.023
}
],
"logging_steps": 2,
"max_steps": 20,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"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": 4,
"trial_name": null,
"trial_params": null
}