{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 3.027027027027027,
"eval_steps": 25,
"global_step": 42,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07207207207207207,
"grad_norm": 0.23242872953414917,
"learning_rate": 5e-05,
"loss": 10.3706,
"step": 1
},
{
"epoch": 0.07207207207207207,
"eval_loss": NaN,
"eval_runtime": 0.1032,
"eval_samples_per_second": 484.269,
"eval_steps_per_second": 125.91,
"step": 1
},
{
"epoch": 0.14414414414414414,
"grad_norm": 0.27956777811050415,
"learning_rate": 0.0001,
"loss": 10.3809,
"step": 2
},
{
"epoch": 0.21621621621621623,
"grad_norm": 0.33814385533332825,
"learning_rate": 9.986128001799077e-05,
"loss": 10.3776,
"step": 3
},
{
"epoch": 0.2882882882882883,
"grad_norm": 0.22053034603595734,
"learning_rate": 9.94459753267812e-05,
"loss": 10.3718,
"step": 4
},
{
"epoch": 0.36036036036036034,
"grad_norm": 0.2625846862792969,
"learning_rate": 9.875664641789545e-05,
"loss": 10.3714,
"step": 5
},
{
"epoch": 0.43243243243243246,
"grad_norm": 0.3214924931526184,
"learning_rate": 9.779754323328192e-05,
"loss": 10.3845,
"step": 6
},
{
"epoch": 0.5045045045045045,
"grad_norm": 0.26409900188446045,
"learning_rate": 9.657457896300791e-05,
"loss": 10.3931,
"step": 7
},
{
"epoch": 0.5765765765765766,
"grad_norm": 0.2600726783275604,
"learning_rate": 9.509529358847655e-05,
"loss": 10.384,
"step": 8
},
{
"epoch": 0.6486486486486487,
"grad_norm": 0.30863380432128906,
"learning_rate": 9.336880739593416e-05,
"loss": 10.3812,
"step": 9
},
{
"epoch": 0.7207207207207207,
"grad_norm": 0.31988584995269775,
"learning_rate": 9.140576474687264e-05,
"loss": 10.3635,
"step": 10
},
{
"epoch": 0.7927927927927928,
"grad_norm": 0.23925259709358215,
"learning_rate": 8.921826845200139e-05,
"loss": 10.3874,
"step": 11
},
{
"epoch": 0.8648648648648649,
"grad_norm": 0.3147229254245758,
"learning_rate": 8.681980515339464e-05,
"loss": 10.3739,
"step": 12
},
{
"epoch": 0.9369369369369369,
"grad_norm": 0.4201517105102539,
"learning_rate": 8.422516217485826e-05,
"loss": 10.3673,
"step": 13
},
{
"epoch": 1.009009009009009,
"grad_norm": 0.33698132634162903,
"learning_rate": 8.14503363531613e-05,
"loss": 11.8408,
"step": 14
},
{
"epoch": 1.0810810810810811,
"grad_norm": 0.2550658881664276,
"learning_rate": 7.85124354122177e-05,
"loss": 9.1756,
"step": 15
},
{
"epoch": 1.1531531531531531,
"grad_norm": 0.40897005796432495,
"learning_rate": 7.542957248827961e-05,
"loss": 12.3049,
"step": 16
},
{
"epoch": 1.2252252252252251,
"grad_norm": 0.3496151864528656,
"learning_rate": 7.222075445642904e-05,
"loss": 9.059,
"step": 17
},
{
"epoch": 1.2972972972972974,
"grad_norm": 0.3040536940097809,
"learning_rate": 6.890576474687263e-05,
"loss": 11.035,
"step": 18
},
{
"epoch": 1.3693693693693694,
"grad_norm": 0.320978045463562,
"learning_rate": 6.550504137351576e-05,
"loss": 9.6682,
"step": 19
},
{
"epoch": 1.4414414414414414,
"grad_norm": 0.4239856004714966,
"learning_rate": 6.203955092681039e-05,
"loss": 10.5403,
"step": 20
},
{
"epoch": 1.5135135135135136,
"grad_norm": 0.34272250533103943,
"learning_rate": 5.8530659307753036e-05,
"loss": 10.5671,
"step": 21
},
{
"epoch": 1.5855855855855856,
"grad_norm": 0.3536415100097656,
"learning_rate": 5.500000000000001e-05,
"loss": 10.1439,
"step": 22
},
{
"epoch": 1.6576576576576576,
"grad_norm": 0.4582449793815613,
"learning_rate": 5.1469340692246995e-05,
"loss": 11.4783,
"step": 23
},
{
"epoch": 1.7297297297297298,
"grad_norm": 0.36027440428733826,
"learning_rate": 4.7960449073189606e-05,
"loss": 9.6784,
"step": 24
},
{
"epoch": 1.8018018018018018,
"grad_norm": 0.34310826659202576,
"learning_rate": 4.4494958626484276e-05,
"loss": 9.7889,
"step": 25
},
{
"epoch": 1.8018018018018018,
"eval_loss": NaN,
"eval_runtime": 0.1168,
"eval_samples_per_second": 428.002,
"eval_steps_per_second": 111.28,
"step": 25
},
{
"epoch": 1.8738738738738738,
"grad_norm": 0.5108070373535156,
"learning_rate": 4.109423525312738e-05,
"loss": 11.2485,
"step": 26
},
{
"epoch": 1.945945945945946,
"grad_norm": 0.5605173110961914,
"learning_rate": 3.777924554357096e-05,
"loss": 10.3144,
"step": 27
},
{
"epoch": 2.018018018018018,
"grad_norm": 0.4780227541923523,
"learning_rate": 3.45704275117204e-05,
"loss": 11.2554,
"step": 28
},
{
"epoch": 2.09009009009009,
"grad_norm": 0.3900972306728363,
"learning_rate": 3.1487564587782306e-05,
"loss": 10.069,
"step": 29
},
{
"epoch": 2.1621621621621623,
"grad_norm": 0.4860075116157532,
"learning_rate": 2.854966364683872e-05,
"loss": 11.2109,
"step": 30
},
{
"epoch": 2.234234234234234,
"grad_norm": 0.4599916636943817,
"learning_rate": 2.577483782514174e-05,
"loss": 8.562,
"step": 31
},
{
"epoch": 2.3063063063063063,
"grad_norm": 0.3811488151550293,
"learning_rate": 2.3180194846605367e-05,
"loss": 10.8037,
"step": 32
},
{
"epoch": 2.3783783783783785,
"grad_norm": 0.5661867260932922,
"learning_rate": 2.0781731547998614e-05,
"loss": 12.446,
"step": 33
},
{
"epoch": 2.4504504504504503,
"grad_norm": 0.5369315147399902,
"learning_rate": 1.8594235253127375e-05,
"loss": 9.2962,
"step": 34
},
{
"epoch": 2.5225225225225225,
"grad_norm": 0.41405609250068665,
"learning_rate": 1.6631192604065855e-05,
"loss": 10.2131,
"step": 35
},
{
"epoch": 2.5945945945945947,
"grad_norm": 0.43550166487693787,
"learning_rate": 1.490470641152345e-05,
"loss": 10.1199,
"step": 36
},
{
"epoch": 2.6666666666666665,
"grad_norm": 0.5510601997375488,
"learning_rate": 1.3425421036992098e-05,
"loss": 10.9105,
"step": 37
},
{
"epoch": 2.7387387387387387,
"grad_norm": 0.44297927618026733,
"learning_rate": 1.2202456766718093e-05,
"loss": 10.5097,
"step": 38
},
{
"epoch": 2.810810810810811,
"grad_norm": 0.4119100868701935,
"learning_rate": 1.1243353582104556e-05,
"loss": 9.4872,
"step": 39
},
{
"epoch": 2.8828828828828827,
"grad_norm": 0.5762305855751038,
"learning_rate": 1.0554024673218807e-05,
"loss": 11.9048,
"step": 40
},
{
"epoch": 2.954954954954955,
"grad_norm": 0.524325966835022,
"learning_rate": 1.0138719982009242e-05,
"loss": 10.0337,
"step": 41
},
{
"epoch": 3.027027027027027,
"grad_norm": 0.5072345733642578,
"learning_rate": 1e-05,
"loss": 10.4668,
"step": 42
}
],
"logging_steps": 1,
"max_steps": 42,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 35925170061312.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}