MHGanainy's picture
MHGanainy/gpt2-xl-lora-ecthr-random-balanced-cluster-8-id-6
c23e548 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5269,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01897893338394382,
"grad_norm": 0.16455961763858795,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.4473,
"step": 100
},
{
"epoch": 0.03795786676788764,
"grad_norm": 0.15589718520641327,
"learning_rate": 4.000000000000001e-06,
"loss": 2.3958,
"step": 200
},
{
"epoch": 0.05693680015183147,
"grad_norm": 0.22491300106048584,
"learning_rate": 6e-06,
"loss": 2.4127,
"step": 300
},
{
"epoch": 0.07591573353577528,
"grad_norm": 0.27128249406814575,
"learning_rate": 8.000000000000001e-06,
"loss": 2.3425,
"step": 400
},
{
"epoch": 0.09489466691971911,
"grad_norm": 0.3409845232963562,
"learning_rate": 1e-05,
"loss": 2.3406,
"step": 500
},
{
"epoch": 0.11387360030366293,
"grad_norm": 0.4303252696990967,
"learning_rate": 1.2e-05,
"loss": 2.2827,
"step": 600
},
{
"epoch": 0.13285253368760674,
"grad_norm": 0.4239923655986786,
"learning_rate": 1.4e-05,
"loss": 2.2578,
"step": 700
},
{
"epoch": 0.15183146707155057,
"grad_norm": 0.5540084838867188,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.2406,
"step": 800
},
{
"epoch": 0.1708104004554944,
"grad_norm": 0.5286028981208801,
"learning_rate": 1.8e-05,
"loss": 2.2016,
"step": 900
},
{
"epoch": 0.18978933383943822,
"grad_norm": 0.6286925673484802,
"learning_rate": 2e-05,
"loss": 2.1954,
"step": 1000
},
{
"epoch": 0.20876826722338204,
"grad_norm": 0.6797956824302673,
"learning_rate": 1.9972934164759383e-05,
"loss": 2.1821,
"step": 1100
},
{
"epoch": 0.22774720060732587,
"grad_norm": 0.6893311142921448,
"learning_rate": 1.9891883170924986e-05,
"loss": 2.1191,
"step": 1200
},
{
"epoch": 0.2467261339912697,
"grad_norm": 0.7030719518661499,
"learning_rate": 1.9757285761065846e-05,
"loss": 2.1244,
"step": 1300
},
{
"epoch": 0.2657050673752135,
"grad_norm": 0.9822287559509277,
"learning_rate": 1.9569870533445783e-05,
"loss": 2.1247,
"step": 1400
},
{
"epoch": 0.28468400075915734,
"grad_norm": 0.7738551497459412,
"learning_rate": 1.933065199799926e-05,
"loss": 2.1051,
"step": 1500
},
{
"epoch": 0.30366293414310114,
"grad_norm": 0.7393893003463745,
"learning_rate": 1.9040925084619663e-05,
"loss": 2.1113,
"step": 1600
},
{
"epoch": 0.322641867527045,
"grad_norm": 0.9361407160758972,
"learning_rate": 1.8702258133487446e-05,
"loss": 2.0613,
"step": 1700
},
{
"epoch": 0.3416208009109888,
"grad_norm": 0.9538021087646484,
"learning_rate": 1.831648440538277e-05,
"loss": 2.0347,
"step": 1800
},
{
"epoch": 0.36059973429493264,
"grad_norm": 0.8312991261482239,
"learning_rate": 1.7885692157938646e-05,
"loss": 2.0875,
"step": 1900
},
{
"epoch": 0.37957866767887644,
"grad_norm": 0.9724030494689941,
"learning_rate": 1.7412213341553518e-05,
"loss": 2.0666,
"step": 2000
},
{
"epoch": 0.3985576010628203,
"grad_norm": 0.9147292375564575,
"learning_rate": 1.689861097615423e-05,
"loss": 2.0367,
"step": 2100
},
{
"epoch": 0.4175365344467641,
"grad_norm": 1.1803175210952759,
"learning_rate": 1.6347665277141005e-05,
"loss": 2.0376,
"step": 2200
},
{
"epoch": 0.43651546783070794,
"grad_norm": 0.9863779544830322,
"learning_rate": 1.576235860561704e-05,
"loss": 2.0362,
"step": 2300
},
{
"epoch": 0.45549440121465173,
"grad_norm": 1.0676170587539673,
"learning_rate": 1.5145859324369678e-05,
"loss": 2.0744,
"step": 2400
},
{
"epoch": 0.4744733345985956,
"grad_norm": 1.0011714696884155,
"learning_rate": 1.4501504646993358e-05,
"loss": 2.0567,
"step": 2500
},
{
"epoch": 0.4934522679825394,
"grad_norm": 1.0237438678741455,
"learning_rate": 1.3832782572994961e-05,
"loss": 2.0407,
"step": 2600
},
{
"epoch": 0.5124312013664832,
"grad_norm": 1.2096575498580933,
"learning_rate": 1.3143313006669802e-05,
"loss": 2.0454,
"step": 2700
},
{
"epoch": 0.531410134750427,
"grad_norm": 0.854215681552887,
"learning_rate": 1.2436828161955004e-05,
"loss": 2.0554,
"step": 2800
},
{
"epoch": 0.5503890681343708,
"grad_norm": 0.9747099876403809,
"learning_rate": 1.171715235933197e-05,
"loss": 1.998,
"step": 2900
},
{
"epoch": 0.5693680015183147,
"grad_norm": 0.9982984066009521,
"learning_rate": 1.0988181324140792e-05,
"loss": 1.9904,
"step": 3000
},
{
"epoch": 0.5883469349022585,
"grad_norm": 0.7807527184486389,
"learning_rate": 1.0253861098368203e-05,
"loss": 2.0082,
"step": 3100
},
{
"epoch": 0.6073258682862023,
"grad_norm": 0.8988199234008789,
"learning_rate": 9.518166680063126e-06,
"loss": 1.9718,
"step": 3200
},
{
"epoch": 0.6263048016701461,
"grad_norm": 1.0487923622131348,
"learning_rate": 8.785080506008221e-06,
"loss": 2.0602,
"step": 3300
},
{
"epoch": 0.64528373505409,
"grad_norm": 0.796579122543335,
"learning_rate": 8.058570894124317e-06,
"loss": 2.0266,
"step": 3400
},
{
"epoch": 0.6642626684380338,
"grad_norm": 0.7757595181465149,
"learning_rate": 7.342570562302606e-06,
"loss": 2.0555,
"step": 3500
},
{
"epoch": 0.6832416018219776,
"grad_norm": 1.0452457666397095,
"learning_rate": 6.640955339945751e-06,
"loss": 2.0494,
"step": 3600
},
{
"epoch": 0.7022205352059214,
"grad_norm": 0.9034073352813721,
"learning_rate": 5.957523187455876e-06,
"loss": 2.007,
"step": 3700
},
{
"epoch": 0.7211994685898653,
"grad_norm": 1.0185625553131104,
"learning_rate": 5.29597363724047e-06,
"loss": 2.0148,
"step": 3800
},
{
"epoch": 0.740178401973809,
"grad_norm": 0.6561883687973022,
"learning_rate": 4.659887767525457e-06,
"loss": 1.991,
"step": 3900
},
{
"epoch": 0.7591573353577529,
"grad_norm": 1.013913631439209,
"learning_rate": 4.052708817380557e-06,
"loss": 1.9972,
"step": 4000
},
{
"epoch": 0.7781362687416967,
"grad_norm": 0.8857009410858154,
"learning_rate": 3.477723547891012e-06,
"loss": 1.9966,
"step": 4100
},
{
"epoch": 0.7971152021256406,
"grad_norm": 1.1049866676330566,
"learning_rate": 2.9380444503707715e-06,
"loss": 2.0037,
"step": 4200
},
{
"epoch": 0.8160941355095843,
"grad_norm": 1.0857770442962646,
"learning_rate": 2.4365928979271005e-06,
"loss": 1.9777,
"step": 4300
},
{
"epoch": 0.8350730688935282,
"grad_norm": 0.9005129933357239,
"learning_rate": 1.976083331579909e-06,
"loss": 2.0582,
"step": 4400
},
{
"epoch": 0.854052002277472,
"grad_norm": 1.1704425811767578,
"learning_rate": 1.559008566539103e-06,
"loss": 2.03,
"step": 4500
},
{
"epoch": 0.8730309356614159,
"grad_norm": 0.8802852630615234,
"learning_rate": 1.1876262981793984e-06,
"loss": 2.005,
"step": 4600
},
{
"epoch": 0.8920098690453596,
"grad_norm": 1.1852850914001465,
"learning_rate": 8.639468807581397e-07,
"loss": 2.0452,
"step": 4700
},
{
"epoch": 0.9109888024293035,
"grad_norm": 0.8399674892425537,
"learning_rate": 5.897224450318684e-07,
"loss": 2.0223,
"step": 4800
},
{
"epoch": 0.9299677358132473,
"grad_norm": 1.1396406888961792,
"learning_rate": 3.664374136798465e-07,
"loss": 1.9713,
"step": 4900
},
{
"epoch": 0.9489466691971912,
"grad_norm": 1.135856032371521,
"learning_rate": 1.9530046587612927e-07,
"loss": 1.9986,
"step": 5000
},
{
"epoch": 0.9679256025811349,
"grad_norm": 0.9097400307655334,
"learning_rate": 7.72379945072832e-08,
"loss": 2.0123,
"step": 5100
},
{
"epoch": 0.9869045359650788,
"grad_norm": 0.9359187483787537,
"learning_rate": 1.2889091452942259e-08,
"loss": 1.9949,
"step": 5200
},
{
"epoch": 1.0,
"step": 5269,
"total_flos": 9.597350805504e+16,
"train_loss": 2.090950048406474,
"train_runtime": 846.2233,
"train_samples_per_second": 12.453,
"train_steps_per_second": 6.226
}
],
"logging_steps": 100,
"max_steps": 5269,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 9.597350805504e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}