|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.2781954887218046, |
|
"eval_steps": 500, |
|
"global_step": 510, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02506265664160401, |
|
"grad_norm": 1.0692139863967896, |
|
"learning_rate": 2.5e-06, |
|
"loss": 4.188, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.05012531328320802, |
|
"grad_norm": 1.1046545505523682, |
|
"learning_rate": 5e-06, |
|
"loss": 4.1657, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.07518796992481203, |
|
"grad_norm": 1.2392791509628296, |
|
"learning_rate": 7.500000000000001e-06, |
|
"loss": 4.1205, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.10025062656641603, |
|
"grad_norm": 1.4656062126159668, |
|
"learning_rate": 1e-05, |
|
"loss": 4.0411, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.12531328320802004, |
|
"grad_norm": 1.5381596088409424, |
|
"learning_rate": 9.722222222222223e-06, |
|
"loss": 3.8527, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.15037593984962405, |
|
"grad_norm": 1.220762014389038, |
|
"learning_rate": 9.444444444444445e-06, |
|
"loss": 3.6254, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.17543859649122806, |
|
"grad_norm": 1.0793465375900269, |
|
"learning_rate": 9.166666666666666e-06, |
|
"loss": 3.4326, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.20050125313283207, |
|
"grad_norm": 0.9771835803985596, |
|
"learning_rate": 8.888888888888888e-06, |
|
"loss": 3.2486, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.22556390977443608, |
|
"grad_norm": 0.9600415825843811, |
|
"learning_rate": 8.611111111111112e-06, |
|
"loss": 3.0867, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.2506265664160401, |
|
"grad_norm": 0.789818525314331, |
|
"learning_rate": 8.333333333333334e-06, |
|
"loss": 2.9344, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.2756892230576441, |
|
"grad_norm": 0.7392975091934204, |
|
"learning_rate": 9.365079365079366e-06, |
|
"loss": 2.8172, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.3007518796992481, |
|
"grad_norm": 0.7141592502593994, |
|
"learning_rate": 9.206349206349207e-06, |
|
"loss": 2.6949, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.3258145363408521, |
|
"grad_norm": 0.6999505162239075, |
|
"learning_rate": 9.047619047619049e-06, |
|
"loss": 2.5975, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.3508771929824561, |
|
"grad_norm": 0.7100343704223633, |
|
"learning_rate": 8.888888888888888e-06, |
|
"loss": 2.4933, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.37593984962406013, |
|
"grad_norm": 0.7077847719192505, |
|
"learning_rate": 8.730158730158731e-06, |
|
"loss": 2.3849, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.40100250626566414, |
|
"grad_norm": 0.7145490050315857, |
|
"learning_rate": 8.571428571428571e-06, |
|
"loss": 2.2824, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.42606516290726815, |
|
"grad_norm": 0.7200222611427307, |
|
"learning_rate": 8.412698412698414e-06, |
|
"loss": 2.1871, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.45112781954887216, |
|
"grad_norm": 0.7174162864685059, |
|
"learning_rate": 8.253968253968254e-06, |
|
"loss": 2.0916, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.47619047619047616, |
|
"grad_norm": 0.7255663871765137, |
|
"learning_rate": 8.095238095238097e-06, |
|
"loss": 1.9964, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.5012531328320802, |
|
"grad_norm": 0.7197927236557007, |
|
"learning_rate": 7.936507936507936e-06, |
|
"loss": 1.8927, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.5263157894736842, |
|
"grad_norm": 0.7157548666000366, |
|
"learning_rate": 7.77777777777778e-06, |
|
"loss": 1.8088, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.5513784461152882, |
|
"grad_norm": 0.7149109840393066, |
|
"learning_rate": 7.61904761904762e-06, |
|
"loss": 1.7166, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.5764411027568922, |
|
"grad_norm": 0.7100406289100647, |
|
"learning_rate": 7.460317460317461e-06, |
|
"loss": 1.643, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.6015037593984962, |
|
"grad_norm": 0.6912670135498047, |
|
"learning_rate": 7.301587301587301e-06, |
|
"loss": 1.5751, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.6265664160401002, |
|
"grad_norm": 0.6892037987709045, |
|
"learning_rate": 7.1428571428571436e-06, |
|
"loss": 1.4972, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.6516290726817042, |
|
"grad_norm": 0.6863360404968262, |
|
"learning_rate": 6.984126984126984e-06, |
|
"loss": 1.4356, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.6766917293233082, |
|
"grad_norm": 0.6862374544143677, |
|
"learning_rate": 6.825396825396826e-06, |
|
"loss": 1.36, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.7017543859649122, |
|
"grad_norm": 0.7181079387664795, |
|
"learning_rate": 6.666666666666667e-06, |
|
"loss": 1.3035, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.7268170426065163, |
|
"grad_norm": 0.7799757719039917, |
|
"learning_rate": 6.507936507936509e-06, |
|
"loss": 1.2459, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.7518796992481203, |
|
"grad_norm": 0.8159253001213074, |
|
"learning_rate": 6.349206349206349e-06, |
|
"loss": 1.1798, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.7769423558897243, |
|
"grad_norm": 0.745711088180542, |
|
"learning_rate": 6.1904761904761914e-06, |
|
"loss": 1.1132, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.8020050125313283, |
|
"grad_norm": 0.7495912909507751, |
|
"learning_rate": 6.031746031746032e-06, |
|
"loss": 1.0668, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.8270676691729323, |
|
"grad_norm": 0.7342067360877991, |
|
"learning_rate": 5.873015873015874e-06, |
|
"loss": 1.0187, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.8521303258145363, |
|
"grad_norm": 0.7345426082611084, |
|
"learning_rate": 5.7142857142857145e-06, |
|
"loss": 0.987, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.8771929824561403, |
|
"grad_norm": 0.7322160601615906, |
|
"learning_rate": 5.555555555555557e-06, |
|
"loss": 0.9476, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.9022556390977443, |
|
"grad_norm": 0.7495856881141663, |
|
"learning_rate": 5.396825396825397e-06, |
|
"loss": 0.9219, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.9273182957393483, |
|
"grad_norm": 0.7894755005836487, |
|
"learning_rate": 5.2380952380952384e-06, |
|
"loss": 0.8988, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.9523809523809523, |
|
"grad_norm": 0.8114584684371948, |
|
"learning_rate": 5.07936507936508e-06, |
|
"loss": 0.8827, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.9774436090225563, |
|
"grad_norm": 0.8420091271400452, |
|
"learning_rate": 4.920634920634921e-06, |
|
"loss": 0.8516, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.0025062656641603, |
|
"grad_norm": 0.8762117624282837, |
|
"learning_rate": 4.761904761904762e-06, |
|
"loss": 0.8343, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.0275689223057645, |
|
"grad_norm": 0.8553557991981506, |
|
"learning_rate": 4.603174603174604e-06, |
|
"loss": 0.8124, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.0526315789473684, |
|
"grad_norm": 0.7959764003753662, |
|
"learning_rate": 4.444444444444444e-06, |
|
"loss": 0.8053, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.0776942355889725, |
|
"grad_norm": 0.6741518378257751, |
|
"learning_rate": 4.2857142857142855e-06, |
|
"loss": 0.7804, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.1027568922305764, |
|
"grad_norm": 0.554545521736145, |
|
"learning_rate": 4.126984126984127e-06, |
|
"loss": 0.7657, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.1278195488721805, |
|
"grad_norm": 0.48400139808654785, |
|
"learning_rate": 3.968253968253968e-06, |
|
"loss": 0.7531, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.1528822055137844, |
|
"grad_norm": 0.47219163179397583, |
|
"learning_rate": 3.80952380952381e-06, |
|
"loss": 0.7444, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.1779448621553885, |
|
"grad_norm": 0.4428965151309967, |
|
"learning_rate": 3.6507936507936507e-06, |
|
"loss": 0.7259, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.2030075187969924, |
|
"grad_norm": 0.45144426822662354, |
|
"learning_rate": 3.492063492063492e-06, |
|
"loss": 0.717, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.2280701754385965, |
|
"grad_norm": 0.41748014092445374, |
|
"learning_rate": 3.3333333333333333e-06, |
|
"loss": 0.7078, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.2531328320802004, |
|
"grad_norm": 0.4345729947090149, |
|
"learning_rate": 3.1746031746031746e-06, |
|
"loss": 0.7044, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.2781954887218046, |
|
"grad_norm": 0.42705973982810974, |
|
"learning_rate": 3.015873015873016e-06, |
|
"loss": 0.6964, |
|
"step": 510 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 700, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 10, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5.5000090384290816e+17, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|