|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 237, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.004219409282700422, |
|
"grad_norm": 41.47472723630441, |
|
"learning_rate": 1.2499999999999999e-05, |
|
"loss": 2.7746, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02109704641350211, |
|
"grad_norm": 64.04925382439093, |
|
"learning_rate": 6.25e-05, |
|
"loss": 7.0206, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.04219409282700422, |
|
"grad_norm": 31.695867233164076, |
|
"learning_rate": 0.000125, |
|
"loss": 2.0729, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.06329113924050633, |
|
"grad_norm": 20.697061646205608, |
|
"learning_rate": 0.00018749999999999998, |
|
"loss": 2.3708, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.08438818565400844, |
|
"grad_norm": 27.19753629081583, |
|
"learning_rate": 0.00025, |
|
"loss": 2.0771, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.10548523206751055, |
|
"grad_norm": 98.00456381942149, |
|
"learning_rate": 0.0002999836847426398, |
|
"loss": 4.1945, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.12658227848101267, |
|
"grad_norm": 182.51493263483027, |
|
"learning_rate": 0.0002994130233112417, |
|
"loss": 3.4014, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.14767932489451477, |
|
"grad_norm": 11.535478461037668, |
|
"learning_rate": 0.00029803014471122853, |
|
"loss": 2.4622, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.16877637130801687, |
|
"grad_norm": 20.197984273278912, |
|
"learning_rate": 0.00029584256634447164, |
|
"loss": 2.6132, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.189873417721519, |
|
"grad_norm": 8.178205900726194, |
|
"learning_rate": 0.0002928621800037197, |
|
"loss": 1.9102, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.2109704641350211, |
|
"grad_norm": 5.9959330455646125, |
|
"learning_rate": 0.00028910518722817866, |
|
"loss": 1.7519, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.2320675105485232, |
|
"grad_norm": 13.868140556663864, |
|
"learning_rate": 0.00028459201123108015, |
|
"loss": 1.7839, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.25316455696202533, |
|
"grad_norm": 8.017800813910466, |
|
"learning_rate": 0.00027934718587800417, |
|
"loss": 1.6271, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.2742616033755274, |
|
"grad_norm": 5.37043737910495, |
|
"learning_rate": 0.0002733992223194766, |
|
"loss": 1.5652, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.29535864978902954, |
|
"grad_norm": 3.3275774087311523, |
|
"learning_rate": 0.00026678045400283336, |
|
"loss": 1.5245, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.31645569620253167, |
|
"grad_norm": 4.741642465345151, |
|
"learning_rate": 0.0002595268609058751, |
|
"loss": 1.5238, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.33755274261603374, |
|
"grad_norm": 4.030676855228214, |
|
"learning_rate": 0.00025167787394778763, |
|
"loss": 1.5316, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.35864978902953587, |
|
"grad_norm": 2.119168421995465, |
|
"learning_rate": 0.000243276160640561, |
|
"loss": 1.4865, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.379746835443038, |
|
"grad_norm": 9.504914395443073, |
|
"learning_rate": 0.0002343673931461171, |
|
"loss": 1.4966, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.4008438818565401, |
|
"grad_norm": 1.9138438030380622, |
|
"learning_rate": 0.000225, |
|
"loss": 1.5385, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.4219409282700422, |
|
"grad_norm": 2.0250123306044228, |
|
"learning_rate": 0.0002152249028512724, |
|
"loss": 1.4467, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.4430379746835443, |
|
"grad_norm": 5.253723621821196, |
|
"learning_rate": 0.0002050952396497135, |
|
"loss": 1.4458, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.4641350210970464, |
|
"grad_norm": 1.667081359954707, |
|
"learning_rate": 0.00019466607578508832, |
|
"loss": 1.4039, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.48523206751054854, |
|
"grad_norm": 1.612910217878065, |
|
"learning_rate": 0.00018399410474875, |
|
"loss": 1.3915, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.5063291139240507, |
|
"grad_norm": 4.664851099721208, |
|
"learning_rate": 0.00017313733994479531, |
|
"loss": 1.3946, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.5274261603375527, |
|
"grad_norm": 1.1333666368766908, |
|
"learning_rate": 0.00016215479932610397, |
|
"loss": 1.3759, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.5485232067510548, |
|
"grad_norm": 46.39351482577546, |
|
"learning_rate": 0.00015110618456959686, |
|
"loss": 1.3596, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.569620253164557, |
|
"grad_norm": 11.304078659755062, |
|
"learning_rate": 0.00014005155653473443, |
|
"loss": 1.3708, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.5907172995780591, |
|
"grad_norm": 1.4112479369616122, |
|
"learning_rate": 0.00012905100876947907, |
|
"loss": 1.3954, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.6118143459915611, |
|
"grad_norm": 4.386921961578911, |
|
"learning_rate": 0.00011816434083856155, |
|
"loss": 1.3064, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.6329113924050633, |
|
"grad_norm": 1.2097887430832492, |
|
"learning_rate": 0.00010745073324985548, |
|
"loss": 1.3082, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.6540084388185654, |
|
"grad_norm": 1.1759289220096156, |
|
"learning_rate": 9.696842574597847e-05, |
|
"loss": 1.2311, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.6751054852320675, |
|
"grad_norm": 2.762333419837543, |
|
"learning_rate": 8.677440070994279e-05, |
|
"loss": 1.2588, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.6962025316455697, |
|
"grad_norm": 0.8634167427320883, |
|
"learning_rate": 7.692407340588055e-05, |
|
"loss": 1.1888, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.7172995780590717, |
|
"grad_norm": 2.2322735412619386, |
|
"learning_rate": 6.747099073871015e-05, |
|
"loss": 1.2047, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.7383966244725738, |
|
"grad_norm": 0.7808932928409826, |
|
"learning_rate": 5.8466540170303925e-05, |
|
"loss": 1.1594, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.759493670886076, |
|
"grad_norm": 0.7823146836939375, |
|
"learning_rate": 4.995967037450238e-05, |
|
"loss": 1.1763, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.7805907172995781, |
|
"grad_norm": 0.7925457205036505, |
|
"learning_rate": 4.199662514951142e-05, |
|
"loss": 1.1291, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.8016877637130801, |
|
"grad_norm": 0.8477428122185438, |
|
"learning_rate": 3.4620692034146904e-05, |
|
"loss": 1.1162, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.8227848101265823, |
|
"grad_norm": 0.7180062181554933, |
|
"learning_rate": 2.7871966994463884e-05, |
|
"loss": 1.1061, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.8438818565400844, |
|
"grad_norm": 0.6932161729089131, |
|
"learning_rate": 2.1787136459944886e-05, |
|
"loss": 1.1264, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.8649789029535865, |
|
"grad_norm": 0.7413528530014878, |
|
"learning_rate": 1.639927789411174e-05, |
|
"loss": 1.1001, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.8860759493670886, |
|
"grad_norm": 0.7062510216168646, |
|
"learning_rate": 1.1737679983668258e-05, |
|
"loss": 1.0853, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.9071729957805907, |
|
"grad_norm": 0.6294764868696124, |
|
"learning_rate": 7.8276834236364e-06, |
|
"loss": 1.0527, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.9282700421940928, |
|
"grad_norm": 0.6759047685020939, |
|
"learning_rate": 4.690543163985771e-06, |
|
"loss": 1.0758, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.9493670886075949, |
|
"grad_norm": 1.3620865902651844, |
|
"learning_rate": 2.343312866591163e-06, |
|
"loss": 1.0805, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.9704641350210971, |
|
"grad_norm": 0.6839144968477266, |
|
"learning_rate": 7.987522006165426e-07, |
|
"loss": 1.0588, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.9915611814345991, |
|
"grad_norm": 1.1867918696725697, |
|
"learning_rate": 6.525748027244593e-08, |
|
"loss": 1.0692, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 2.265784978866577, |
|
"eval_runtime": 2.2863, |
|
"eval_samples_per_second": 0.875, |
|
"eval_steps_per_second": 0.437, |
|
"step": 237 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 237, |
|
"total_flos": 12379572142080.0, |
|
"train_loss": 1.644804019968218, |
|
"train_runtime": 4500.3652, |
|
"train_samples_per_second": 1.682, |
|
"train_steps_per_second": 0.053 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 237, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 12379572142080.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|