| { | |
| "best_metric": 0.048522137105464935, | |
| "best_model_checkpoint": "./xlam_lora_new_ete_over_size_3epoch_multi_full_eng/checkpoint-342", | |
| "epoch": 0.6646826601882782, | |
| "eval_steps": 171, | |
| "global_step": 342, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019435165502581234, | |
| "grad_norm": 0.2028260976076126, | |
| "learning_rate": 3.205128205128205e-06, | |
| "loss": 0.0883, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03887033100516247, | |
| "grad_norm": 0.16199472546577454, | |
| "learning_rate": 6.41025641025641e-06, | |
| "loss": 0.0862, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0583054965077437, | |
| "grad_norm": 0.10014229267835617, | |
| "learning_rate": 9.615384615384616e-06, | |
| "loss": 0.0785, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07774066201032494, | |
| "grad_norm": 0.07943801581859589, | |
| "learning_rate": 1.282051282051282e-05, | |
| "loss": 0.0772, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09717582751290617, | |
| "grad_norm": 0.11369317024946213, | |
| "learning_rate": 1.602564102564103e-05, | |
| "loss": 0.0649, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1166109930154874, | |
| "grad_norm": 0.10264527052640915, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 0.0686, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13604615851806864, | |
| "grad_norm": 0.08583803474903107, | |
| "learning_rate": 2.2435897435897437e-05, | |
| "loss": 0.0657, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15548132402064987, | |
| "grad_norm": 0.09326862543821335, | |
| "learning_rate": 2.4999884878368972e-05, | |
| "loss": 0.0605, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1749164895232311, | |
| "grad_norm": 0.09622487425804138, | |
| "learning_rate": 2.4995855843928913e-05, | |
| "loss": 0.0617, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19435165502581234, | |
| "grad_norm": 0.10855123400688171, | |
| "learning_rate": 2.4986072848240374e-05, | |
| "loss": 0.0548, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21378682052839357, | |
| "grad_norm": 0.12510105967521667, | |
| "learning_rate": 2.4970540396075083e-05, | |
| "loss": 0.0545, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2332219860309748, | |
| "grad_norm": 0.11628145724534988, | |
| "learning_rate": 2.494926563965445e-05, | |
| "loss": 0.0601, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.252657151533556, | |
| "grad_norm": 0.12050613015890121, | |
| "learning_rate": 2.4922258375356232e-05, | |
| "loss": 0.0585, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2720923170361373, | |
| "grad_norm": 0.08949285745620728, | |
| "learning_rate": 2.488953103920354e-05, | |
| "loss": 0.0477, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2915274825387185, | |
| "grad_norm": 0.14706853032112122, | |
| "learning_rate": 2.4851098701138466e-05, | |
| "loss": 0.0555, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31096264804129975, | |
| "grad_norm": 0.13029147684574127, | |
| "learning_rate": 2.4806979058082832e-05, | |
| "loss": 0.0493, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.330397813543881, | |
| "grad_norm": 0.1321103274822235, | |
| "learning_rate": 2.475719242578929e-05, | |
| "loss": 0.0547, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3323413300941391, | |
| "eval_loss": 0.054034121334552765, | |
| "eval_runtime": 172.2024, | |
| "eval_samples_per_second": 5.029, | |
| "eval_steps_per_second": 5.029, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.3498329790464622, | |
| "grad_norm": 0.14103983342647552, | |
| "learning_rate": 2.470176172948652e-05, | |
| "loss": 0.0522, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.36926814454904344, | |
| "grad_norm": 0.14120739698410034, | |
| "learning_rate": 2.4640712493322894e-05, | |
| "loss": 0.0501, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3887033100516247, | |
| "grad_norm": 0.1301490068435669, | |
| "learning_rate": 2.4574072828613354e-05, | |
| "loss": 0.0492, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4081384755542059, | |
| "grad_norm": 0.1606156975030899, | |
| "learning_rate": 2.450187342089502e-05, | |
| "loss": 0.0488, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.42757364105678713, | |
| "grad_norm": 0.1623048037290573, | |
| "learning_rate": 2.442414751579744e-05, | |
| "loss": 0.0459, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44700880655936837, | |
| "grad_norm": 0.1424696147441864, | |
| "learning_rate": 2.434093090373396e-05, | |
| "loss": 0.0441, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4664439720619496, | |
| "grad_norm": 0.13980570435523987, | |
| "learning_rate": 2.4252261903421375e-05, | |
| "loss": 0.0483, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4858791375645308, | |
| "grad_norm": 0.17693087458610535, | |
| "learning_rate": 2.415818134423528e-05, | |
| "loss": 0.0451, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.505314303067112, | |
| "grad_norm": 0.18210634589195251, | |
| "learning_rate": 2.405873254740942e-05, | |
| "loss": 0.0466, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5247494685696933, | |
| "grad_norm": 0.1527709811925888, | |
| "learning_rate": 2.395396130608756e-05, | |
| "loss": 0.0488, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5441846340722746, | |
| "grad_norm": 0.15795762836933136, | |
| "learning_rate": 2.3843915864237143e-05, | |
| "loss": 0.0448, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5636197995748558, | |
| "grad_norm": 0.15495383739471436, | |
| "learning_rate": 2.3728646894434413e-05, | |
| "loss": 0.047, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.583054965077437, | |
| "grad_norm": 0.17630279064178467, | |
| "learning_rate": 2.3608207474531236e-05, | |
| "loss": 0.0429, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6024901305800182, | |
| "grad_norm": 0.17523537576198578, | |
| "learning_rate": 2.3482653063214356e-05, | |
| "loss": 0.0473, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6219252960825995, | |
| "grad_norm": 0.1995943933725357, | |
| "learning_rate": 2.3352041474468373e-05, | |
| "loss": 0.0392, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6413604615851807, | |
| "grad_norm": 0.1683543622493744, | |
| "learning_rate": 2.3216432850954155e-05, | |
| "loss": 0.0438, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.660795627087762, | |
| "grad_norm": 0.1374560445547104, | |
| "learning_rate": 2.307588963631497e-05, | |
| "loss": 0.0388, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6646826601882782, | |
| "eval_loss": 0.048522137105464935, | |
| "eval_runtime": 174.8794, | |
| "eval_samples_per_second": 4.952, | |
| "eval_steps_per_second": 4.952, | |
| "step": 342 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1542, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 171, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6197272133828608e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |