| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020648358455502787, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008259343382201115, | |
| "grad_norm": 1677.547119140625, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 103.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008259343382201115, | |
| "eval_loss": 13.492105484008789, | |
| "eval_runtime": 244.2801, | |
| "eval_samples_per_second": 4.176, | |
| "eval_steps_per_second": 2.088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001651868676440223, | |
| "grad_norm": 1696.8392333984375, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 105.2538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024778030146603344, | |
| "grad_norm": 941.0369873046875, | |
| "learning_rate": 0.0001, | |
| "loss": 66.4773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003303737352880446, | |
| "grad_norm": 699.8087768554688, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 29.6233, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0041296716911005575, | |
| "grad_norm": 504.3501892089844, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 9.9401, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004955606029320669, | |
| "grad_norm": 1.2597764730453491, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.0057, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005781540367540781, | |
| "grad_norm": 0.005221178755164146, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006607474705760892, | |
| "grad_norm": 0.026343591511249542, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.0001, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007433409043981004, | |
| "grad_norm": 0.6239492297172546, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0002, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008259343382201115, | |
| "grad_norm": 0.001214036368764937, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009085277720421227, | |
| "grad_norm": 0.0005943904398009181, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009911212058641337, | |
| "grad_norm": 0.00028382017626427114, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01073714639686145, | |
| "grad_norm": 0.00030877735116519034, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011563080735081561, | |
| "grad_norm": 0.00028087597456760705, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012389015073301672, | |
| "grad_norm": 0.00024960265727713704, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013214949411521784, | |
| "grad_norm": 0.0001821557671064511, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014040883749741896, | |
| "grad_norm": 0.00019730778876692057, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014866818087962008, | |
| "grad_norm": 0.0001254954986507073, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015692752426182118, | |
| "grad_norm": 0.00014692585682496428, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01651868676440223, | |
| "grad_norm": 0.00016185363347176462, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017344621102622342, | |
| "grad_norm": 0.00012402540596667677, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018170555440842454, | |
| "grad_norm": 8.475293725496158e-05, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018996489779062563, | |
| "grad_norm": 7.959387585287914e-05, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019822424117282675, | |
| "grad_norm": 7.412952982122079e-05, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020648358455502787, | |
| "grad_norm": 5.231930845184252e-05, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020648358455502787, | |
| "eval_loss": 4.6826649224840367e-08, | |
| "eval_runtime": 246.3015, | |
| "eval_samples_per_second": 4.141, | |
| "eval_steps_per_second": 2.071, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.553948699774157e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |