| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.035404496371039124, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014161798548415648, | |
| "grad_norm": 23.20075035095215, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.3912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014161798548415648, | |
| "eval_loss": 10.59463119506836, | |
| "eval_runtime": 151.6501, | |
| "eval_samples_per_second": 3.924, | |
| "eval_steps_per_second": 1.965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028323597096831295, | |
| "grad_norm": 28.277725219726562, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.9081, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004248539564524694, | |
| "grad_norm": 24.364511489868164, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0504, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005664719419366259, | |
| "grad_norm": 18.489341735839844, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 7.3342, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007080899274207825, | |
| "grad_norm": 25.614126205444336, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 3.8967, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008497079129049389, | |
| "grad_norm": 41.44906234741211, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.9891, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009913258983890954, | |
| "grad_norm": 24.81721305847168, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.3137, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011329438838732518, | |
| "grad_norm": 7.7688493728637695, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.4025, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012745618693574084, | |
| "grad_norm": 4.148148059844971, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1716, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01416179854841565, | |
| "grad_norm": 0.756351113319397, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0929, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015577978403257213, | |
| "grad_norm": 4.284754276275635, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1716, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016994158258098777, | |
| "grad_norm": 5.088748455047607, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1915, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018410338112940343, | |
| "grad_norm": 3.0917534828186035, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.1343, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01982651796778191, | |
| "grad_norm": 3.725177049636841, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.1964, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021242697822623474, | |
| "grad_norm": 1.8048001527786255, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1206, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022658877677465036, | |
| "grad_norm": 0.94793301820755, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.1201, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024075057532306602, | |
| "grad_norm": 2.34434175491333, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.1184, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.025491237387148168, | |
| "grad_norm": 2.191009759902954, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1479, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026907417241989733, | |
| "grad_norm": 1.4999676942825317, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.1267, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0283235970968313, | |
| "grad_norm": 0.44820383191108704, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.1192, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02973977695167286, | |
| "grad_norm": 2.531404733657837, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1483, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.031155956806514427, | |
| "grad_norm": 0.7770451903343201, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.1114, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03257213666135599, | |
| "grad_norm": 1.0737981796264648, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.118, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.033988316516197555, | |
| "grad_norm": 3.9276962280273438, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2074, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.035404496371039124, | |
| "grad_norm": 4.217297554016113, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.2623, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.035404496371039124, | |
| "eval_loss": 0.1676926612854004, | |
| "eval_runtime": 152.4912, | |
| "eval_samples_per_second": 3.902, | |
| "eval_steps_per_second": 1.954, | |
| "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": 3.786003044735386e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |