| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.986666666666667, | |
| "eval_steps": 500, | |
| "global_step": 336, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 4.360917091369629, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 1.9685, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 2.809581995010376, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.9362, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 1.614979863166809, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 0.3709, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.012127161026001, | |
| "learning_rate": 9.990263847374976e-05, | |
| "loss": 0.1608, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 2.006868600845337, | |
| "learning_rate": 9.930902394260747e-05, | |
| "loss": 0.1725, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 1.6568659543991089, | |
| "learning_rate": 9.818229479678158e-05, | |
| "loss": 0.1163, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.42504391074180603, | |
| "learning_rate": 9.653463289927411e-05, | |
| "loss": 0.098, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.5771023035049438, | |
| "learning_rate": 9.438385228425938e-05, | |
| "loss": 0.0846, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.1149694919586182, | |
| "learning_rate": 9.175320655700406e-05, | |
| "loss": 0.0609, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.1335147619247437, | |
| "learning_rate": 8.86711374827494e-05, | |
| "loss": 0.1032, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.7952611446380615, | |
| "learning_rate": 8.517096748273951e-05, | |
| "loss": 0.0451, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.6720146536827087, | |
| "learning_rate": 8.129053936203687e-05, | |
| "loss": 0.0333, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 1.2561999559402466, | |
| "learning_rate": 7.707180716428237e-05, | |
| "loss": 0.052, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 0.3796238601207733, | |
| "learning_rate": 7.256038257695687e-05, | |
| "loss": 0.0251, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.7928345799446106, | |
| "learning_rate": 6.780504179127734e-05, | |
| "loss": 0.047, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.5534237623214722, | |
| "learning_rate": 6.28571981484123e-05, | |
| "loss": 0.0367, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 0.15348124504089355, | |
| "learning_rate": 5.7770346273610254e-05, | |
| "loss": 0.0462, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.8944855332374573, | |
| "learning_rate": 5.2599483708099016e-05, | |
| "loss": 0.0248, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 0.14208973944187164, | |
| "learning_rate": 4.740051629190099e-05, | |
| "loss": 0.0339, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.6974976062774658, | |
| "learning_rate": 4.2229653726389765e-05, | |
| "loss": 0.029, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.3344897925853729, | |
| "learning_rate": 3.714280185158771e-05, | |
| "loss": 0.0239, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 0.7733135223388672, | |
| "learning_rate": 3.219495820872265e-05, | |
| "loss": 0.0206, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 0.30857089161872864, | |
| "learning_rate": 2.7439617423043145e-05, | |
| "loss": 0.0188, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.48630648851394653, | |
| "learning_rate": 2.2928192835717644e-05, | |
| "loss": 0.0129, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.024921678006649017, | |
| "learning_rate": 1.8709460637963123e-05, | |
| "loss": 0.0194, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 0.26087790727615356, | |
| "learning_rate": 1.4829032517260489e-05, | |
| "loss": 0.0105, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.14827875792980194, | |
| "learning_rate": 1.132886251725061e-05, | |
| "loss": 0.0174, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.32020169496536255, | |
| "learning_rate": 8.246793442995954e-06, | |
| "loss": 0.0199, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 0.15603934228420258, | |
| "learning_rate": 5.616147715740611e-06, | |
| "loss": 0.0159, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.13697227835655212, | |
| "learning_rate": 3.465367100725908e-06, | |
| "loss": 0.0065, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.7555555555555555, | |
| "grad_norm": 0.25967034697532654, | |
| "learning_rate": 1.8177052032184283e-06, | |
| "loss": 0.0119, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.27596426010131836, | |
| "learning_rate": 6.909760573925561e-07, | |
| "loss": 0.0086, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 0.06968388706445694, | |
| "learning_rate": 9.73615262502503e-08, | |
| "loss": 0.0076, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.986666666666667, | |
| "step": 336, | |
| "total_flos": 1.0812364748292096e+16, | |
| "train_loss": 0.1382851616390759, | |
| "train_runtime": 3802.491, | |
| "train_samples_per_second": 0.71, | |
| "train_steps_per_second": 0.088 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 336, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0812364748292096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |