| { | |
| "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": 0.6975772976875305, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.913, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.591727614402771, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.8774, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.6257310509681702, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 0.7954, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.4526883065700531, | |
| "learning_rate": 9.990263847374976e-05, | |
| "loss": 0.7382, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.5159986019134521, | |
| "learning_rate": 9.930902394260747e-05, | |
| "loss": 0.7335, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.5612029433250427, | |
| "learning_rate": 9.818229479678158e-05, | |
| "loss": 0.7586, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.6560376882553101, | |
| "learning_rate": 9.653463289927411e-05, | |
| "loss": 0.7147, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.49994340538978577, | |
| "learning_rate": 9.438385228425938e-05, | |
| "loss": 0.7583, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.5289478302001953, | |
| "learning_rate": 9.175320655700406e-05, | |
| "loss": 0.7012, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.3789616525173187, | |
| "learning_rate": 8.86711374827494e-05, | |
| "loss": 0.7226, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.47833511233329773, | |
| "learning_rate": 8.517096748273951e-05, | |
| "loss": 0.75, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.4347563683986664, | |
| "learning_rate": 8.129053936203687e-05, | |
| "loss": 0.6529, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 0.4362315535545349, | |
| "learning_rate": 7.707180716428237e-05, | |
| "loss": 0.6358, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 0.599666178226471, | |
| "learning_rate": 7.256038257695687e-05, | |
| "loss": 0.6568, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.8356653451919556, | |
| "learning_rate": 6.780504179127734e-05, | |
| "loss": 0.6376, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.8184866309165955, | |
| "learning_rate": 6.28571981484123e-05, | |
| "loss": 0.6286, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 0.7259312272071838, | |
| "learning_rate": 5.7770346273610254e-05, | |
| "loss": 0.6114, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.8278394937515259, | |
| "learning_rate": 5.2599483708099016e-05, | |
| "loss": 0.6427, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 0.8557686805725098, | |
| "learning_rate": 4.740051629190099e-05, | |
| "loss": 0.6302, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.8115431666374207, | |
| "learning_rate": 4.2229653726389765e-05, | |
| "loss": 0.6985, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.705405056476593, | |
| "learning_rate": 3.714280185158771e-05, | |
| "loss": 0.5733, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 0.808897852897644, | |
| "learning_rate": 3.219495820872265e-05, | |
| "loss": 0.631, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 0.7055577635765076, | |
| "learning_rate": 2.7439617423043145e-05, | |
| "loss": 0.5628, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.818642258644104, | |
| "learning_rate": 2.2928192835717644e-05, | |
| "loss": 0.4699, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.1146687269210815, | |
| "learning_rate": 1.8709460637963123e-05, | |
| "loss": 0.5786, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 0.8422965407371521, | |
| "learning_rate": 1.4829032517260489e-05, | |
| "loss": 0.4809, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.1625632047653198, | |
| "learning_rate": 1.132886251725061e-05, | |
| "loss": 0.4812, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.9333996176719666, | |
| "learning_rate": 8.246793442995954e-06, | |
| "loss": 0.4922, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 0.9746198654174805, | |
| "learning_rate": 5.616147715740611e-06, | |
| "loss": 0.5673, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.7620270848274231, | |
| "learning_rate": 3.465367100725908e-06, | |
| "loss": 0.4935, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.7555555555555555, | |
| "grad_norm": 1.050020694732666, | |
| "learning_rate": 1.8177052032184283e-06, | |
| "loss": 0.4809, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 1.236220359802246, | |
| "learning_rate": 6.909760573925561e-07, | |
| "loss": 0.5241, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 1.2275803089141846, | |
| "learning_rate": 9.73615262502503e-08, | |
| "loss": 0.4713, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.986666666666667, | |
| "step": 336, | |
| "total_flos": 4.305727770800947e+16, | |
| "train_loss": 0.6357665289015997, | |
| "train_runtime": 471.1596, | |
| "train_samples_per_second": 5.731, | |
| "train_steps_per_second": 0.713 | |
| } | |
| ], | |
| "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": 4.305727770800947e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |