| { | |
| "best_global_step": 1037, | |
| "best_metric": 0.49676260352134705, | |
| "best_model_checkpoint": "./mcqa_model_test/checkpoint-1037", | |
| "epoch": 0.9995180722891567, | |
| "eval_steps": 500, | |
| "global_step": 1037, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": 42.887596130371094, | |
| "learning_rate": 4.2307692307692304e-07, | |
| "loss": 0.7896, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": 72.85254669189453, | |
| "learning_rate": 9.038461538461538e-07, | |
| "loss": 0.6271, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 73.7239990234375, | |
| "learning_rate": 9.571275455519828e-07, | |
| "loss": 0.5829, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 49.094295501708984, | |
| "learning_rate": 9.035369774919614e-07, | |
| "loss": 0.547, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 36.50214767456055, | |
| "learning_rate": 8.4994640943194e-07, | |
| "loss": 0.6207, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 75.927001953125, | |
| "learning_rate": 7.963558413719184e-07, | |
| "loss": 0.5786, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3373493975903614, | |
| "grad_norm": 42.72712707519531, | |
| "learning_rate": 7.42765273311897e-07, | |
| "loss": 0.5925, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 69.0036849975586, | |
| "learning_rate": 6.891747052518756e-07, | |
| "loss": 0.5646, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 58.4212646484375, | |
| "learning_rate": 6.355841371918542e-07, | |
| "loss": 0.5514, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 47.25130844116211, | |
| "learning_rate": 5.819935691318327e-07, | |
| "loss": 0.5391, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5301204819277109, | |
| "grad_norm": 54.83015060424805, | |
| "learning_rate": 5.284030010718113e-07, | |
| "loss": 0.5741, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 59.51740646362305, | |
| "learning_rate": 4.748124330117899e-07, | |
| "loss": 0.5348, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6265060240963856, | |
| "grad_norm": 40.834083557128906, | |
| "learning_rate": 4.2122186495176846e-07, | |
| "loss": 0.6069, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6746987951807228, | |
| "grad_norm": 80.05315399169922, | |
| "learning_rate": 3.6763129689174703e-07, | |
| "loss": 0.5564, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 45.48673629760742, | |
| "learning_rate": 3.140407288317256e-07, | |
| "loss": 0.5112, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": 47.77269744873047, | |
| "learning_rate": 2.6045016077170417e-07, | |
| "loss": 0.4865, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8192771084337349, | |
| "grad_norm": 87.04841613769531, | |
| "learning_rate": 2.0685959271168274e-07, | |
| "loss": 0.5324, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 45.74528884887695, | |
| "learning_rate": 1.532690246516613e-07, | |
| "loss": 0.5099, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9156626506024096, | |
| "grad_norm": 44.13926315307617, | |
| "learning_rate": 9.967845659163988e-08, | |
| "loss": 0.5559, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": 53.90440368652344, | |
| "learning_rate": 4.608788853161844e-08, | |
| "loss": 0.4868, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9995180722891567, | |
| "eval_loss": 0.49676260352134705, | |
| "eval_runtime": 30.1745, | |
| "eval_samples_per_second": 103.1, | |
| "eval_steps_per_second": 12.892, | |
| "step": 1037 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1037, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 7892894912348160.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |