| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9966329966329966, | |
| "eval_steps": 100, | |
| "global_step": 185, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026936026936026935, | |
| "grad_norm": 67.7872314453125, | |
| "learning_rate": 1.9976687691905394e-05, | |
| "loss": 6.0971, | |
| "num_input_tokens_seen": 82560, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05387205387205387, | |
| "grad_norm": 1003.2200317382812, | |
| "learning_rate": 1.988216769442353e-05, | |
| "loss": 5.282, | |
| "num_input_tokens_seen": 165120, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 47.967403411865234, | |
| "learning_rate": 1.9715670893979416e-05, | |
| "loss": 4.301, | |
| "num_input_tokens_seen": 247680, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10774410774410774, | |
| "grad_norm": 66.77752685546875, | |
| "learning_rate": 1.947840997060136e-05, | |
| "loss": 2.5698, | |
| "num_input_tokens_seen": 330240, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13468013468013468, | |
| "grad_norm": 21.431270599365234, | |
| "learning_rate": 1.917211301505453e-05, | |
| "loss": 1.0565, | |
| "num_input_tokens_seen": 412800, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 5.1596455574035645, | |
| "learning_rate": 1.879901094228584e-05, | |
| "loss": 0.2428, | |
| "num_input_tokens_seen": 495360, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18855218855218855, | |
| "grad_norm": 2.640035390853882, | |
| "learning_rate": 1.836182124254711e-05, | |
| "loss": 0.2839, | |
| "num_input_tokens_seen": 577920, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21548821548821548, | |
| "grad_norm": 2.514108896255493, | |
| "learning_rate": 1.7863728188545326e-05, | |
| "loss": 0.0107, | |
| "num_input_tokens_seen": 660480, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.09124995023012161, | |
| "learning_rate": 1.730835964278124e-05, | |
| "loss": 0.0023, | |
| "num_input_tokens_seen": 743040, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26936026936026936, | |
| "grad_norm": 11.549006462097168, | |
| "learning_rate": 1.6699760634000166e-05, | |
| "loss": 0.2308, | |
| "num_input_tokens_seen": 825600, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 1.6471961736679077, | |
| "learning_rate": 1.6042363895210948e-05, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 908160, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 0.02977609820663929, | |
| "learning_rate": 1.5340957577859605e-05, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 990720, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3501683501683502, | |
| "grad_norm": 0.17247651517391205, | |
| "learning_rate": 1.4600650377311523e-05, | |
| "loss": 0.0012, | |
| "num_input_tokens_seen": 1073280, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3771043771043771, | |
| "grad_norm": 71.56356811523438, | |
| "learning_rate": 1.3826834323650899e-05, | |
| "loss": 0.6015, | |
| "num_input_tokens_seen": 1155840, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 0.016915204003453255, | |
| "learning_rate": 1.302514550881076e-05, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 1238400, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.43097643097643096, | |
| "grad_norm": 0.008289608173072338, | |
| "learning_rate": 1.2201423036077657e-05, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 1320960, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.45791245791245794, | |
| "grad_norm": 0.01277772057801485, | |
| "learning_rate": 1.1361666490962468e-05, | |
| "loss": 0.0025, | |
| "num_input_tokens_seen": 1403520, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.006596778519451618, | |
| "learning_rate": 1.0511992243198335e-05, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 1486080, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5117845117845118, | |
| "grad_norm": 0.020030811429023743, | |
| "learning_rate": 9.658588898140322e-06, | |
| "loss": 0.046, | |
| "num_input_tokens_seen": 1568640, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5387205387205387, | |
| "grad_norm": 0.08077715337276459, | |
| "learning_rate": 8.807672222036692e-06, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 1651200, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5387205387205387, | |
| "eval_loss": 0.00024870518245734274, | |
| "eval_runtime": 7.5641, | |
| "eval_samples_per_second": 3.966, | |
| "eval_steps_per_second": 1.983, | |
| "num_input_tokens_seen": 1651200, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5656565656565656, | |
| "grad_norm": 0.011016723699867725, | |
| "learning_rate": 7.965439869473664e-06, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 1733760, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.23388978838920593, | |
| "learning_rate": 7.1380262427365885e-06, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 1816320, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6195286195286195, | |
| "grad_norm": 0.07084622979164124, | |
| "learning_rate": 6.331457811869437e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 1898880, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": 0.035638194531202316, | |
| "learning_rate": 5.55160922085916e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 1981440, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "grad_norm": 0.008004716597497463, | |
| "learning_rate": 4.804160499645667e-06, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 2064000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7003367003367004, | |
| "grad_norm": 0.008612624369561672, | |
| "learning_rate": 4.094555693603891e-06, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 2146560, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.03172842785716057, | |
| "learning_rate": 3.4279632118202744e-06, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 2229120, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7542087542087542, | |
| "grad_norm": 0.004970299545675516, | |
| "learning_rate": 2.809238182967092e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 2311680, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7811447811447811, | |
| "grad_norm": 0.1790950447320938, | |
| "learning_rate": 2.2428870929558012e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 2394240, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 40.12051773071289, | |
| "learning_rate": 1.7330349619311415e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 2476800, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.835016835016835, | |
| "grad_norm": 0.004456690046936274, | |
| "learning_rate": 1.2833952996724864e-06, | |
| "loss": 0.0743, | |
| "num_input_tokens_seen": 2559360, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8619528619528619, | |
| "grad_norm": 0.046330228447914124, | |
| "learning_rate": 8.972430582323788e-07, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 2641920, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.015978099778294563, | |
| "learning_rate": 5.77390778811796e-07, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 2724480, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9158249158249159, | |
| "grad_norm": 0.014428800903260708, | |
| "learning_rate": 3.261681066064859e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 2807040, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9427609427609428, | |
| "grad_norm": 0.03189552202820778, | |
| "learning_rate": 1.4540482282803136e-07, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 2889600, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.008983040228486061, | |
| "learning_rate": 3.641751748600042e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 2972160, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9966329966329966, | |
| "grad_norm": 0.006297091022133827, | |
| "learning_rate": 0.0, | |
| "loss": 0.2164, | |
| "num_input_tokens_seen": 3054720, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.9966329966329966, | |
| "num_input_tokens_seen": 3054720, | |
| "step": 185, | |
| "total_flos": 4.410158569555968e+16, | |
| "train_loss": 0.5683108514618456, | |
| "train_runtime": 2363.4699, | |
| "train_samples_per_second": 1.257, | |
| "train_steps_per_second": 0.078 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 185, | |
| "num_input_tokens_seen": 3054720, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.410158569555968e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |