| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.984709480122324, | |
| "eval_steps": 500, | |
| "global_step": 366, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08154943934760449, | |
| "grad_norm": 1.5832443237304688, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 1.8972, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16309887869520898, | |
| "grad_norm": 1.6229541301727295, | |
| "learning_rate": 5.405405405405406e-05, | |
| "loss": 1.7883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24464831804281345, | |
| "grad_norm": 1.407547116279602, | |
| "learning_rate": 8.108108108108109e-05, | |
| "loss": 1.3865, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32619775739041795, | |
| "grad_norm": 2.573899745941162, | |
| "learning_rate": 9.999088210158001e-05, | |
| "loss": 1.3647, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4077471967380224, | |
| "grad_norm": 2.391404390335083, | |
| "learning_rate": 9.967210469256656e-05, | |
| "loss": 1.2114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4892966360856269, | |
| "grad_norm": 1.054701805114746, | |
| "learning_rate": 9.890075235781779e-05, | |
| "loss": 1.2255, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5708460754332314, | |
| "grad_norm": 1.9387873411178589, | |
| "learning_rate": 9.768385308070138e-05, | |
| "loss": 1.3242, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6523955147808359, | |
| "grad_norm": 0.961560070514679, | |
| "learning_rate": 9.603249433382144e-05, | |
| "loss": 1.106, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 0.783678412437439, | |
| "learning_rate": 9.396172205829234e-05, | |
| "loss": 1.1686, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8154943934760448, | |
| "grad_norm": 1.3414908647537231, | |
| "learning_rate": 9.149040357641929e-05, | |
| "loss": 1.148, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8970438328236493, | |
| "grad_norm": 1.628290057182312, | |
| "learning_rate": 8.864105568682244e-05, | |
| "loss": 1.3969, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9785932721712538, | |
| "grad_norm": 1.0776128768920898, | |
| "learning_rate": 8.543963950827279e-05, | |
| "loss": 1.1595, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0601427115188584, | |
| "grad_norm": 0.6094745993614197, | |
| "learning_rate": 8.191532394146865e-05, | |
| "loss": 1.091, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1416921508664628, | |
| "grad_norm": 1.0875447988510132, | |
| "learning_rate": 7.810021990391164e-05, | |
| "loss": 1.0718, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2232415902140672, | |
| "grad_norm": 0.9140685200691223, | |
| "learning_rate": 7.402908775933419e-05, | |
| "loss": 1.0833, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3047910295616718, | |
| "grad_norm": 0.7726348638534546, | |
| "learning_rate": 6.973902060736226e-05, | |
| "loss": 1.073, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3863404689092762, | |
| "grad_norm": 1.4581207036972046, | |
| "learning_rate": 6.526910631903973e-05, | |
| "loss": 1.0823, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "grad_norm": 0.8327229022979736, | |
| "learning_rate": 6.0660071397493514e-05, | |
| "loss": 0.9893, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.5494393476044852, | |
| "grad_norm": 0.6057823300361633, | |
| "learning_rate": 5.5953909908613114e-05, | |
| "loss": 0.9235, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6309887869520896, | |
| "grad_norm": 0.7681270241737366, | |
| "learning_rate": 5.119350086265004e-05, | |
| "loss": 1.012, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.7125382262996942, | |
| "grad_norm": 1.238531231880188, | |
| "learning_rate": 4.64222175328687e-05, | |
| "loss": 1.0746, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.7940876656472988, | |
| "grad_norm": 1.5333278179168701, | |
| "learning_rate": 4.1683532270843504e-05, | |
| "loss": 1.0924, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8756371049949032, | |
| "grad_norm": 1.807810664176941, | |
| "learning_rate": 3.7020620419029094e-05, | |
| "loss": 1.0545, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.9571865443425076, | |
| "grad_norm": 1.5522844791412354, | |
| "learning_rate": 3.2475966929454504e-05, | |
| "loss": 1.0335, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.038735983690112, | |
| "grad_norm": 1.2546252012252808, | |
| "learning_rate": 2.8090979272736662e-05, | |
| "loss": 0.9929, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.120285423037717, | |
| "grad_norm": 1.7230066061019897, | |
| "learning_rate": 2.3905610164295394e-05, | |
| "loss": 0.9195, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.2018348623853212, | |
| "grad_norm": 1.0860559940338135, | |
| "learning_rate": 1.995799354520598e-05, | |
| "loss": 0.8906, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.2833843017329256, | |
| "grad_norm": 1.6877241134643555, | |
| "learning_rate": 1.6284097134357536e-05, | |
| "loss": 0.8852, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.36493374108053, | |
| "grad_norm": 0.8254657983779907, | |
| "learning_rate": 1.2917394717602121e-05, | |
| "loss": 0.8899, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.4464831804281344, | |
| "grad_norm": 1.212756633758545, | |
| "learning_rate": 9.888561159748993e-06, | |
| "loss": 0.9932, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.528032619775739, | |
| "grad_norm": 1.147220253944397, | |
| "learning_rate": 7.225192918226214e-06, | |
| "loss": 0.8445, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.6095820591233436, | |
| "grad_norm": 1.090319275856018, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.8961, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.691131498470948, | |
| "grad_norm": 0.7078003287315369, | |
| "learning_rate": 3.0883678868214806e-06, | |
| "loss": 0.9571, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.7726809378185524, | |
| "grad_norm": 0.9578835964202881, | |
| "learning_rate": 1.6526027408301226e-06, | |
| "loss": 0.9048, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.8542303771661572, | |
| "grad_norm": 2.023444652557373, | |
| "learning_rate": 6.573427809888067e-07, | |
| "loss": 0.8868, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.9357798165137616, | |
| "grad_norm": 1.268535852432251, | |
| "learning_rate": 1.1165606884234181e-07, | |
| "loss": 0.9579, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.984709480122324, | |
| "step": 366, | |
| "total_flos": 2.6312102502948864e+16, | |
| "train_loss": 1.1005799705213537, | |
| "train_runtime": 684.9766, | |
| "train_samples_per_second": 4.296, | |
| "train_steps_per_second": 0.534 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 366, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6312102502948864e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |