| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4770423375074538, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011926058437686345, | |
| "grad_norm": 0.5661849975585938, | |
| "learning_rate": 4.999804802810596e-05, | |
| "loss": 1.4421, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02385211687537269, | |
| "grad_norm": 0.5908129811286926, | |
| "learning_rate": 4.999219241723937e-05, | |
| "loss": 1.3306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03577817531305903, | |
| "grad_norm": 0.6965810060501099, | |
| "learning_rate": 4.998243408179925e-05, | |
| "loss": 1.1873, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04770423375074538, | |
| "grad_norm": 0.5752276182174683, | |
| "learning_rate": 4.9968774545625344e-05, | |
| "loss": 1.0583, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05963029218843172, | |
| "grad_norm": 0.6488135457038879, | |
| "learning_rate": 4.9951215941760075e-05, | |
| "loss": 1.0045, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07155635062611806, | |
| "grad_norm": 0.7977299094200134, | |
| "learning_rate": 4.992976101211558e-05, | |
| "loss": 0.9836, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08348240906380441, | |
| "grad_norm": 0.8842712044715881, | |
| "learning_rate": 4.99044131070454e-05, | |
| "loss": 0.8925, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09540846750149076, | |
| "grad_norm": 0.798170804977417, | |
| "learning_rate": 4.987517618482142e-05, | |
| "loss": 0.8783, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1073345259391771, | |
| "grad_norm": 0.8196467757225037, | |
| "learning_rate": 4.984205481101565e-05, | |
| "loss": 0.8681, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11926058437686345, | |
| "grad_norm": 0.9973539113998413, | |
| "learning_rate": 4.980505415778738e-05, | |
| "loss": 0.8251, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13118664281454978, | |
| "grad_norm": 0.8836011290550232, | |
| "learning_rate": 4.97641800030754e-05, | |
| "loss": 0.8079, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14311270125223613, | |
| "grad_norm": 0.9255298972129822, | |
| "learning_rate": 4.971943872969582e-05, | |
| "loss": 0.7769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 0.9712087512016296, | |
| "learning_rate": 4.967083732434529e-05, | |
| "loss": 0.777, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16696481812760883, | |
| "grad_norm": 0.7609415054321289, | |
| "learning_rate": 4.961838337650997e-05, | |
| "loss": 0.7303, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17889087656529518, | |
| "grad_norm": 0.8297658562660217, | |
| "learning_rate": 4.9562085077280443e-05, | |
| "loss": 0.7442, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19081693500298152, | |
| "grad_norm": 1.01498281955719, | |
| "learning_rate": 4.950195121807251e-05, | |
| "loss": 0.7077, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20274299344066785, | |
| "grad_norm": 0.9629709720611572, | |
| "learning_rate": 4.943799118925443e-05, | |
| "loss": 0.673, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2146690518783542, | |
| "grad_norm": 0.9121557474136353, | |
| "learning_rate": 4.937021497868047e-05, | |
| "loss": 0.7109, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22659511031604054, | |
| "grad_norm": 0.841573178768158, | |
| "learning_rate": 4.9298633170131304e-05, | |
| "loss": 0.6798, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2385211687537269, | |
| "grad_norm": 0.9693652391433716, | |
| "learning_rate": 4.922325694166119e-05, | |
| "loss": 0.6471, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2504472271914132, | |
| "grad_norm": 1.1198012828826904, | |
| "learning_rate": 4.9144098063852485e-05, | |
| "loss": 0.6456, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.26237328562909956, | |
| "grad_norm": 1.1725982427597046, | |
| "learning_rate": 4.9061168897977564e-05, | |
| "loss": 0.6462, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2742993440667859, | |
| "grad_norm": 0.9855665564537048, | |
| "learning_rate": 4.8974482394068514e-05, | |
| "loss": 0.6594, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.28622540250447226, | |
| "grad_norm": 0.8321542739868164, | |
| "learning_rate": 4.888405208889486e-05, | |
| "loss": 0.6372, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2981514609421586, | |
| "grad_norm": 0.9451864957809448, | |
| "learning_rate": 4.878989210384972e-05, | |
| "loss": 0.6594, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 1.1336216926574707, | |
| "learning_rate": 4.869201714274467e-05, | |
| "loss": 0.6544, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3220035778175313, | |
| "grad_norm": 0.8466928601264954, | |
| "learning_rate": 4.8590442489513543e-05, | |
| "loss": 0.6275, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.33392963625521765, | |
| "grad_norm": 0.979365885257721, | |
| "learning_rate": 4.8485184005825815e-05, | |
| "loss": 0.6348, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.345855694692904, | |
| "grad_norm": 0.9159572124481201, | |
| "learning_rate": 4.837625812860961e-05, | |
| "loss": 0.6045, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.35778175313059035, | |
| "grad_norm": 1.0542089939117432, | |
| "learning_rate": 4.8263681867485e-05, | |
| "loss": 0.6487, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3697078115682767, | |
| "grad_norm": 1.0264719724655151, | |
| "learning_rate": 4.814747280210782e-05, | |
| "loss": 0.6026, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.38163387000596305, | |
| "grad_norm": 0.9389889240264893, | |
| "learning_rate": 4.80276490794244e-05, | |
| "loss": 0.6083, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3935599284436494, | |
| "grad_norm": 1.1090476512908936, | |
| "learning_rate": 4.790422941083786e-05, | |
| "loss": 0.5957, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4054859868813357, | |
| "grad_norm": 1.0268605947494507, | |
| "learning_rate": 4.7777233069286154e-05, | |
| "loss": 0.6538, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41741204531902204, | |
| "grad_norm": 1.240955114364624, | |
| "learning_rate": 4.7646679886232414e-05, | |
| "loss": 0.62, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4293381037567084, | |
| "grad_norm": 1.2029043436050415, | |
| "learning_rate": 4.7512590248568163e-05, | |
| "loss": 0.6461, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.44126416219439474, | |
| "grad_norm": 1.0567660331726074, | |
| "learning_rate": 4.7374985095429725e-05, | |
| "loss": 0.633, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.4531902206320811, | |
| "grad_norm": 0.928354024887085, | |
| "learning_rate": 4.723388591492841e-05, | |
| "loss": 0.633, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 0.8453586101531982, | |
| "learning_rate": 4.708931474079499e-05, | |
| "loss": 0.6082, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.4770423375074538, | |
| "grad_norm": 1.33816397190094, | |
| "learning_rate": 4.6941294148938954e-05, | |
| "loss": 0.6176, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1257, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.97054418436096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |