| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 13.655919661733614, |
| "eval_steps": 500, |
| "global_step": 31000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4404510218463707, |
| "grad_norm": 4.032470226287842, |
| "learning_rate": 6.837606837606838e-05, |
| "loss": 3.4199, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8809020436927414, |
| "grad_norm": 3.2777514457702637, |
| "learning_rate": 7.990501800381062e-05, |
| "loss": 2.7144, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.3213530655391121, |
| "grad_norm": 2.619133710861206, |
| "learning_rate": 7.953897633451287e-05, |
| "loss": 2.5336, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.7618040873854828, |
| "grad_norm": 2.6373283863067627, |
| "learning_rate": 7.89004118428791e-05, |
| "loss": 2.4685, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.2022551092318534, |
| "grad_norm": 2.54191517829895, |
| "learning_rate": 7.799372584157945e-05, |
| "loss": 2.3449, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.643058491895701, |
| "grad_norm": 2.7752420902252197, |
| "learning_rate": 7.682516767369139e-05, |
| "loss": 2.2135, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.083509513742072, |
| "grad_norm": 2.874178647994995, |
| "learning_rate": 7.540279163903496e-05, |
| "loss": 2.164, |
| "step": 7000 |
| }, |
| { |
| "epoch": 3.5239605355884427, |
| "grad_norm": 3.0076916217803955, |
| "learning_rate": 7.373640147982414e-05, |
| "loss": 2.0313, |
| "step": 8000 |
| }, |
| { |
| "epoch": 3.964411557434813, |
| "grad_norm": 3.3123347759246826, |
| "learning_rate": 7.183949364786388e-05, |
| "loss": 2.0361, |
| "step": 9000 |
| }, |
| { |
| "epoch": 4.405038759689923, |
| "grad_norm": 3.380844831466675, |
| "learning_rate": 6.972134717258394e-05, |
| "loss": 1.8111, |
| "step": 10000 |
| }, |
| { |
| "epoch": 4.845489781536293, |
| "grad_norm": 3.283961057662964, |
| "learning_rate": 6.739834599022777e-05, |
| "loss": 1.8308, |
| "step": 11000 |
| }, |
| { |
| "epoch": 5.285940803382664, |
| "grad_norm": 3.721411943435669, |
| "learning_rate": 6.488650141158779e-05, |
| "loss": 1.6801, |
| "step": 12000 |
| }, |
| { |
| "epoch": 5.726391825229035, |
| "grad_norm": 4.229532241821289, |
| "learning_rate": 6.220588934355638e-05, |
| "loss": 1.6222, |
| "step": 13000 |
| }, |
| { |
| "epoch": 6.167195207892882, |
| "grad_norm": 4.481683731079102, |
| "learning_rate": 5.936962243074913e-05, |
| "loss": 1.4268, |
| "step": 14000 |
| }, |
| { |
| "epoch": 6.607822410147992, |
| "grad_norm": 4.215762615203857, |
| "learning_rate": 5.6399850185690715e-05, |
| "loss": 1.3724, |
| "step": 15000 |
| }, |
| { |
| "epoch": 7.048273431994362, |
| "grad_norm": 5.387717247009277, |
| "learning_rate": 5.331704179572355e-05, |
| "loss": 1.3981, |
| "step": 16000 |
| }, |
| { |
| "epoch": 7.488724453840733, |
| "grad_norm": 4.61813497543335, |
| "learning_rate": 5.0145658757833603e-05, |
| "loss": 1.2341, |
| "step": 17000 |
| }, |
| { |
| "epoch": 7.929351656095842, |
| "grad_norm": 4.356705665588379, |
| "learning_rate": 4.6901214401686045e-05, |
| "loss": 1.1431, |
| "step": 18000 |
| }, |
| { |
| "epoch": 8.369802677942213, |
| "grad_norm": 4.830331802368164, |
| "learning_rate": 4.3612511588650615e-05, |
| "loss": 1.0619, |
| "step": 19000 |
| }, |
| { |
| "epoch": 8.810253699788584, |
| "grad_norm": 5.71049690246582, |
| "learning_rate": 4.029563753692198e-05, |
| "loss": 1.0978, |
| "step": 20000 |
| }, |
| { |
| "epoch": 9.250704721634953, |
| "grad_norm": 5.030432224273682, |
| "learning_rate": 3.697672580027027e-05, |
| "loss": 0.9781, |
| "step": 21000 |
| }, |
| { |
| "epoch": 9.691508104298801, |
| "grad_norm": 5.41664457321167, |
| "learning_rate": 3.367865201376263e-05, |
| "loss": 0.844, |
| "step": 22000 |
| }, |
| { |
| "epoch": 10.131959126145173, |
| "grad_norm": 6.824735164642334, |
| "learning_rate": 3.0427373428497704e-05, |
| "loss": 0.8406, |
| "step": 23000 |
| }, |
| { |
| "epoch": 10.572410147991544, |
| "grad_norm": 5.802671909332275, |
| "learning_rate": 2.723879419604715e-05, |
| "loss": 0.7467, |
| "step": 24000 |
| }, |
| { |
| "epoch": 11.013037350246652, |
| "grad_norm": 5.451844215393066, |
| "learning_rate": 2.4138171712721338e-05, |
| "loss": 0.6603, |
| "step": 25000 |
| }, |
| { |
| "epoch": 11.453488372093023, |
| "grad_norm": 6.357388496398926, |
| "learning_rate": 2.1146877052546197e-05, |
| "loss": 0.6224, |
| "step": 26000 |
| }, |
| { |
| "epoch": 11.893939393939394, |
| "grad_norm": 6.137206554412842, |
| "learning_rate": 1.828831754233944e-05, |
| "loss": 0.646, |
| "step": 27000 |
| }, |
| { |
| "epoch": 12.334566596194502, |
| "grad_norm": 6.055389881134033, |
| "learning_rate": 1.5576476285220303e-05, |
| "loss": 0.5049, |
| "step": 28000 |
| }, |
| { |
| "epoch": 12.775017618040874, |
| "grad_norm": 5.402553081512451, |
| "learning_rate": 1.3035427908216205e-05, |
| "loss": 0.5154, |
| "step": 29000 |
| }, |
| { |
| "epoch": 13.215468639887245, |
| "grad_norm": 4.508989334106445, |
| "learning_rate": 1.0677602357724904e-05, |
| "loss": 0.4723, |
| "step": 30000 |
| }, |
| { |
| "epoch": 13.655919661733614, |
| "grad_norm": 5.23668909072876, |
| "learning_rate": 8.521881750354111e-06, |
| "loss": 0.418, |
| "step": 31000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 39000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 18, |
| "save_steps": 1000, |
| "total_flos": 1.5826675027968e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
