| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0819000819000819, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001638001638001638, | |
| "eval_loss": 2.5393452644348145, | |
| "eval_runtime": 43.4533, | |
| "eval_samples_per_second": 23.681, | |
| "eval_steps_per_second": 2.969, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004914004914004914, | |
| "grad_norm": 5.812180995941162, | |
| "learning_rate": 3e-05, | |
| "loss": 9.7727, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00819000819000819, | |
| "eval_loss": 2.494248628616333, | |
| "eval_runtime": 43.4947, | |
| "eval_samples_per_second": 23.658, | |
| "eval_steps_per_second": 2.966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "grad_norm": 6.924543857574463, | |
| "learning_rate": 6e-05, | |
| "loss": 10.5791, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014742014742014743, | |
| "grad_norm": 5.603793621063232, | |
| "learning_rate": 9e-05, | |
| "loss": 10.1633, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01638001638001638, | |
| "eval_loss": 2.426388740539551, | |
| "eval_runtime": 43.5129, | |
| "eval_samples_per_second": 23.648, | |
| "eval_steps_per_second": 2.965, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019656019656019656, | |
| "grad_norm": 5.900361061096191, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 9.6284, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02457002457002457, | |
| "grad_norm": 5.402828693389893, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.7673, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02457002457002457, | |
| "eval_loss": 2.3815274238586426, | |
| "eval_runtime": 43.5165, | |
| "eval_samples_per_second": 23.646, | |
| "eval_steps_per_second": 2.964, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029484029484029485, | |
| "grad_norm": 4.60156774520874, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 9.0834, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03276003276003276, | |
| "eval_loss": 2.353917121887207, | |
| "eval_runtime": 43.5183, | |
| "eval_samples_per_second": 23.645, | |
| "eval_steps_per_second": 2.964, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0343980343980344, | |
| "grad_norm": 4.772480487823486, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 8.9754, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03931203931203931, | |
| "grad_norm": 5.090885162353516, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 9.3215, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04095004095004095, | |
| "eval_loss": 2.3329718112945557, | |
| "eval_runtime": 43.5079, | |
| "eval_samples_per_second": 23.651, | |
| "eval_steps_per_second": 2.965, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.044226044226044224, | |
| "grad_norm": 4.790841579437256, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 9.2829, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04914004914004914, | |
| "grad_norm": 5.003331661224365, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1937, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04914004914004914, | |
| "eval_loss": 2.321431875228882, | |
| "eval_runtime": 43.5005, | |
| "eval_samples_per_second": 23.655, | |
| "eval_steps_per_second": 2.965, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 4.781295299530029, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 9.5147, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05733005733005733, | |
| "eval_loss": 2.3083062171936035, | |
| "eval_runtime": 43.5322, | |
| "eval_samples_per_second": 23.638, | |
| "eval_steps_per_second": 2.963, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05896805896805897, | |
| "grad_norm": 5.4107513427734375, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 9.4414, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06388206388206388, | |
| "grad_norm": 5.330532073974609, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 9.5488, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06552006552006552, | |
| "eval_loss": 2.3022868633270264, | |
| "eval_runtime": 43.5359, | |
| "eval_samples_per_second": 23.636, | |
| "eval_steps_per_second": 2.963, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0687960687960688, | |
| "grad_norm": 4.837084770202637, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 9.8265, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07371007371007371, | |
| "grad_norm": 4.688211441040039, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.6876, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07371007371007371, | |
| "eval_loss": 2.300471782684326, | |
| "eval_runtime": 43.5151, | |
| "eval_samples_per_second": 23.647, | |
| "eval_steps_per_second": 2.964, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07862407862407862, | |
| "grad_norm": 4.837754726409912, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 9.299, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0819000819000819, | |
| "eval_loss": 2.2990529537200928, | |
| "eval_runtime": 43.524, | |
| "eval_samples_per_second": 23.642, | |
| "eval_steps_per_second": 2.964, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.23758274674688e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |