| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20618556701030927, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004123711340206186, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.1644, | |
| "eval_samples_per_second": 14.522, | |
| "eval_steps_per_second": 1.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012371134020618556, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "eval_loss": NaN, | |
| "eval_runtime": 27.8635, | |
| "eval_samples_per_second": 14.679, | |
| "eval_steps_per_second": 1.866, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024742268041237112, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03711340206185567, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "eval_loss": NaN, | |
| "eval_runtime": 27.9185, | |
| "eval_samples_per_second": 14.65, | |
| "eval_steps_per_second": 1.863, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.049484536082474224, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "eval_loss": NaN, | |
| "eval_runtime": 27.9745, | |
| "eval_samples_per_second": 14.62, | |
| "eval_steps_per_second": 1.859, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07422680412371134, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.0142, | |
| "eval_samples_per_second": 14.6, | |
| "eval_steps_per_second": 1.856, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0865979381443299, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09896907216494845, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10309278350515463, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.0535, | |
| "eval_samples_per_second": 14.579, | |
| "eval_steps_per_second": 1.854, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11134020618556702, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.0902, | |
| "eval_samples_per_second": 14.56, | |
| "eval_steps_per_second": 1.851, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1360824742268041, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14432989690721648, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.0691, | |
| "eval_samples_per_second": 14.571, | |
| "eval_steps_per_second": 1.853, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14845360824742268, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16082474226804125, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.0541, | |
| "eval_samples_per_second": 14.579, | |
| "eval_steps_per_second": 1.854, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1731958762886598, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18556701030927836, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18556701030927836, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.057, | |
| "eval_samples_per_second": 14.577, | |
| "eval_steps_per_second": 1.853, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1979381443298969, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.0132, | |
| "eval_samples_per_second": 14.6, | |
| "eval_steps_per_second": 1.856, | |
| "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": 6.71020323176448e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |