| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7894736842105263, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017543859649122806, | |
| "eval_loss": 10.366873741149902, | |
| "eval_runtime": 0.1727, | |
| "eval_samples_per_second": 555.877, | |
| "eval_steps_per_second": 69.485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 0.07264672964811325, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "eval_loss": 10.366547584533691, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 573.519, | |
| "eval_steps_per_second": 71.69, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.08514741063117981, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3717, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.08602377027273178, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3709, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "eval_loss": 10.365401268005371, | |
| "eval_runtime": 0.1659, | |
| "eval_samples_per_second": 578.602, | |
| "eval_steps_per_second": 72.325, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.07277622818946838, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 10.3704, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 0.07048846036195755, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3696, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "eval_loss": 10.363677024841309, | |
| "eval_runtime": 0.1716, | |
| "eval_samples_per_second": 559.366, | |
| "eval_steps_per_second": 69.921, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.09568169713020325, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3689, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "eval_loss": 10.36184310913086, | |
| "eval_runtime": 0.1886, | |
| "eval_samples_per_second": 508.996, | |
| "eval_steps_per_second": 63.625, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 0.08425775915384293, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 10.3657, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.11433319002389908, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 10.3645, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "eval_loss": 10.35986328125, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 577.559, | |
| "eval_steps_per_second": 72.195, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 0.1078442707657814, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 10.3641, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.11035740375518799, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3617, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "eval_loss": 10.358070373535156, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 566.668, | |
| "eval_steps_per_second": 70.833, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 0.158222496509552, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 10.3614, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6140350877192983, | |
| "eval_loss": 10.356663703918457, | |
| "eval_runtime": 0.1699, | |
| "eval_samples_per_second": 565.089, | |
| "eval_steps_per_second": 70.636, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.13146649301052094, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 10.3615, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 0.12355206906795502, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 10.3609, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "eval_loss": 10.355828285217285, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 576.456, | |
| "eval_steps_per_second": 72.057, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.13545456528663635, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3617, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.1202831044793129, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3582, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "eval_loss": 10.355480194091797, | |
| "eval_runtime": 0.1709, | |
| "eval_samples_per_second": 561.655, | |
| "eval_steps_per_second": 70.207, | |
| "step": 45 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5019779727360.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |