| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008753118298393803, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017506236596787607, | |
| "eval_loss": 5.437164783477783, | |
| "eval_runtime": 404.4705, | |
| "eval_samples_per_second": 23.787, | |
| "eval_steps_per_second": 2.974, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005251870979036281, | |
| "grad_norm": 21.258892059326172, | |
| "learning_rate": 3e-05, | |
| "loss": 5.2371, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008753118298393803, | |
| "eval_loss": 4.403726100921631, | |
| "eval_runtime": 406.9303, | |
| "eval_samples_per_second": 23.643, | |
| "eval_steps_per_second": 2.956, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010503741958072562, | |
| "grad_norm": 50.95747375488281, | |
| "learning_rate": 6e-05, | |
| "loss": 4.875, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015755612937108845, | |
| "grad_norm": 10.002364158630371, | |
| "learning_rate": 9e-05, | |
| "loss": 3.2756, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017506236596787606, | |
| "eval_loss": 2.5834808349609375, | |
| "eval_runtime": 406.3149, | |
| "eval_samples_per_second": 23.679, | |
| "eval_steps_per_second": 2.961, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021007483916145125, | |
| "grad_norm": 8.257246971130371, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.0523, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0026259354895181407, | |
| "grad_norm": 7.305975914001465, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.954, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026259354895181407, | |
| "eval_loss": 1.72903311252594, | |
| "eval_runtime": 406.2308, | |
| "eval_samples_per_second": 23.684, | |
| "eval_steps_per_second": 2.961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003151122587421769, | |
| "grad_norm": 3.5953474044799805, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.6887, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003501247319357521, | |
| "eval_loss": 1.3892496824264526, | |
| "eval_runtime": 406.3687, | |
| "eval_samples_per_second": 23.676, | |
| "eval_steps_per_second": 2.96, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003676309685325397, | |
| "grad_norm": 6.9651875495910645, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.558, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004201496783229025, | |
| "grad_norm": 4.267176151275635, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.1948, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004376559149196902, | |
| "eval_loss": 1.228528380393982, | |
| "eval_runtime": 406.2491, | |
| "eval_samples_per_second": 23.683, | |
| "eval_steps_per_second": 2.961, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004726683881132654, | |
| "grad_norm": 5.901070594787598, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.0971, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005251870979036281, | |
| "grad_norm": 6.64203405380249, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0402, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005251870979036281, | |
| "eval_loss": 1.1571475267410278, | |
| "eval_runtime": 406.5337, | |
| "eval_samples_per_second": 23.666, | |
| "eval_steps_per_second": 2.959, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00577705807693991, | |
| "grad_norm": 5.948985576629639, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.2086, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006127182808875662, | |
| "eval_loss": 1.0342975854873657, | |
| "eval_runtime": 406.3239, | |
| "eval_samples_per_second": 23.678, | |
| "eval_steps_per_second": 2.961, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006302245174843538, | |
| "grad_norm": 5.374086856842041, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.0343, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0068274322727471665, | |
| "grad_norm": 3.7836270332336426, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.8489, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007002494638715042, | |
| "eval_loss": 0.9912478923797607, | |
| "eval_runtime": 406.1961, | |
| "eval_samples_per_second": 23.686, | |
| "eval_steps_per_second": 2.962, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007352619370650794, | |
| "grad_norm": 7.458286285400391, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.022, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007877806468554422, | |
| "grad_norm": 5.143349647521973, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1537, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007877806468554422, | |
| "eval_loss": 0.9653515815734863, | |
| "eval_runtime": 406.4439, | |
| "eval_samples_per_second": 23.671, | |
| "eval_steps_per_second": 2.96, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00840299356645805, | |
| "grad_norm": 5.0879807472229, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.9486, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008753118298393803, | |
| "eval_loss": 0.9580356478691101, | |
| "eval_runtime": 406.5042, | |
| "eval_samples_per_second": 23.668, | |
| "eval_steps_per_second": 2.959, | |
| "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": 2.1224821132099584e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |