| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00922636896249481, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001845273792498962, | |
| "eval_loss": NaN, | |
| "eval_runtime": 630.9319, | |
| "eval_samples_per_second": 14.466, | |
| "eval_steps_per_second": 1.808, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005535821377496887, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000922636896249481, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.3548, | |
| "eval_samples_per_second": 14.456, | |
| "eval_steps_per_second": 1.807, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011071642754993773, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016607464132490659, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001845273792498962, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.6033, | |
| "eval_samples_per_second": 14.451, | |
| "eval_steps_per_second": 1.807, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022143285509987547, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002767910688748443, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002767910688748443, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.533, | |
| "eval_samples_per_second": 14.452, | |
| "eval_steps_per_second": 1.807, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033214928264981318, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003690547584997924, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.3699, | |
| "eval_samples_per_second": 14.456, | |
| "eval_steps_per_second": 1.807, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00387507496424782, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004428657101997509, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004613184481247405, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.0689, | |
| "eval_samples_per_second": 14.463, | |
| "eval_steps_per_second": 1.808, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004982239239747197, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005535821377496886, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005535821377496886, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.1255, | |
| "eval_samples_per_second": 14.461, | |
| "eval_steps_per_second": 1.808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006089403515246575, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006458458273746367, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.0194, | |
| "eval_samples_per_second": 14.464, | |
| "eval_steps_per_second": 1.808, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0066429856529962635, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007196567790745952, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007381095169995848, | |
| "eval_loss": NaN, | |
| "eval_runtime": 630.8367, | |
| "eval_samples_per_second": 14.468, | |
| "eval_steps_per_second": 1.809, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00775014992849564, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00830373206624533, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00830373206624533, | |
| "eval_loss": NaN, | |
| "eval_runtime": 630.7275, | |
| "eval_samples_per_second": 14.471, | |
| "eval_steps_per_second": 1.809, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008857314203995019, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00922636896249481, | |
| "eval_loss": NaN, | |
| "eval_runtime": 630.0096, | |
| "eval_samples_per_second": 14.487, | |
| "eval_steps_per_second": 1.811, | |
| "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": 7.15499004493824e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |