| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00726823418250536, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014536468365010721, | |
| "eval_loss": NaN, | |
| "eval_runtime": 66.5275, | |
| "eval_samples_per_second": 43.546, | |
| "eval_steps_per_second": 21.78, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000726823418250536, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001453646836501072, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001453646836501072, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.2774, | |
| "eval_samples_per_second": 45.07, | |
| "eval_steps_per_second": 22.543, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002180470254751608, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002907293673002144, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8638, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002907293673002144, | |
| "eval_loss": NaN, | |
| "eval_runtime": 59.2667, | |
| "eval_samples_per_second": 48.881, | |
| "eval_steps_per_second": 24.449, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00363411709125268, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004360940509503216, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004360940509503216, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.8191, | |
| "eval_samples_per_second": 50.986, | |
| "eval_steps_per_second": 25.502, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005087763927753753, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005814587346004288, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005814587346004288, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.8474, | |
| "eval_samples_per_second": 50.961, | |
| "eval_steps_per_second": 25.489, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0065414107642548245, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00726823418250536, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00726823418250536, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.8534, | |
| "eval_samples_per_second": 50.956, | |
| "eval_steps_per_second": 25.487, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 55356133736448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |