| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0326477309826967, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000652954619653934, | |
| "eval_loss": NaN, | |
| "eval_runtime": 184.5439, | |
| "eval_samples_per_second": 13.98, | |
| "eval_steps_per_second": 1.75, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019588638589618022, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00326477309826967, | |
| "eval_loss": NaN, | |
| "eval_runtime": 184.9944, | |
| "eval_samples_per_second": 13.946, | |
| "eval_steps_per_second": 1.746, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0039177277179236044, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005876591576885406, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00652954619653934, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1188, | |
| "eval_samples_per_second": 13.937, | |
| "eval_steps_per_second": 1.745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007835455435847209, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009794319294809012, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009794319294809012, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1011, | |
| "eval_samples_per_second": 13.938, | |
| "eval_steps_per_second": 1.745, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011753183153770812, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01305909239307868, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1576, | |
| "eval_samples_per_second": 13.934, | |
| "eval_steps_per_second": 1.744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013712047012732615, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015670910871694418, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01632386549134835, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1053, | |
| "eval_samples_per_second": 13.938, | |
| "eval_steps_per_second": 1.745, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01762977473065622, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019588638589618023, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019588638589618023, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1647, | |
| "eval_samples_per_second": 13.934, | |
| "eval_steps_per_second": 1.744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021547502448579822, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022853411687887692, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1747, | |
| "eval_samples_per_second": 13.933, | |
| "eval_steps_per_second": 1.744, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023506366307541625, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.025465230166503428, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02611818478615736, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1721, | |
| "eval_samples_per_second": 13.933, | |
| "eval_steps_per_second": 1.744, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02742409402546523, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029382957884427033, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.029382957884427033, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1182, | |
| "eval_samples_per_second": 13.937, | |
| "eval_steps_per_second": 1.745, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.031341821743388835, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0326477309826967, | |
| "eval_loss": NaN, | |
| "eval_runtime": 185.1756, | |
| "eval_samples_per_second": 13.933, | |
| "eval_steps_per_second": 1.744, | |
| "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": 6.719007726816461e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |