| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0052782054101605455, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017594018033868485, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.9042, | |
| "eval_samples_per_second": 40.642, | |
| "eval_steps_per_second": 20.321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005278205410160546, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008797009016934242, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.8744, | |
| "eval_samples_per_second": 40.663, | |
| "eval_steps_per_second": 20.331, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010556410820321091, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015834616230481636, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017594018033868484, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.928, | |
| "eval_samples_per_second": 40.626, | |
| "eval_steps_per_second": 20.313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021112821640642183, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0026391027050802728, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026391027050802728, | |
| "eval_loss": NaN, | |
| "eval_runtime": 59.0827, | |
| "eval_samples_per_second": 40.519, | |
| "eval_steps_per_second": 20.26, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0031669232460963272, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003518803606773697, | |
| "eval_loss": NaN, | |
| "eval_runtime": 59.1343, | |
| "eval_samples_per_second": 40.484, | |
| "eval_steps_per_second": 20.242, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036947437871123817, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004222564328128437, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004398504508467121, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.9695, | |
| "eval_samples_per_second": 40.597, | |
| "eval_steps_per_second": 20.299, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004750384869144491, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0052782054101605455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0052782054101605455, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.8719, | |
| "eval_samples_per_second": 40.665, | |
| "eval_steps_per_second": 20.332, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2401764837949440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |