| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018597731076808628, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003719546215361726, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.6568, | |
| "eval_samples_per_second": 15.163, | |
| "eval_steps_per_second": 7.581, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001859773107680863, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003719546215361726, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003719546215361726, | |
| "eval_loss": NaN, | |
| "eval_runtime": 147.4322, | |
| "eval_samples_per_second": 7.678, | |
| "eval_steps_per_second": 3.839, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0055793193230425885, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007439092430723452, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007439092430723452, | |
| "eval_loss": NaN, | |
| "eval_runtime": 129.245, | |
| "eval_samples_per_second": 8.759, | |
| "eval_steps_per_second": 4.379, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009298865538404314, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011158638646085177, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011158638646085177, | |
| "eval_loss": NaN, | |
| "eval_runtime": 124.8955, | |
| "eval_samples_per_second": 9.064, | |
| "eval_steps_per_second": 4.532, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01301841175376604, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014878184861446904, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014878184861446904, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.0365, | |
| "eval_samples_per_second": 5.745, | |
| "eval_steps_per_second": 2.873, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016737957969127765, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018597731076808628, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018597731076808628, | |
| "eval_loss": NaN, | |
| "eval_runtime": 210.9812, | |
| "eval_samples_per_second": 5.365, | |
| "eval_steps_per_second": 2.683, | |
| "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": 9432777665544192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |