| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0213857998289136, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000427715996578272, | |
| "eval_loss": 0.9877161383628845, | |
| "eval_runtime": 18.7953, | |
| "eval_samples_per_second": 52.407, | |
| "eval_steps_per_second": 26.23, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00213857998289136, | |
| "grad_norm": 2.1632139682769775, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8487, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00427715996578272, | |
| "grad_norm": 1.2678030729293823, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7846, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00427715996578272, | |
| "eval_loss": 0.895944356918335, | |
| "eval_runtime": 19.1514, | |
| "eval_samples_per_second": 51.432, | |
| "eval_steps_per_second": 25.742, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00641573994867408, | |
| "grad_norm": 1.0661193132400513, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6493, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00855431993156544, | |
| "grad_norm": 1.1885366439819336, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6315, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00855431993156544, | |
| "eval_loss": 0.6547719240188599, | |
| "eval_runtime": 18.8181, | |
| "eval_samples_per_second": 52.343, | |
| "eval_steps_per_second": 26.198, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0106928999144568, | |
| "grad_norm": 1.0234185457229614, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4865, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01283147989734816, | |
| "grad_norm": 0.8162946105003357, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4356, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01283147989734816, | |
| "eval_loss": 0.5716511607170105, | |
| "eval_runtime": 18.8325, | |
| "eval_samples_per_second": 52.303, | |
| "eval_steps_per_second": 26.178, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014970059880239521, | |
| "grad_norm": 0.6465003490447998, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3828, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01710863986313088, | |
| "grad_norm": 0.8710920810699463, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3842, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01710863986313088, | |
| "eval_loss": 0.5427811741828918, | |
| "eval_runtime": 18.9249, | |
| "eval_samples_per_second": 52.048, | |
| "eval_steps_per_second": 26.05, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01924721984602224, | |
| "grad_norm": 0.9607442021369934, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.422, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0213857998289136, | |
| "grad_norm": 0.9566428065299988, | |
| "learning_rate": 0.0, | |
| "loss": 0.3988, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0213857998289136, | |
| "eval_loss": 0.5382503867149353, | |
| "eval_runtime": 18.7243, | |
| "eval_samples_per_second": 52.605, | |
| "eval_steps_per_second": 26.329, | |
| "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": 253765613518848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |