| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3766478342749529, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007532956685499058, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.787, | |
| "eval_samples_per_second": 20.093, | |
| "eval_steps_per_second": 10.047, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03766478342749529, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07532956685499058, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07532956685499058, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3367, | |
| "eval_samples_per_second": 23.965, | |
| "eval_steps_per_second": 11.983, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15065913370998116, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15065913370998116, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3155, | |
| "eval_samples_per_second": 24.185, | |
| "eval_steps_per_second": 12.092, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18832391713747645, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3003, | |
| "eval_samples_per_second": 24.345, | |
| "eval_steps_per_second": 12.172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.263653483992467, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3013182674199623, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3013182674199623, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3615, | |
| "eval_samples_per_second": 23.713, | |
| "eval_steps_per_second": 11.857, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3766478342749529, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3766478342749529, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2987, | |
| "eval_samples_per_second": 24.361, | |
| "eval_steps_per_second": 12.181, | |
| "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": 3428033180467200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |