| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13717421124828533, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027434842249657062, | |
| "eval_loss": 3.4267003536224365, | |
| "eval_runtime": 10.3785, | |
| "eval_samples_per_second": 14.838, | |
| "eval_steps_per_second": 7.419, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013717421124828532, | |
| "grad_norm": 2.1229054927825928, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3064, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027434842249657063, | |
| "grad_norm": 3.5053462982177734, | |
| "learning_rate": 0.0001, | |
| "loss": 2.845, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027434842249657063, | |
| "eval_loss": 2.4402740001678467, | |
| "eval_runtime": 10.4344, | |
| "eval_samples_per_second": 14.759, | |
| "eval_steps_per_second": 7.379, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 2.800006866455078, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8493, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05486968449931413, | |
| "grad_norm": 2.7812533378601074, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1243, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05486968449931413, | |
| "eval_loss": 0.7997536063194275, | |
| "eval_runtime": 10.4152, | |
| "eval_samples_per_second": 14.786, | |
| "eval_steps_per_second": 7.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06858710562414266, | |
| "grad_norm": 1.792678952217102, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8035, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "grad_norm": 2.133634090423584, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5812, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "eval_loss": 0.6047865748405457, | |
| "eval_runtime": 10.4617, | |
| "eval_samples_per_second": 14.72, | |
| "eval_steps_per_second": 7.36, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09602194787379972, | |
| "grad_norm": 2.243466377258301, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5879, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10973936899862825, | |
| "grad_norm": 1.500490427017212, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.554, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10973936899862825, | |
| "eval_loss": 0.5699788928031921, | |
| "eval_runtime": 10.5398, | |
| "eval_samples_per_second": 14.611, | |
| "eval_steps_per_second": 7.306, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": 1.647884726524353, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5496, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13717421124828533, | |
| "grad_norm": 1.6762826442718506, | |
| "learning_rate": 0.0, | |
| "loss": 0.5618, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13717421124828533, | |
| "eval_loss": 0.5613898634910583, | |
| "eval_runtime": 10.4353, | |
| "eval_samples_per_second": 14.758, | |
| "eval_steps_per_second": 7.379, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |