| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005414771496642842, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010829542993285683, | |
| "eval_loss": 4.484375, | |
| "eval_runtime": 191.0247, | |
| "eval_samples_per_second": 20.353, | |
| "eval_steps_per_second": 10.177, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005414771496642842, | |
| "grad_norm": 5.39006233215332, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3685, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010829542993285683, | |
| "grad_norm": 5.86919641494751, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1762, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010829542993285683, | |
| "eval_loss": 2.7510037422180176, | |
| "eval_runtime": 190.2451, | |
| "eval_samples_per_second": 20.437, | |
| "eval_steps_per_second": 10.218, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016244314489928524, | |
| "grad_norm": 2.1008031368255615, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7914, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021659085986571367, | |
| "grad_norm": 2.6695444583892822, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6153, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0021659085986571367, | |
| "eval_loss": 1.4342576265335083, | |
| "eval_runtime": 187.0504, | |
| "eval_samples_per_second": 20.786, | |
| "eval_steps_per_second": 10.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002707385748321421, | |
| "grad_norm": 2.947023868560791, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.366, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003248862897985705, | |
| "grad_norm": 4.017838001251221, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5395, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003248862897985705, | |
| "eval_loss": 0.6098601222038269, | |
| "eval_runtime": 186.9724, | |
| "eval_samples_per_second": 20.795, | |
| "eval_steps_per_second": 10.397, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003790340047649989, | |
| "grad_norm": 4.869180202484131, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004331817197314273, | |
| "grad_norm": 1.2285847663879395, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3597, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004331817197314273, | |
| "eval_loss": 0.31437918543815613, | |
| "eval_runtime": 187.306, | |
| "eval_samples_per_second": 20.757, | |
| "eval_steps_per_second": 10.379, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004873294346978557, | |
| "grad_norm": 5.538555145263672, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3615, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005414771496642842, | |
| "grad_norm": 2.030707836151123, | |
| "learning_rate": 0.0, | |
| "loss": 0.3599, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005414771496642842, | |
| "eval_loss": 0.29705044627189636, | |
| "eval_runtime": 186.6731, | |
| "eval_samples_per_second": 20.828, | |
| "eval_steps_per_second": 10.414, | |
| "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": 3445173346369536.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |