| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002835270768358378, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002835270768358378, | |
| "grad_norm": 0.11436523497104645, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3873, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002835270768358378, | |
| "eval_loss": 10.386615753173828, | |
| "eval_runtime": 19.1277, | |
| "eval_samples_per_second": 155.272, | |
| "eval_steps_per_second": 38.844, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005670541536716756, | |
| "grad_norm": 0.10197721421718597, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3837, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008505812305075135, | |
| "grad_norm": 0.09985292702913284, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3872, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008505812305075135, | |
| "eval_loss": 10.386556625366211, | |
| "eval_runtime": 19.1474, | |
| "eval_samples_per_second": 155.113, | |
| "eval_steps_per_second": 38.804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011341083073433513, | |
| "grad_norm": 0.10966996103525162, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3891, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001417635384179189, | |
| "grad_norm": 0.10431879758834839, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3901, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001701162461015027, | |
| "grad_norm": 0.1112552359700203, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3879, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001701162461015027, | |
| "eval_loss": 10.386096000671387, | |
| "eval_runtime": 19.5641, | |
| "eval_samples_per_second": 151.809, | |
| "eval_steps_per_second": 37.978, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001984689537850865, | |
| "grad_norm": 0.0982154831290245, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3886, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022682166146867026, | |
| "grad_norm": 0.10347899794578552, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3883, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025517436915225406, | |
| "grad_norm": 0.10859348624944687, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3829, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025517436915225406, | |
| "eval_loss": 10.385502815246582, | |
| "eval_runtime": 19.2386, | |
| "eval_samples_per_second": 154.377, | |
| "eval_steps_per_second": 38.62, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002835270768358378, | |
| "grad_norm": 0.12301714718341827, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3881, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2092097863680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |