| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022443540468508907, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002244354046850891, | |
| "grad_norm": 0.0071536279283463955, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9324, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002244354046850891, | |
| "eval_loss": 11.932108879089355, | |
| "eval_runtime": 21.7961, | |
| "eval_samples_per_second": 34.456, | |
| "eval_steps_per_second": 17.251, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004488708093701782, | |
| "grad_norm": 0.006937204394489527, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9339, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0067330621405526725, | |
| "grad_norm": 0.006365339271724224, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9332, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0067330621405526725, | |
| "eval_loss": 11.932106018066406, | |
| "eval_runtime": 1.2857, | |
| "eval_samples_per_second": 584.13, | |
| "eval_steps_per_second": 292.454, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008977416187403563, | |
| "grad_norm": 0.006913006771355867, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011221770234254453, | |
| "grad_norm": 0.005801013205200434, | |
| "learning_rate": 5e-05, | |
| "loss": 11.933, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013466124281105345, | |
| "grad_norm": 0.006616393104195595, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9327, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013466124281105345, | |
| "eval_loss": 11.932095527648926, | |
| "eval_runtime": 1.2957, | |
| "eval_samples_per_second": 579.612, | |
| "eval_steps_per_second": 290.192, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015710478327956235, | |
| "grad_norm": 0.006690428126603365, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017954832374807127, | |
| "grad_norm": 0.005688569042831659, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9329, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020199186421658015, | |
| "grad_norm": 0.0057091317139565945, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9328, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020199186421658015, | |
| "eval_loss": 11.932080268859863, | |
| "eval_runtime": 1.2893, | |
| "eval_samples_per_second": 582.476, | |
| "eval_steps_per_second": 291.626, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022443540468508907, | |
| "grad_norm": 0.005243333987891674, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9326, | |
| "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": 5671747584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |