| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3669724770642202, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03669724770642202, | |
| "eval_loss": 6.940816402435303, | |
| "eval_runtime": 0.4894, | |
| "eval_samples_per_second": 94.001, | |
| "eval_steps_per_second": 12.261, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11009174311926606, | |
| "grad_norm": 0.44857925176620483, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9418, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1834862385321101, | |
| "eval_loss": 6.936913013458252, | |
| "eval_runtime": 0.0633, | |
| "eval_samples_per_second": 726.735, | |
| "eval_steps_per_second": 94.792, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22018348623853212, | |
| "grad_norm": 0.4511624872684479, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9388, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3302752293577982, | |
| "grad_norm": 0.44215646386146545, | |
| "learning_rate": 9e-05, | |
| "loss": 6.9322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "eval_loss": 6.922896862030029, | |
| "eval_runtime": 0.0602, | |
| "eval_samples_per_second": 763.509, | |
| "eval_steps_per_second": 99.588, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 225865089024.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |