| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08356545961002786, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002785515320334262, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3716, | |
| "eval_samples_per_second": 18.157, | |
| "eval_steps_per_second": 9.078, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013927576601671309, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3599, | |
| "eval_samples_per_second": 18.182, | |
| "eval_steps_per_second": 9.091, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016713091922005572, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025069637883008356, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027855153203342618, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3619, | |
| "eval_samples_per_second": 18.178, | |
| "eval_steps_per_second": 9.089, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.033426183844011144, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04178272980501393, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04178272980501393, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3737, | |
| "eval_samples_per_second": 18.152, | |
| "eval_steps_per_second": 9.076, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05013927576601671, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.055710306406685235, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3546, | |
| "eval_samples_per_second": 18.194, | |
| "eval_steps_per_second": 9.097, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0584958217270195, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06685236768802229, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06963788300835655, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3766, | |
| "eval_samples_per_second": 18.146, | |
| "eval_steps_per_second": 9.073, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07520891364902507, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08356545961002786, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08356545961002786, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3555, | |
| "eval_samples_per_second": 18.192, | |
| "eval_steps_per_second": 9.096, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9888459569233920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |