| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9446693657219973, | |
| "eval_steps": 50, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.4132792949676514, | |
| "eval_runtime": 24.6579, | |
| "eval_samples_per_second": 4.056, | |
| "eval_steps_per_second": 0.527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.3802086114883423, | |
| "eval_runtime": 24.6958, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 0.526, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.3620883226394653, | |
| "eval_runtime": 24.6721, | |
| "eval_samples_per_second": 4.053, | |
| "eval_steps_per_second": 0.527, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.34859037399292, | |
| "eval_runtime": 24.7313, | |
| "eval_samples_per_second": 4.043, | |
| "eval_steps_per_second": 0.526, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.3401516675949097, | |
| "eval_runtime": 24.6981, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 0.526, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.3350552320480347, | |
| "eval_runtime": 24.7526, | |
| "eval_samples_per_second": 4.04, | |
| "eval_steps_per_second": 0.525, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.3288078308105469, | |
| "eval_runtime": 24.7114, | |
| "eval_samples_per_second": 4.047, | |
| "eval_steps_per_second": 0.526, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.3192832469940186, | |
| "eval_runtime": 24.7246, | |
| "eval_samples_per_second": 4.045, | |
| "eval_steps_per_second": 0.526, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.3144173622131348, | |
| "eval_runtime": 24.6861, | |
| "eval_samples_per_second": 4.051, | |
| "eval_steps_per_second": 0.527, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.224606580829757e-06, | |
| "loss": 1.3853, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.3092302083969116, | |
| "eval_runtime": 24.7017, | |
| "eval_samples_per_second": 4.048, | |
| "eval_steps_per_second": 0.526, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.303202509880066, | |
| "eval_runtime": 24.6861, | |
| "eval_samples_per_second": 4.051, | |
| "eval_steps_per_second": 0.527, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.29935884475708, | |
| "eval_runtime": 24.6791, | |
| "eval_samples_per_second": 4.052, | |
| "eval_steps_per_second": 0.527, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.2970906496047974, | |
| "eval_runtime": 24.7065, | |
| "eval_samples_per_second": 4.048, | |
| "eval_steps_per_second": 0.526, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.2959811687469482, | |
| "eval_runtime": 24.7115, | |
| "eval_samples_per_second": 4.047, | |
| "eval_steps_per_second": 0.526, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 700, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 4.49645833728e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |