| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9218407596785974, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.878256635013392e-05, | |
| "loss": 2.6057, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7565132700267836e-05, | |
| "loss": 1.6183, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.6347699050401754e-05, | |
| "loss": 1.4458, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5130265400535673e-05, | |
| "loss": 1.3302, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.3912831750669588e-05, | |
| "loss": 1.2907, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.1919312477111816, | |
| "eval_runtime": 31.0955, | |
| "eval_samples_per_second": 339.921, | |
| "eval_steps_per_second": 10.645, | |
| "step": 2738 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.2695398100803507e-05, | |
| "loss": 1.1433, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.1477964450937425e-05, | |
| "loss": 1.0745, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.0260530801071342e-05, | |
| "loss": 1.0585, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.043097151205261e-06, | |
| "loss": 1.0363, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.825663501339178e-06, | |
| "loss": 1.0204, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.1315094232559204, | |
| "eval_runtime": 31.3264, | |
| "eval_samples_per_second": 337.415, | |
| "eval_steps_per_second": 10.566, | |
| "step": 5476 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.608229851473095e-06, | |
| "loss": 1.0234, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.390796201607013e-06, | |
| "loss": 0.8935, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.17336255174093e-06, | |
| "loss": 0.8695, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.9559289018748483e-06, | |
| "loss": 0.8781, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.7384952520087656e-06, | |
| "loss": 0.8728, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.210616021426833e-07, | |
| "loss": 0.8542, | |
| "step": 8000 | |
| } | |
| ], | |
| "max_steps": 8214, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.5082063552093184e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |