| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 8436, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.7036510194404934e-05, | |
| "loss": 2.3549, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.4073020388809866e-05, | |
| "loss": 1.973, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.11095305832148e-05, | |
| "loss": 1.8373, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.814604077761973e-05, | |
| "loss": 1.7386, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.518255097202466e-05, | |
| "loss": 1.6915, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.2219061166429585e-05, | |
| "loss": 1.5726, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9255571360834523e-05, | |
| "loss": 1.3692, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.629208155523945e-05, | |
| "loss": 1.3636, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3328591749644383e-05, | |
| "loss": 1.3577, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.0365101944049315e-05, | |
| "loss": 1.3569, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.7401612138454246e-05, | |
| "loss": 1.3117, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4438122332859174e-05, | |
| "loss": 1.1396, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1474632527264106e-05, | |
| "loss": 1.0792, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.511142721669037e-06, | |
| "loss": 1.0822, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.547652916073969e-06, | |
| "loss": 1.0525, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.5841631104789e-06, | |
| "loss": 1.0456, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 8436, | |
| "total_flos": 8682442781638656.0, | |
| "train_loss": 1.4358761833990394, | |
| "train_runtime": 2342.6276, | |
| "train_samples_per_second": 35.999, | |
| "train_steps_per_second": 3.601 | |
| } | |
| ], | |
| "max_steps": 8436, | |
| "num_train_epochs": 3, | |
| "total_flos": 8682442781638656.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |