| { | |
| "best_metric": 2.248004913330078, | |
| "best_model_checkpoint": "output/linkin-park/checkpoint-140", | |
| "epoch": 2.0, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001354300570714007, | |
| "loss": 2.895, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00013021156058794955, | |
| "loss": 2.9711, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001218137945423232, | |
| "loss": 3.0184, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00011067009906946294, | |
| "loss": 2.635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.735550930058317e-05, | |
| "loss": 2.6937, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.255708249541069e-05, | |
| "loss": 2.9303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 6.703844462707114e-05, | |
| "loss": 2.5872, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.160038588088708e-05, | |
| "loss": 2.5982, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.703953841164296e-05, | |
| "loss": 2.5227, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.410726866285494e-05, | |
| "loss": 2.6876, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3470905479788493e-05, | |
| "loss": 2.8587, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.679304716725937e-06, | |
| "loss": 2.566, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.1345272679252971e-06, | |
| "loss": 2.6052, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.4942777156829834, | |
| "eval_runtime": 4.673, | |
| "eval_samples_per_second": 22.041, | |
| "eval_steps_per_second": 2.782, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.9438, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.463841438293457, | |
| "eval_runtime": 4.6348, | |
| "eval_samples_per_second": 20.929, | |
| "eval_steps_per_second": 2.805, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.7199452243268996e-06, | |
| "loss": 2.4952, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.793535661894047e-06, | |
| "loss": 2.5481, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.4966360302693133e-05, | |
| "loss": 2.6492, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.582859959249087e-05, | |
| "loss": 2.3078, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.88355754965355e-05, | |
| "loss": 2.6034, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.333506393059682e-05, | |
| "loss": 2.4777, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 6.859999999999999e-05, | |
| "loss": 2.2842, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.386493606940316e-05, | |
| "loss": 2.577, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.836442450346448e-05, | |
| "loss": 2.3194, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00011137140040750911, | |
| "loss": 2.3364, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012223363969730684, | |
| "loss": 2.3984, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00013040646433810595, | |
| "loss": 2.2814, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0001354800547756731, | |
| "loss": 2.2059, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001372, | |
| "loss": 1.9945, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.248004913330078, | |
| "eval_runtime": 4.6064, | |
| "eval_samples_per_second": 21.058, | |
| "eval_steps_per_second": 2.822, | |
| "step": 140 | |
| } | |
| ], | |
| "max_steps": 140, | |
| "num_train_epochs": 2, | |
| "total_flos": 144625139712000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |