| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 18281, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9452983972430393e-05, | |
| "loss": 1.3461, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.8905967944860785e-05, | |
| "loss": 1.3888, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.835895191729118e-05, | |
| "loss": 1.3245, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.781193588972157e-05, | |
| "loss": 1.3348, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7264919862151964e-05, | |
| "loss": 1.3438, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6717903834582355e-05, | |
| "loss": 1.3493, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6170887807012747e-05, | |
| "loss": 1.3611, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.562387177944314e-05, | |
| "loss": 1.3614, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5076855751873532e-05, | |
| "loss": 1.3719, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4529839724303922e-05, | |
| "loss": 1.3835, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.3982823696734315e-05, | |
| "loss": 1.3944, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3435807669164707e-05, | |
| "loss": 1.3957, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.28887916415951e-05, | |
| "loss": 1.4024, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2341775614025492e-05, | |
| "loss": 1.4204, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.1794759586455884e-05, | |
| "loss": 1.4221, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1247743558886277e-05, | |
| "loss": 1.4281, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0700727531316667e-05, | |
| "loss": 1.4418, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.015371150374706e-05, | |
| "loss": 1.442, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.606695476177453e-06, | |
| "loss": 1.4512, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.059679448607846e-06, | |
| "loss": 1.4572, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.512663421038238e-06, | |
| "loss": 1.4636, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.96564739346863e-06, | |
| "loss": 1.4739, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.418631365899022e-06, | |
| "loss": 1.4867, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.871615338329414e-06, | |
| "loss": 1.488, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.324599310759806e-06, | |
| "loss": 1.5029, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.777583283190198e-06, | |
| "loss": 1.5143, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.23056725562059e-06, | |
| "loss": 1.5163, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.683551228050982e-06, | |
| "loss": 1.5327, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.136535200481375e-06, | |
| "loss": 1.5273, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.589519172911767e-06, | |
| "loss": 1.5378, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.042503145342159e-06, | |
| "loss": 1.5542, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.495487117772551e-06, | |
| "loss": 1.5605, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.948471090202943e-06, | |
| "loss": 1.5624, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.4014550626333353e-06, | |
| "loss": 1.5738, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 8.544390350637274e-07, | |
| "loss": 1.587, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.0742300749411957e-07, | |
| "loss": 1.5977, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 18281, | |
| "total_flos": 2326813943992320.0, | |
| "train_runtime": 29351.0857, | |
| "train_samples_per_second": 0.623 | |
| } | |
| ], | |
| "max_steps": 18281, | |
| "num_train_epochs": 1, | |
| "total_flos": 2326813943992320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |