| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9833024118738405, | |
| "eval_steps": 500, | |
| "global_step": 201, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.523809523809525e-07, | |
| "loss": 1.5933, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.761904761904762e-06, | |
| "loss": 1.4782, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.523809523809525e-06, | |
| "loss": 1.5256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 1.4709, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.904761904761905e-05, | |
| "loss": 1.5224, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 1.5039, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.9876883405951378e-05, | |
| "loss": 1.4679, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 1.4341, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.945518575599317e-05, | |
| "loss": 1.4291, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 1.4145, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.874619707139396e-05, | |
| "loss": 1.4082, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8290375725550417e-05, | |
| "loss": 1.3682, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.777145961456971e-05, | |
| "loss": 1.3838, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 1.3204, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.3371310234069824, | |
| "eval_runtime": 60.5562, | |
| "eval_samples_per_second": 8.207, | |
| "eval_steps_per_second": 2.064, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.6560590289905074e-05, | |
| "loss": 1.3366, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 1.357, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.5150380749100545e-05, | |
| "loss": 1.3083, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.4383711467890776e-05, | |
| "loss": 1.3313, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.3583679495453e-05, | |
| "loss": 1.3263, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.2756373558169992e-05, | |
| "loss": 1.343, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.190808995376545e-05, | |
| "loss": 1.3439, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 1.2764, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.0174524064372837e-05, | |
| "loss": 1.3138, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.302435262558748e-06, | |
| "loss": 1.3108, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.43565534959769e-06, | |
| "loss": 1.2986, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.580781044003324e-06, | |
| "loss": 1.2803, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 6.744318455428436e-06, | |
| "loss": 1.3083, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.2949973344802856, | |
| "eval_runtime": 60.6302, | |
| "eval_samples_per_second": 8.197, | |
| "eval_steps_per_second": 2.062, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 1.3041, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 5.151903797536631e-06, | |
| "loss": 1.2992, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 4.408070965292534e-06, | |
| "loss": 1.2984, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.7067960895016277e-06, | |
| "loss": 1.284, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 3.0534162954100264e-06, | |
| "loss": 1.3143, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.45290419777228e-06, | |
| "loss": 1.3138, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 1.3192, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.4283269929788779e-06, | |
| "loss": 1.3079, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1.012059537008332e-06, | |
| "loss": 1.3073, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.641957350279838e-07, | |
| "loss": 1.3209, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.8738304061681107e-07, | |
| "loss": 1.3137, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.8372816552336025e-07, | |
| "loss": 1.2787, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 5.4781046317267103e-08, | |
| "loss": 1.2959, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.5230484360873043e-09, | |
| "loss": 1.2921, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 1.2931873798370361, | |
| "eval_runtime": 60.4523, | |
| "eval_samples_per_second": 8.221, | |
| "eval_steps_per_second": 2.068, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "step": 201, | |
| "total_flos": 1.0527084092262973e+18, | |
| "train_loss": 1.3530203068434303, | |
| "train_runtime": 5442.6995, | |
| "train_samples_per_second": 2.376, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 201, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.0527084092262973e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |