| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.5629515647888184, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.5660052299499512, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1775, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.7450891733169556, | |
| "learning_rate": 0.0001, | |
| "loss": 1.048, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.785325050354004, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0855, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 2.3252322673797607, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9265, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.5729879140853882, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9402, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 1.5131912231445312, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9867, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.9407297372817993, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8494, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 1.085139513015747, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8612, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.0694725513458252, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.8292067050933838, | |
| "eval_runtime": 53.3995, | |
| "eval_samples_per_second": 9.363, | |
| "eval_steps_per_second": 4.682, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.7079308032989502, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8869, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.5450018644332886, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9056, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 1.4224787950515747, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8426, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 2.317502737045288, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1121, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.5484294891357422, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7657, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.1524784564971924, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9395, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 1.3373467922210693, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8741, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.813785195350647, | |
| "learning_rate": 0.0001, | |
| "loss": 0.807, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1.3544365167617798, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8619, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.4264659881591797, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7061, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.7746801972389221, | |
| "eval_runtime": 53.3696, | |
| "eval_samples_per_second": 9.369, | |
| "eval_steps_per_second": 4.684, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 1.9158445596694946, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8594, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.9574500322341919, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8221, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 1.2509143352508545, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7963, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.714758038520813, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7244, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.070537805557251, | |
| "learning_rate": 0.0001, | |
| "loss": 0.784, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 3.861132860183716, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8176, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 1.2554326057434082, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8537, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.9133288264274597, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7829, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 1.508233666419983, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9645, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.0573885440826416, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7912, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.7474251985549927, | |
| "eval_runtime": 53.3631, | |
| "eval_samples_per_second": 9.37, | |
| "eval_steps_per_second": 4.685, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 1.4665676355361938, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8004, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.0176584720611572, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8841, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 2.208796501159668, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8888, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 1.3332535028457642, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7775, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 2.814683675765991, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7112, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.540370225906372, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8344, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 1.5666872262954712, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7647, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 1.2998279333114624, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8868, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 1.2700724601745605, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8204, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.0913368463516235, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7203, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.7208259105682373, | |
| "eval_runtime": 53.3297, | |
| "eval_samples_per_second": 9.376, | |
| "eval_steps_per_second": 4.688, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 1.0129300355911255, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6732, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 1.3054537773132324, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7467, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 1.4525396823883057, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8085, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 1.1094130277633667, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7971, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.422092318534851, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7452, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 1.9026339054107666, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9912, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.0568705797195435, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7249, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.3295648097991943, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6573, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 1.215010404586792, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8908, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9312228560447693, | |
| "learning_rate": 0.0001, | |
| "loss": 0.714, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.7121768593788147, | |
| "eval_runtime": 53.3521, | |
| "eval_samples_per_second": 9.372, | |
| "eval_steps_per_second": 4.686, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.294978471477248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |