| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 169, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029585798816568046, | |
| "grad_norm": 2.342892423396605, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 1.0992, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05917159763313609, | |
| "grad_norm": 1.6368371604135565, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.0402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08875739644970414, | |
| "grad_norm": 0.8989769231311087, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.9533, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11834319526627218, | |
| "grad_norm": 0.6137256595940042, | |
| "learning_rate": 1.9980782984658682e-05, | |
| "loss": 0.8922, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14792899408284024, | |
| "grad_norm": 0.5492009965568149, | |
| "learning_rate": 1.9863613034027224e-05, | |
| "loss": 0.8551, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17751479289940827, | |
| "grad_norm": 0.4349573184458919, | |
| "learning_rate": 1.9641197940012136e-05, | |
| "loss": 0.8283, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20710059171597633, | |
| "grad_norm": 0.38659663740930433, | |
| "learning_rate": 1.9315910880512792e-05, | |
| "loss": 0.8229, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23668639053254437, | |
| "grad_norm": 0.4119151414508529, | |
| "learning_rate": 1.8891222681391853e-05, | |
| "loss": 0.8225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26627218934911245, | |
| "grad_norm": 0.35458480206676984, | |
| "learning_rate": 1.8371664782625287e-05, | |
| "loss": 0.8073, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2958579881656805, | |
| "grad_norm": 0.34430708054184417, | |
| "learning_rate": 1.7762780887657576e-05, | |
| "loss": 0.7977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3254437869822485, | |
| "grad_norm": 0.3838154059326915, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.7877, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35502958579881655, | |
| "grad_norm": 0.383532491946636, | |
| "learning_rate": 1.6303906161279554e-05, | |
| "loss": 0.7981, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.35083975989542854, | |
| "learning_rate": 1.5469481581224274e-05, | |
| "loss": 0.7722, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.41420118343195267, | |
| "grad_norm": 0.35395203723670016, | |
| "learning_rate": 1.4576697415156818e-05, | |
| "loss": 0.7741, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4437869822485207, | |
| "grad_norm": 0.34555629817939354, | |
| "learning_rate": 1.3635079705638298e-05, | |
| "loss": 0.7852, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47337278106508873, | |
| "grad_norm": 0.35805756615265727, | |
| "learning_rate": 1.2654675551080724e-05, | |
| "loss": 0.7667, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5029585798816568, | |
| "grad_norm": 0.3781865827387411, | |
| "learning_rate": 1.164594590280734e-05, | |
| "loss": 0.7706, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5325443786982249, | |
| "grad_norm": 0.36455865865784565, | |
| "learning_rate": 1.0619653946285948e-05, | |
| "loss": 0.7701, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5621301775147929, | |
| "grad_norm": 0.37271134883355717, | |
| "learning_rate": 9.586750257511868e-06, | |
| "loss": 0.7772, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.591715976331361, | |
| "grad_norm": 0.3429534883848641, | |
| "learning_rate": 8.558255959926533e-06, | |
| "loss": 0.753, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.591715976331361, | |
| "eval_loss": 0.7881382703781128, | |
| "eval_runtime": 1.6822, | |
| "eval_samples_per_second": 76.093, | |
| "eval_steps_per_second": 2.378, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.621301775147929, | |
| "grad_norm": 0.34272683406564375, | |
| "learning_rate": 7.545145128592009e-06, | |
| "loss": 0.757, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.650887573964497, | |
| "grad_norm": 0.35326011905545884, | |
| "learning_rate": 6.558227696373617e-06, | |
| "loss": 0.7682, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6804733727810651, | |
| "grad_norm": 0.3175593796339319, | |
| "learning_rate": 5.608034111526298e-06, | |
| "loss": 0.7623, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7100591715976331, | |
| "grad_norm": 0.30113559390386235, | |
| "learning_rate": 4.704702977392914e-06, | |
| "loss": 0.7514, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7396449704142012, | |
| "grad_norm": 0.3514515497713594, | |
| "learning_rate": 3.857872873103322e-06, | |
| "loss": 0.7538, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.32077249449415507, | |
| "learning_rate": 3.0765795095517026e-06, | |
| "loss": 0.7555, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7988165680473372, | |
| "grad_norm": 0.32980480359237835, | |
| "learning_rate": 2.369159318001937e-06, | |
| "loss": 0.7585, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8284023668639053, | |
| "grad_norm": 0.30552938976565036, | |
| "learning_rate": 1.743160500034443e-06, | |
| "loss": 0.7498, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8579881656804734, | |
| "grad_norm": 0.3199948980261291, | |
| "learning_rate": 1.2052624879351105e-06, | |
| "loss": 0.7566, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8875739644970414, | |
| "grad_norm": 0.3029762272084133, | |
| "learning_rate": 7.612046748871327e-07, | |
| "loss": 0.7666, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9171597633136095, | |
| "grad_norm": 0.30367592763134704, | |
| "learning_rate": 4.1572517541747294e-07, | |
| "loss": 0.7613, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9467455621301775, | |
| "grad_norm": 0.29238016566832153, | |
| "learning_rate": 1.7251026952640583e-07, | |
| "loss": 0.7607, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9763313609467456, | |
| "grad_norm": 0.2814543563664885, | |
| "learning_rate": 3.4155069933301535e-08, | |
| "loss": 0.7446, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 169, | |
| "total_flos": 76916824473600.0, | |
| "train_loss": 0.8026671296746067, | |
| "train_runtime": 1041.4464, | |
| "train_samples_per_second": 20.75, | |
| "train_steps_per_second": 0.162 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 169, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 76916824473600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |