| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.946428571428571, | |
| "global_step": 16500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9956320789411338e-05, | |
| "loss": 2.043, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.9825664732332886e-05, | |
| "loss": 2.0171, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.9609173219450998e-05, | |
| "loss": 1.9996, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.9308737486442045e-05, | |
| "loss": 2.0033, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.8926982092436117e-05, | |
| "loss": 1.9819, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.8467241992282842e-05, | |
| "loss": 1.9644, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.7933533402912354e-05, | |
| "loss": 1.9713, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 1.9521, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.6663465779520042e-05, | |
| "loss": 1.9435, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.5938201855735017e-05, | |
| "loss": 1.9492, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.5161062738075068e-05, | |
| "loss": 1.9399, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.4338837391175582e-05, | |
| "loss": 1.9118, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.3478708645852272e-05, | |
| "loss": 1.9172, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.2588190451025209e-05, | |
| "loss": 1.8927, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.1675062233047365e-05, | |
| "loss": 1.8941, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 1.8892, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.81301133569098e-06, | |
| "loss": 1.8915, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.880355238966923e-06, | |
| "loss": 1.8914, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.957480182103198e-06, | |
| "loss": 1.882, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 7.052448255890958e-06, | |
| "loss": 1.89, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.173165676349103e-06, | |
| "loss": 1.8947, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 5.32731371726938e-06, | |
| "loss": 1.8757, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.522281607821288e-06, | |
| "loss": 1.8693, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 1.8495, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.0623894397145837e-06, | |
| "loss": 1.8522, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.420282768545469e-06, | |
| "loss": 1.8602, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.8443913104073984e-06, | |
| "loss": 1.8625, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 1.8574, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.107552258778907e-07, | |
| "loss": 1.8522, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.611666969163243e-07, | |
| "loss": 1.8509, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.940343254660905e-07, | |
| "loss": 1.8589, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 1.852, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.5731849821833955e-08, | |
| "loss": 1.8588, | |
| "step": 16500 | |
| } | |
| ], | |
| "max_steps": 16800, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.864707281361306e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |