| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 195, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005128205128205128, | |
| "grad_norm": 0.7784475088119507, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 2.2555, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 0.8670551180839539, | |
| "learning_rate": 7.5e-05, | |
| "loss": 2.2468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 1.2530401945114136, | |
| "learning_rate": 0.00015, | |
| "loss": 2.1352, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 1.460581660270691, | |
| "learning_rate": 0.000225, | |
| "loss": 1.6865, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 2.0667366981506348, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2589, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 0.6875319480895996, | |
| "learning_rate": 0.00029939614409928584, | |
| "loss": 1.1478, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.6013126373291016, | |
| "learning_rate": 0.00029758943828979444, | |
| "loss": 1.076, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1794871794871795, | |
| "grad_norm": 0.31481531262397766, | |
| "learning_rate": 0.00029459442910437797, | |
| "loss": 1.0179, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.3045659065246582, | |
| "learning_rate": 0.00029043523059596053, | |
| "loss": 0.9824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 0.2231951653957367, | |
| "learning_rate": 0.0002851453301853628, | |
| "loss": 0.9611, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.18813718855381012, | |
| "learning_rate": 0.0002787673190402799, | |
| "loss": 0.9461, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28205128205128205, | |
| "grad_norm": 0.21799354255199432, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.9254, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.21888460218906403, | |
| "learning_rate": 0.00026296071990054165, | |
| "loss": 0.9223, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.18513959646224976, | |
| "learning_rate": 0.0002536593973480297, | |
| "loss": 0.9083, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 0.5329850316047668, | |
| "learning_rate": 0.00024352347027881003, | |
| "loss": 0.9041, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.19489431381225586, | |
| "learning_rate": 0.00023263454721781537, | |
| "loss": 0.9033, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.2275352030992508, | |
| "learning_rate": 0.0002210802993709498, | |
| "loss": 0.892, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4358974358974359, | |
| "grad_norm": 0.1980154812335968, | |
| "learning_rate": 0.00020895375474808852, | |
| "loss": 0.8903, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 0.20675401389598846, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.8815, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.48717948717948717, | |
| "grad_norm": 0.21656563878059387, | |
| "learning_rate": 0.00018337814009344714, | |
| "loss": 0.879, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.22672973573207855, | |
| "learning_rate": 0.00017013498987264832, | |
| "loss": 0.879, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 0.2003437578678131, | |
| "learning_rate": 0.00015672972455257723, | |
| "loss": 0.8746, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 0.21689733862876892, | |
| "learning_rate": 0.0001432702754474228, | |
| "loss": 0.8522, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5897435897435898, | |
| "grad_norm": 0.23330777883529663, | |
| "learning_rate": 0.0001298650101273517, | |
| "loss": 0.8732, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.211246058344841, | |
| "learning_rate": 0.00011662185990655284, | |
| "loss": 0.8594, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6410256410256411, | |
| "grad_norm": 0.2110731303691864, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.8601, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.22622446715831757, | |
| "learning_rate": 9.104624525191145e-05, | |
| "loss": 0.8555, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.19781175255775452, | |
| "learning_rate": 7.89197006290502e-05, | |
| "loss": 0.8542, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 0.2107241153717041, | |
| "learning_rate": 6.736545278218463e-05, | |
| "loss": 0.8587, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7435897435897436, | |
| "grad_norm": 0.19920115172863007, | |
| "learning_rate": 5.6476529721189974e-05, | |
| "loss": 0.8544, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.19098255038261414, | |
| "learning_rate": 4.63406026519703e-05, | |
| "loss": 0.8572, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7948717948717948, | |
| "grad_norm": 0.18926502764225006, | |
| "learning_rate": 3.7039280099458366e-05, | |
| "loss": 0.8577, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.20493926107883453, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 0.8507, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 0.18808531761169434, | |
| "learning_rate": 2.1232680959720082e-05, | |
| "loss": 0.8415, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.8717948717948718, | |
| "grad_norm": 0.18048973381519318, | |
| "learning_rate": 1.4854669814637143e-05, | |
| "loss": 0.8506, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8974358974358975, | |
| "grad_norm": 0.18150238692760468, | |
| "learning_rate": 9.564769404039419e-06, | |
| "loss": 0.8499, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.20749987661838531, | |
| "learning_rate": 5.405570895622013e-06, | |
| "loss": 0.8447, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9487179487179487, | |
| "grad_norm": 0.19975171983242035, | |
| "learning_rate": 2.4105617102055496e-06, | |
| "loss": 0.8446, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.9743589743589743, | |
| "grad_norm": 0.19153565168380737, | |
| "learning_rate": 6.038559007141397e-07, | |
| "loss": 0.8535, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.21618981659412384, | |
| "learning_rate": 0.0, | |
| "loss": 0.8477, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.0191240310668945, | |
| "eval_runtime": 1.1347, | |
| "eval_samples_per_second": 8.813, | |
| "eval_steps_per_second": 0.881, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 195, | |
| "total_flos": 5.7571825768464384e+17, | |
| "train_loss": 0.9919446505033053, | |
| "train_runtime": 2098.6313, | |
| "train_samples_per_second": 5.945, | |
| "train_steps_per_second": 0.093 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 195, | |
| "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": 5.7571825768464384e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |