| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.612756264236902, | |
| "eval_steps": 500, | |
| "global_step": 176, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9999323080037623e-05, | |
| "loss": 0.8679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.9983081582712684e-05, | |
| "loss": 0.8526, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.9932383577419432e-05, | |
| "loss": 0.8014, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 0.7437, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.6867304444313049, | |
| "eval_runtime": 30.7118, | |
| "eval_samples_per_second": 6.512, | |
| "eval_steps_per_second": 0.814, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.973044870579824e-05, | |
| "loss": 0.6989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.957989512315489e-05, | |
| "loss": 0.6673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.6539, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.9182161068802742e-05, | |
| "loss": 0.6372, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.621515691280365, | |
| "eval_runtime": 30.0651, | |
| "eval_samples_per_second": 6.652, | |
| "eval_steps_per_second": 0.832, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8936326403234125e-05, | |
| "loss": 0.6243, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.6186, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.8354878114129368e-05, | |
| "loss": 0.6078, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.5859256386756897, | |
| "eval_runtime": 30.0404, | |
| "eval_samples_per_second": 6.658, | |
| "eval_steps_per_second": 0.832, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.802123192755044e-05, | |
| "loss": 0.5942, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.5896, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.7273736415730488e-05, | |
| "loss": 0.5848, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.686241637868734e-05, | |
| "loss": 0.5724, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_loss": 0.562507688999176, | |
| "eval_runtime": 30.0633, | |
| "eval_samples_per_second": 6.653, | |
| "eval_steps_per_second": 0.832, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.5703, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 1.5971585917027864e-05, | |
| "loss": 0.5612, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 1.5495089780708062e-05, | |
| "loss": 0.5613, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 0.544775128364563, | |
| "eval_runtime": 30.0298, | |
| "eval_samples_per_second": 6.66, | |
| "eval_steps_per_second": 0.833, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.5509, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 1.4487991802004625e-05, | |
| "loss": 0.5486, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 1.396079766039157e-05, | |
| "loss": 0.5485, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.5427, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "eval_loss": 0.5336735844612122, | |
| "eval_runtime": 30.037, | |
| "eval_samples_per_second": 6.658, | |
| "eval_steps_per_second": 0.832, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 1.2868032327110904e-05, | |
| "loss": 0.5399, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 1.2306158707424402e-05, | |
| "loss": 0.5376, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.5388, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "eval_loss": 0.5273823142051697, | |
| "eval_runtime": 30.0618, | |
| "eval_samples_per_second": 6.653, | |
| "eval_steps_per_second": 0.832, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 1.1160929141252303e-05, | |
| "loss": 0.5321, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 1.0581448289104759e-05, | |
| "loss": 0.5323, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5326, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 9.418551710895243e-06, | |
| "loss": 0.5284, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_loss": 0.5229138731956482, | |
| "eval_runtime": 30.0491, | |
| "eval_samples_per_second": 6.656, | |
| "eval_steps_per_second": 0.832, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 8.839070858747697e-06, | |
| "loss": 0.529, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.5277, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 7.6938412925756e-06, | |
| "loss": 0.5285, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "eval_loss": 0.5188391208648682, | |
| "eval_runtime": 30.0316, | |
| "eval_samples_per_second": 6.66, | |
| "eval_steps_per_second": 0.832, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 7.131967672889101e-06, | |
| "loss": 0.5219, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.5249, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 6.039202339608432e-06, | |
| "loss": 0.5249, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 5.512008197995379e-06, | |
| "loss": 0.5222, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "eval_loss": 0.5165340304374695, | |
| "eval_runtime": 30.0644, | |
| "eval_samples_per_second": 6.652, | |
| "eval_steps_per_second": 0.832, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "step": 176, | |
| "total_flos": 1.59704785354752e+16, | |
| "train_loss": 0.5895595401525497, | |
| "train_runtime": 27383.9371, | |
| "train_samples_per_second": 2.562, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 270, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.59704785354752e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |