| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9976470588235294, | |
| "eval_steps": 500, | |
| "global_step": 212, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.999890203099519e-05, | |
| "loss": 1.2086, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.99725628283861e-05, | |
| "loss": 1.0943, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9890401873221642e-05, | |
| "loss": 0.916, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.975396798735198e-05, | |
| "loss": 0.8638, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9564009842765225e-05, | |
| "loss": 0.8407, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.932156982230388e-05, | |
| "loss": 0.8379, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9027978299657436e-05, | |
| "loss": 0.806, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8684846339024145e-05, | |
| "loss": 0.7773, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.829405685450202e-05, | |
| "loss": 0.7836, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.7857754277721417e-05, | |
| "loss": 0.7955, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.7378332790417275e-05, | |
| "loss": 0.7679, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.6858423186514108e-05, | |
| "loss": 0.7665, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.6300878435817115e-05, | |
| "loss": 0.7698, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.5708758028527754e-05, | |
| "loss": 0.7811, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.5085311186492206e-05, | |
| "loss": 0.7672, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.4433959033309888e-05, | |
| "loss": 0.7651, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.3758275821142382e-05, | |
| "loss": 0.7348, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.306196931723947e-05, | |
| "loss": 0.7506, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.234886045780984e-05, | |
| "loss": 0.7291, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.16228623808846e-05, | |
| "loss": 0.7273, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0887958953229349e-05, | |
| "loss": 0.7319, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0148182909136928e-05, | |
| "loss": 0.723, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.407593721062858e-06, | |
| "loss": 0.7265, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.670255323536858e-06, | |
| "loss": 0.7163, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.940213812589018e-06, | |
| "loss": 0.7213, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.2214752430635625e-06, | |
| "loss": 0.717, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.517983645656014e-06, | |
| "loss": 0.7258, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.8335993843037695e-06, | |
| "loss": 0.7135, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.172077972692553e-06, | |
| "loss": 0.7251, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.5370494661216835e-06, | |
| "loss": 0.7171, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.931998541814069e-06, | |
| "loss": 0.7152, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.360245376978779e-06, | |
| "loss": 0.7163, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.8249274295566863e-06, | |
| "loss": 0.7232, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.328982221626087e-06, | |
| "loss": 0.6938, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.875131219943187e-06, | |
| "loss": 0.6961, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.4658649020720539e-06, | |
| "loss": 0.7121, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1034290900525279e-06, | |
| "loss": 0.7038, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.898126265992912e-07, | |
| "loss": 0.7029, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.267364614580861e-07, | |
| "loss": 0.695, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.1564420780701435e-07, | |
| "loss": 0.7147, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.5769422052403172e-07, | |
| "loss": 0.7114, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.375323979063929e-08, | |
| "loss": 0.6828, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.39163491205652e-09, | |
| "loss": 0.7076, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.7019486427307129, | |
| "eval_runtime": 73.9949, | |
| "eval_samples_per_second": 9.568, | |
| "eval_steps_per_second": 0.162, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 212, | |
| "total_flos": 88567594352640.0, | |
| "train_loss": 0.7541754785573708, | |
| "train_runtime": 4987.605, | |
| "train_samples_per_second": 2.726, | |
| "train_steps_per_second": 0.043 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 212, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 88567594352640.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |