| { | |
| "best_metric": 1.8803279399871826, | |
| "best_model_checkpoint": "output/boris-grebenshikov/checkpoint-169", | |
| "epoch": 1.0, | |
| "global_step": 169, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00013690389360668606, | |
| "loss": 2.5933, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00013601813066569938, | |
| "loss": 2.3572, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00013455035782630487, | |
| "loss": 2.2816, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00013251324613578177, | |
| "loss": 2.2503, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00012992438165230672, | |
| "loss": 2.0864, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00012680611362733682, | |
| "loss": 2.1159, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012318536156811003, | |
| "loss": 2.0993, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011909338284586077, | |
| "loss": 1.8802, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011456550285595239, | |
| "loss": 2.0531, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010964081005941026, | |
| "loss": 1.9281, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001043618185385132, | |
| "loss": 2.1099, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.877410097954656e-05, | |
| "loss": 2.0119, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.292589525111794e-05, | |
| "loss": 1.9675, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.686768797438203e-05, | |
| "loss": 1.9512, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.065177868014528e-05, | |
| "loss": 2.047, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.433182831541305e-05, | |
| "loss": 1.9436, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.796239599704895e-05, | |
| "loss": 1.9677, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.159846801167835e-05, | |
| "loss": 1.8582, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.529498312790352e-05, | |
| "loss": 1.9952, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.9106358318734425e-05, | |
| "loss": 1.9317, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.3086018988597235e-05, | |
| "loss": 1.834, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.728593776039493e-05, | |
| "loss": 1.8923, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.1756185804197785e-05, | |
| "loss": 1.9544, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.6544500580870892e-05, | |
| "loss": 1.921, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.169587373223826e-05, | |
| "loss": 1.9539, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.725216267546246e-05, | |
| "loss": 1.9665, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3251729254682012e-05, | |
| "loss": 2.0147, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.729108569369736e-06, | |
| "loss": 1.8575, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.7147108383636075e-06, | |
| "loss": 1.8372, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.234558873329575e-06, | |
| "loss": 1.7437, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.310063428006295e-06, | |
| "loss": 1.8886, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.578383626055595e-07, | |
| "loss": 1.9129, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.895572190242788e-07, | |
| "loss": 1.8767, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8803279399871826, | |
| "eval_runtime": 11.5804, | |
| "eval_samples_per_second": 22.279, | |
| "eval_steps_per_second": 2.85, | |
| "step": 169 | |
| } | |
| ], | |
| "max_steps": 169, | |
| "num_train_epochs": 1, | |
| "total_flos": 176110829568000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |