| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 27.272727272727273, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6772, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 2.7022464275360107, | |
| "eval_runtime": 0.7068, | |
| "eval_samples_per_second": 8.489, | |
| "eval_steps_per_second": 1.415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7e-06, | |
| "loss": 2.8149, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 2.6998846530914307, | |
| "eval_runtime": 0.7138, | |
| "eval_samples_per_second": 8.406, | |
| "eval_steps_per_second": 1.401, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 7e-06, | |
| "loss": 2.8494, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 2.6970536708831787, | |
| "eval_runtime": 0.7302, | |
| "eval_samples_per_second": 8.216, | |
| "eval_steps_per_second": 1.369, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7e-06, | |
| "loss": 2.7035, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 2.6939141750335693, | |
| "eval_runtime": 0.7129, | |
| "eval_samples_per_second": 8.416, | |
| "eval_steps_per_second": 1.403, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5667, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 2.6903278827667236, | |
| "eval_runtime": 0.7707, | |
| "eval_samples_per_second": 7.785, | |
| "eval_steps_per_second": 1.298, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7e-06, | |
| "loss": 2.7766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 2.6863253116607666, | |
| "eval_runtime": 0.7245, | |
| "eval_samples_per_second": 8.281, | |
| "eval_steps_per_second": 1.38, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7e-06, | |
| "loss": 2.7507, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 2.6823132038116455, | |
| "eval_runtime": 0.7678, | |
| "eval_samples_per_second": 7.815, | |
| "eval_steps_per_second": 1.302, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 7e-06, | |
| "loss": 2.7033, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 2.677713632583618, | |
| "eval_runtime": 0.7464, | |
| "eval_samples_per_second": 8.038, | |
| "eval_steps_per_second": 1.34, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 7e-06, | |
| "loss": 2.714, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 2.6728098392486572, | |
| "eval_runtime": 0.7176, | |
| "eval_samples_per_second": 8.361, | |
| "eval_steps_per_second": 1.393, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 7e-06, | |
| "loss": 2.7606, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 2.6675455570220947, | |
| "eval_runtime": 0.7365, | |
| "eval_samples_per_second": 8.147, | |
| "eval_steps_per_second": 1.358, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6694, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.6618385314941406, | |
| "eval_runtime": 0.7145, | |
| "eval_samples_per_second": 8.398, | |
| "eval_steps_per_second": 1.4, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6477, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 2.6561715602874756, | |
| "eval_runtime": 0.7766, | |
| "eval_samples_per_second": 7.726, | |
| "eval_steps_per_second": 1.288, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 7e-06, | |
| "loss": 2.7613, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_loss": 2.649792432785034, | |
| "eval_runtime": 0.7178, | |
| "eval_samples_per_second": 8.359, | |
| "eval_steps_per_second": 1.393, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6446, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_loss": 2.64331316947937, | |
| "eval_runtime": 0.7629, | |
| "eval_samples_per_second": 7.865, | |
| "eval_steps_per_second": 1.311, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 7e-06, | |
| "loss": 2.7039, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "eval_loss": 2.6366422176361084, | |
| "eval_runtime": 0.7438, | |
| "eval_samples_per_second": 8.067, | |
| "eval_steps_per_second": 1.345, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5376, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "eval_loss": 2.6297147274017334, | |
| "eval_runtime": 0.7738, | |
| "eval_samples_per_second": 7.754, | |
| "eval_steps_per_second": 1.292, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6866, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "eval_loss": 2.622584581375122, | |
| "eval_runtime": 0.7654, | |
| "eval_samples_per_second": 7.839, | |
| "eval_steps_per_second": 1.307, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6996, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "eval_loss": 2.615074396133423, | |
| "eval_runtime": 0.7534, | |
| "eval_samples_per_second": 7.964, | |
| "eval_steps_per_second": 1.327, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7e-06, | |
| "loss": 2.72, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "eval_loss": 2.6072492599487305, | |
| "eval_runtime": 0.7627, | |
| "eval_samples_per_second": 7.867, | |
| "eval_steps_per_second": 1.311, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4708, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 2.5988943576812744, | |
| "eval_runtime": 0.7612, | |
| "eval_samples_per_second": 7.882, | |
| "eval_steps_per_second": 1.314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5311, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "eval_loss": 2.5901479721069336, | |
| "eval_runtime": 0.7561, | |
| "eval_samples_per_second": 7.935, | |
| "eval_steps_per_second": 1.322, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6912, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.580698013305664, | |
| "eval_runtime": 0.7525, | |
| "eval_samples_per_second": 7.973, | |
| "eval_steps_per_second": 1.329, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6089, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "eval_loss": 2.5717146396636963, | |
| "eval_runtime": 0.765, | |
| "eval_samples_per_second": 7.843, | |
| "eval_steps_per_second": 1.307, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4803, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "eval_loss": 2.5612823963165283, | |
| "eval_runtime": 0.7202, | |
| "eval_samples_per_second": 8.331, | |
| "eval_steps_per_second": 1.388, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 7e-06, | |
| "loss": 2.6576, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "eval_loss": 2.5491273403167725, | |
| "eval_runtime": 0.7237, | |
| "eval_samples_per_second": 8.291, | |
| "eval_steps_per_second": 1.382, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4848, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "eval_loss": 2.536881446838379, | |
| "eval_runtime": 0.749, | |
| "eval_samples_per_second": 8.011, | |
| "eval_steps_per_second": 1.335, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4875, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "eval_loss": 2.524549722671509, | |
| "eval_runtime": 0.7273, | |
| "eval_samples_per_second": 8.25, | |
| "eval_steps_per_second": 1.375, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5707, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "eval_loss": 2.511542558670044, | |
| "eval_runtime": 0.7341, | |
| "eval_samples_per_second": 8.174, | |
| "eval_steps_per_second": 1.362, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3694, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "eval_loss": 2.4980533123016357, | |
| "eval_runtime": 0.733, | |
| "eval_samples_per_second": 8.186, | |
| "eval_steps_per_second": 1.364, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 7e-06, | |
| "loss": 2.515, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "eval_loss": 2.4852240085601807, | |
| "eval_runtime": 0.7212, | |
| "eval_samples_per_second": 8.319, | |
| "eval_steps_per_second": 1.387, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5051, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "eval_loss": 2.471349000930786, | |
| "eval_runtime": 0.7219, | |
| "eval_samples_per_second": 8.311, | |
| "eval_steps_per_second": 1.385, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5314, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_loss": 2.456756830215454, | |
| "eval_runtime": 0.7344, | |
| "eval_samples_per_second": 8.17, | |
| "eval_steps_per_second": 1.362, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3409, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 2.4444773197174072, | |
| "eval_runtime": 0.7207, | |
| "eval_samples_per_second": 8.326, | |
| "eval_steps_per_second": 1.388, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4272, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "eval_loss": 2.4356348514556885, | |
| "eval_runtime": 0.7258, | |
| "eval_samples_per_second": 8.267, | |
| "eval_steps_per_second": 1.378, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4189, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "eval_loss": 2.428696393966675, | |
| "eval_runtime": 0.7229, | |
| "eval_samples_per_second": 8.3, | |
| "eval_steps_per_second": 1.383, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3876, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "eval_loss": 2.422900915145874, | |
| "eval_runtime": 0.7211, | |
| "eval_samples_per_second": 8.321, | |
| "eval_steps_per_second": 1.387, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 16.82, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3212, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 16.82, | |
| "eval_loss": 2.4173238277435303, | |
| "eval_runtime": 0.72, | |
| "eval_samples_per_second": 8.334, | |
| "eval_steps_per_second": 1.389, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3173, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "eval_loss": 2.4116928577423096, | |
| "eval_runtime": 0.7204, | |
| "eval_samples_per_second": 8.329, | |
| "eval_steps_per_second": 1.388, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 17.73, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3327, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 17.73, | |
| "eval_loss": 2.4064242839813232, | |
| "eval_runtime": 0.7198, | |
| "eval_samples_per_second": 8.335, | |
| "eval_steps_per_second": 1.389, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5256, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "eval_loss": 2.4015276432037354, | |
| "eval_runtime": 0.7429, | |
| "eval_samples_per_second": 8.077, | |
| "eval_steps_per_second": 1.346, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 7e-06, | |
| "loss": 2.2825, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "eval_loss": 2.3970677852630615, | |
| "eval_runtime": 0.7175, | |
| "eval_samples_per_second": 8.363, | |
| "eval_steps_per_second": 1.394, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3417, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "eval_loss": 2.3925275802612305, | |
| "eval_runtime": 0.7168, | |
| "eval_samples_per_second": 8.37, | |
| "eval_steps_per_second": 1.395, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 7e-06, | |
| "loss": 2.2123, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "eval_loss": 2.388213872909546, | |
| "eval_runtime": 0.7288, | |
| "eval_samples_per_second": 8.232, | |
| "eval_steps_per_second": 1.372, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3696, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 2.384182929992676, | |
| "eval_runtime": 0.7182, | |
| "eval_samples_per_second": 8.354, | |
| "eval_steps_per_second": 1.392, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 7e-06, | |
| "loss": 2.4359, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "eval_loss": 2.380094528198242, | |
| "eval_runtime": 0.718, | |
| "eval_samples_per_second": 8.357, | |
| "eval_steps_per_second": 1.393, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 20.91, | |
| "learning_rate": 7e-06, | |
| "loss": 2.1279, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 20.91, | |
| "eval_loss": 2.3762617111206055, | |
| "eval_runtime": 0.7166, | |
| "eval_samples_per_second": 8.372, | |
| "eval_steps_per_second": 1.395, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 21.36, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3891, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 21.36, | |
| "eval_loss": 2.3726041316986084, | |
| "eval_runtime": 0.7167, | |
| "eval_samples_per_second": 8.371, | |
| "eval_steps_per_second": 1.395, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "learning_rate": 7e-06, | |
| "loss": 2.1994, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "eval_loss": 2.36929988861084, | |
| "eval_runtime": 0.7208, | |
| "eval_samples_per_second": 8.324, | |
| "eval_steps_per_second": 1.387, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "learning_rate": 7e-06, | |
| "loss": 2.2041, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "eval_loss": 2.3658368587493896, | |
| "eval_runtime": 0.7161, | |
| "eval_samples_per_second": 8.379, | |
| "eval_steps_per_second": 1.396, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3645, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "eval_loss": 2.362556219100952, | |
| "eval_runtime": 0.7162, | |
| "eval_samples_per_second": 8.378, | |
| "eval_steps_per_second": 1.396, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 23.18, | |
| "learning_rate": 7e-06, | |
| "loss": 2.2448, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 23.18, | |
| "eval_loss": 2.359351873397827, | |
| "eval_runtime": 0.7198, | |
| "eval_samples_per_second": 8.336, | |
| "eval_steps_per_second": 1.389, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "learning_rate": 7e-06, | |
| "loss": 2.1683, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "eval_loss": 2.3562166690826416, | |
| "eval_runtime": 0.7185, | |
| "eval_samples_per_second": 8.351, | |
| "eval_steps_per_second": 1.392, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "learning_rate": 7e-06, | |
| "loss": 2.34, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "eval_loss": 2.352797746658325, | |
| "eval_runtime": 0.717, | |
| "eval_samples_per_second": 8.368, | |
| "eval_steps_per_second": 1.395, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "learning_rate": 7e-06, | |
| "loss": 2.2091, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "eval_loss": 2.349076271057129, | |
| "eval_runtime": 0.7168, | |
| "eval_samples_per_second": 8.371, | |
| "eval_steps_per_second": 1.395, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 7e-06, | |
| "loss": 2.2733, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 2.3457562923431396, | |
| "eval_runtime": 0.716, | |
| "eval_samples_per_second": 8.379, | |
| "eval_steps_per_second": 1.397, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 7e-06, | |
| "loss": 2.3123, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "eval_loss": 2.3424742221832275, | |
| "eval_runtime": 0.7162, | |
| "eval_samples_per_second": 8.378, | |
| "eval_steps_per_second": 1.396, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "learning_rate": 7e-06, | |
| "loss": 2.1236, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "eval_loss": 2.3390562534332275, | |
| "eval_runtime": 0.7167, | |
| "eval_samples_per_second": 8.372, | |
| "eval_steps_per_second": 1.395, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 26.36, | |
| "learning_rate": 7e-06, | |
| "loss": 2.328, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 26.36, | |
| "eval_loss": 2.3360955715179443, | |
| "eval_runtime": 0.732, | |
| "eval_samples_per_second": 8.197, | |
| "eval_steps_per_second": 1.366, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 7e-06, | |
| "loss": 2.117, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "eval_loss": 2.333092451095581, | |
| "eval_runtime": 0.7171, | |
| "eval_samples_per_second": 8.367, | |
| "eval_steps_per_second": 1.395, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 7e-06, | |
| "loss": 2.2671, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "eval_loss": 2.330547571182251, | |
| "eval_runtime": 0.7166, | |
| "eval_samples_per_second": 8.373, | |
| "eval_steps_per_second": 1.395, | |
| "step": 300 | |
| } | |
| ], | |
| "max_steps": 550, | |
| "num_train_epochs": 50, | |
| "total_flos": 116301968424960.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |