| { | |
| "best_metric": 0.6615384615384615, | |
| "best_model_checkpoint": "./results/checkpoint-43", | |
| "epoch": 33.333333333333336, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5076923076923077, | |
| "eval_loss": 1.161078929901123, | |
| "eval_runtime": 0.2665, | |
| "eval_samples_per_second": 243.858, | |
| "eval_steps_per_second": 11.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5076923076923077, | |
| "eval_loss": 1.1464765071868896, | |
| "eval_runtime": 0.3457, | |
| "eval_samples_per_second": 188.041, | |
| "eval_steps_per_second": 8.679, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5076923076923077, | |
| "eval_loss": 1.1057497262954712, | |
| "eval_runtime": 0.3211, | |
| "eval_samples_per_second": 202.425, | |
| "eval_steps_per_second": 9.343, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5076923076923077, | |
| "eval_loss": 1.113421082496643, | |
| "eval_runtime": 0.2679, | |
| "eval_samples_per_second": 242.627, | |
| "eval_steps_per_second": 11.198, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5076923076923077, | |
| "eval_loss": 1.0864346027374268, | |
| "eval_runtime": 0.3081, | |
| "eval_samples_per_second": 210.961, | |
| "eval_steps_per_second": 9.737, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5384615384615384, | |
| "eval_loss": 0.9837771058082581, | |
| "eval_runtime": 0.3805, | |
| "eval_samples_per_second": 170.821, | |
| "eval_steps_per_second": 7.884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5404, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5538461538461539, | |
| "eval_loss": 0.9654892683029175, | |
| "eval_runtime": 0.2642, | |
| "eval_samples_per_second": 246.029, | |
| "eval_steps_per_second": 11.355, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5692307692307692, | |
| "eval_loss": 0.9630248546600342, | |
| "eval_runtime": 0.2668, | |
| "eval_samples_per_second": 243.599, | |
| "eval_steps_per_second": 11.243, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5538461538461539, | |
| "eval_loss": 0.9631487131118774, | |
| "eval_runtime": 0.4451, | |
| "eval_samples_per_second": 146.049, | |
| "eval_steps_per_second": 6.741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5384615384615384, | |
| "eval_loss": 1.0176990032196045, | |
| "eval_runtime": 0.373, | |
| "eval_samples_per_second": 174.264, | |
| "eval_steps_per_second": 8.043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5538461538461539, | |
| "eval_loss": 1.0124413967132568, | |
| "eval_runtime": 0.2736, | |
| "eval_samples_per_second": 237.589, | |
| "eval_steps_per_second": 10.966, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5692307692307692, | |
| "eval_loss": 0.9905163049697876, | |
| "eval_runtime": 0.3001, | |
| "eval_samples_per_second": 216.589, | |
| "eval_steps_per_second": 9.996, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6153846153846154, | |
| "eval_loss": 0.9472815990447998, | |
| "eval_runtime": 0.2929, | |
| "eval_samples_per_second": 221.921, | |
| "eval_steps_per_second": 10.243, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5207, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.9549360871315002, | |
| "eval_runtime": 0.2676, | |
| "eval_samples_per_second": 242.87, | |
| "eval_steps_per_second": 11.209, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5846153846153846, | |
| "eval_loss": 0.934834897518158, | |
| "eval_runtime": 0.2803, | |
| "eval_samples_per_second": 231.892, | |
| "eval_steps_per_second": 10.703, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5846153846153846, | |
| "eval_loss": 0.9018541574478149, | |
| "eval_runtime": 0.3596, | |
| "eval_samples_per_second": 180.772, | |
| "eval_steps_per_second": 8.343, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5846153846153846, | |
| "eval_loss": 0.8686960339546204, | |
| "eval_runtime": 0.3401, | |
| "eval_samples_per_second": 191.114, | |
| "eval_steps_per_second": 8.821, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5846153846153846, | |
| "eval_loss": 0.846206784248352, | |
| "eval_runtime": 0.2696, | |
| "eval_samples_per_second": 241.07, | |
| "eval_steps_per_second": 11.126, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6153846153846154, | |
| "eval_loss": 0.84183669090271, | |
| "eval_runtime": 0.2747, | |
| "eval_samples_per_second": 236.626, | |
| "eval_steps_per_second": 10.921, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5146, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.8419151306152344, | |
| "eval_runtime": 0.2979, | |
| "eval_samples_per_second": 218.221, | |
| "eval_steps_per_second": 10.072, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5692307692307692, | |
| "eval_loss": 0.8435397148132324, | |
| "eval_runtime": 0.3514, | |
| "eval_samples_per_second": 184.977, | |
| "eval_steps_per_second": 8.537, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5538461538461539, | |
| "eval_loss": 0.8414743542671204, | |
| "eval_runtime": 0.4837, | |
| "eval_samples_per_second": 134.389, | |
| "eval_steps_per_second": 6.203, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6153846153846154, | |
| "eval_loss": 0.8293341994285583, | |
| "eval_runtime": 0.4826, | |
| "eval_samples_per_second": 134.685, | |
| "eval_steps_per_second": 6.216, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.8253650665283203, | |
| "eval_runtime": 0.2849, | |
| "eval_samples_per_second": 228.165, | |
| "eval_steps_per_second": 10.531, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6153846153846154, | |
| "eval_loss": 0.8218726515769958, | |
| "eval_runtime": 0.2622, | |
| "eval_samples_per_second": 247.867, | |
| "eval_steps_per_second": 11.44, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6461538461538462, | |
| "eval_loss": 0.8194869160652161, | |
| "eval_runtime": 0.389, | |
| "eval_samples_per_second": 167.11, | |
| "eval_steps_per_second": 7.713, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6461538461538462, | |
| "eval_loss": 0.8192200660705566, | |
| "eval_runtime": 0.2763, | |
| "eval_samples_per_second": 235.224, | |
| "eval_steps_per_second": 10.857, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6307692307692307, | |
| "eval_loss": 0.8197530508041382, | |
| "eval_runtime": 0.2574, | |
| "eval_samples_per_second": 252.551, | |
| "eval_steps_per_second": 11.656, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6615384615384615, | |
| "eval_loss": 0.8229538202285767, | |
| "eval_runtime": 0.2901, | |
| "eval_samples_per_second": 224.029, | |
| "eval_steps_per_second": 10.34, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6461538461538462, | |
| "eval_loss": 0.8263610005378723, | |
| "eval_runtime": 0.2703, | |
| "eval_samples_per_second": 240.492, | |
| "eval_steps_per_second": 11.1, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6461538461538462, | |
| "eval_loss": 0.8268065452575684, | |
| "eval_runtime": 0.425, | |
| "eval_samples_per_second": 152.94, | |
| "eval_steps_per_second": 7.059, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6461538461538462, | |
| "eval_loss": 0.8266280293464661, | |
| "eval_runtime": 0.2626, | |
| "eval_samples_per_second": 247.53, | |
| "eval_steps_per_second": 11.424, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6461538461538462, | |
| "eval_loss": 0.8262693881988525, | |
| "eval_runtime": 0.2849, | |
| "eval_samples_per_second": 228.131, | |
| "eval_steps_per_second": 10.529, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 0.0, | |
| "loss": 0.4724, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "eval_accuracy": 0.6461538461538462, | |
| "eval_loss": 0.8263109922409058, | |
| "eval_runtime": 0.3713, | |
| "eval_samples_per_second": 175.053, | |
| "eval_steps_per_second": 8.079, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "step": 50, | |
| "total_flos": 5.411451203278848e+16, | |
| "train_loss": 0.4966608715057373, | |
| "train_runtime": 129.3451, | |
| "train_samples_per_second": 25.127, | |
| "train_steps_per_second": 0.387 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 5.411451203278848e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |