| { | |
| "best_metric": 0.23951096832752228, | |
| "best_model_checkpoint": "./text2sql/codellama_instruct_spider_e10/checkpoint-500", | |
| "epoch": 8.868360277136258, | |
| "eval_steps": 100, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.08641975308642e-07, | |
| "loss": 1.3897, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 1.3449, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.822, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.5313276648521423, | |
| "eval_runtime": 34.4984, | |
| "eval_samples_per_second": 29.972, | |
| "eval_steps_per_second": 3.768, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.4342, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.9251379038613084e-05, | |
| "loss": 0.3014, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.2763093411922455, | |
| "eval_runtime": 34.3952, | |
| "eval_samples_per_second": 30.062, | |
| "eval_steps_per_second": 3.78, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.826635145784082e-05, | |
| "loss": 0.2401, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.728132387706856e-05, | |
| "loss": 0.2091, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.24685852229595184, | |
| "eval_runtime": 34.5214, | |
| "eval_samples_per_second": 29.952, | |
| "eval_steps_per_second": 3.766, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.1837, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.5311268715524035e-05, | |
| "loss": 0.1697, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.2400880753993988, | |
| "eval_runtime": 34.3334, | |
| "eval_samples_per_second": 30.116, | |
| "eval_steps_per_second": 3.786, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.432624113475177e-05, | |
| "loss": 0.1589, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.334121355397952e-05, | |
| "loss": 0.1495, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.23951096832752228, | |
| "eval_runtime": 34.3515, | |
| "eval_samples_per_second": 30.101, | |
| "eval_steps_per_second": 3.784, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.235618597320725e-05, | |
| "loss": 0.1356, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.1371158392434986e-05, | |
| "loss": 0.1256, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.2525351345539093, | |
| "eval_runtime": 34.4715, | |
| "eval_samples_per_second": 29.996, | |
| "eval_steps_per_second": 3.771, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.0386130811662727e-05, | |
| "loss": 0.1162, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.940110323089047e-05, | |
| "loss": 0.1097, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.2641294002532959, | |
| "eval_runtime": 34.4325, | |
| "eval_samples_per_second": 30.03, | |
| "eval_steps_per_second": 3.776, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.84160756501182e-05, | |
| "loss": 0.1059, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.743104806934594e-05, | |
| "loss": 0.1107, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.2617126703262329, | |
| "eval_runtime": 34.3286, | |
| "eval_samples_per_second": 30.121, | |
| "eval_steps_per_second": 3.787, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 3.6446020488573684e-05, | |
| "loss": 0.0929, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.546099290780142e-05, | |
| "loss": 0.0951, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.26825329661369324, | |
| "eval_runtime": 34.3778, | |
| "eval_samples_per_second": 30.078, | |
| "eval_steps_per_second": 3.782, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 3.447596532702916e-05, | |
| "loss": 0.0885, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 3.349093774625689e-05, | |
| "loss": 0.0882, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_loss": 0.28923752903938293, | |
| "eval_runtime": 34.5013, | |
| "eval_samples_per_second": 29.97, | |
| "eval_steps_per_second": 3.768, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 3.2505910165484634e-05, | |
| "loss": 0.0861, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 3.1520882584712375e-05, | |
| "loss": 0.0818, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_loss": 0.31338369846343994, | |
| "eval_runtime": 34.3826, | |
| "eval_samples_per_second": 30.073, | |
| "eval_steps_per_second": 3.781, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 3.053585500394011e-05, | |
| "loss": 0.0714, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.9550827423167847e-05, | |
| "loss": 0.075, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 0.2977830767631531, | |
| "eval_runtime": 34.4574, | |
| "eval_samples_per_second": 30.008, | |
| "eval_steps_per_second": 3.773, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.8565799842395592e-05, | |
| "loss": 0.0725, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.758077226162333e-05, | |
| "loss": 0.0745, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 0.3094833493232727, | |
| "eval_runtime": 34.5265, | |
| "eval_samples_per_second": 29.948, | |
| "eval_steps_per_second": 3.765, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 2.6595744680851064e-05, | |
| "loss": 0.0737, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.56107171000788e-05, | |
| "loss": 0.0642, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 0.32607167959213257, | |
| "eval_runtime": 34.3998, | |
| "eval_samples_per_second": 30.058, | |
| "eval_steps_per_second": 3.779, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 2.4625689519306542e-05, | |
| "loss": 0.0667, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.364066193853428e-05, | |
| "loss": 0.0622, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "eval_loss": 0.3201189637184143, | |
| "eval_runtime": 34.3251, | |
| "eval_samples_per_second": 30.124, | |
| "eval_steps_per_second": 3.787, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 2.2655634357762018e-05, | |
| "loss": 0.0582, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2.167060677698976e-05, | |
| "loss": 0.0573, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_loss": 0.33428019285202026, | |
| "eval_runtime": 34.4673, | |
| "eval_samples_per_second": 29.999, | |
| "eval_steps_per_second": 3.772, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 2.0685579196217493e-05, | |
| "loss": 0.0562, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.9700551615445234e-05, | |
| "loss": 0.0552, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "eval_loss": 0.3396373391151428, | |
| "eval_runtime": 34.4691, | |
| "eval_samples_per_second": 29.998, | |
| "eval_steps_per_second": 3.771, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.871552403467297e-05, | |
| "loss": 0.0535, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.773049645390071e-05, | |
| "loss": 0.0523, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "eval_loss": 0.3602007329463959, | |
| "eval_runtime": 34.3058, | |
| "eval_samples_per_second": 30.141, | |
| "eval_steps_per_second": 3.789, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 1.6745468873128447e-05, | |
| "loss": 0.0513, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 1.5760441292356188e-05, | |
| "loss": 0.0538, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_loss": 0.34643229842185974, | |
| "eval_runtime": 34.374, | |
| "eval_samples_per_second": 30.081, | |
| "eval_steps_per_second": 3.782, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 1.4775413711583924e-05, | |
| "loss": 0.0457, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.3790386130811665e-05, | |
| "loss": 0.0467, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_loss": 0.3621950149536133, | |
| "eval_runtime": 34.4567, | |
| "eval_samples_per_second": 30.009, | |
| "eval_steps_per_second": 3.773, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.28053585500394e-05, | |
| "loss": 0.0471, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 1.182033096926714e-05, | |
| "loss": 0.0465, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "eval_loss": 0.3696867823600769, | |
| "eval_runtime": 34.3098, | |
| "eval_samples_per_second": 30.137, | |
| "eval_steps_per_second": 3.789, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 1.083530338849488e-05, | |
| "loss": 0.0442, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 9.850275807722617e-06, | |
| "loss": 0.044, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "eval_loss": 0.38901907205581665, | |
| "eval_runtime": 34.3303, | |
| "eval_samples_per_second": 30.119, | |
| "eval_steps_per_second": 3.787, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 8.865248226950355e-06, | |
| "loss": 0.0409, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 7.880220646178094e-06, | |
| "loss": 0.043, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "eval_loss": 0.37854906916618347, | |
| "eval_runtime": 34.4655, | |
| "eval_samples_per_second": 30.001, | |
| "eval_steps_per_second": 3.772, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 6.895193065405832e-06, | |
| "loss": 0.0404, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 5.91016548463357e-06, | |
| "loss": 0.0375, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "eval_loss": 0.386026531457901, | |
| "eval_runtime": 34.3357, | |
| "eval_samples_per_second": 30.114, | |
| "eval_steps_per_second": 3.786, | |
| "step": 2400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2700, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "total_flos": 7.333897698361344e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |