| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.527623311908717, | |
| "eval_steps": 500, | |
| "global_step": 17500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9986295347545738e-05, | |
| "loss": 4.4247, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_gen_len": 6.267, | |
| "eval_loss": 3.5801377296447754, | |
| "eval_rouge1": 27.9882, | |
| "eval_rouge2": 8.9331, | |
| "eval_rougeL": 27.6011, | |
| "eval_rougeLsum": 27.5353, | |
| "eval_runtime": 1554.6657, | |
| "eval_samples_per_second": 1.93, | |
| "eval_steps_per_second": 0.482, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 2.959, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_gen_len": 6.267333333333333, | |
| "eval_loss": 3.238922119140625, | |
| "eval_rouge1": 34.4913, | |
| "eval_rouge2": 14.1739, | |
| "eval_rougeL": 34.2505, | |
| "eval_rougeLsum": 34.1717, | |
| "eval_runtime": 1549.8046, | |
| "eval_samples_per_second": 1.936, | |
| "eval_steps_per_second": 0.484, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.9876883405951378e-05, | |
| "loss": 2.7367, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.983262300491333, | |
| "eval_rouge1": 40.5052, | |
| "eval_rouge2": 18.725, | |
| "eval_rougeL": 40.1333, | |
| "eval_rougeLsum": 40.0554, | |
| "eval_runtime": 1542.1597, | |
| "eval_samples_per_second": 1.945, | |
| "eval_steps_per_second": 0.486, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 2.553, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_gen_len": 6.267333333333333, | |
| "eval_loss": 2.781419277191162, | |
| "eval_rouge1": 45.972, | |
| "eval_rouge2": 24.75, | |
| "eval_rougeL": 45.6989, | |
| "eval_rougeLsum": 45.6257, | |
| "eval_runtime": 1547.6212, | |
| "eval_samples_per_second": 1.938, | |
| "eval_steps_per_second": 0.485, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.9659258262890683e-05, | |
| "loss": 2.3988, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.6185145378112793, | |
| "eval_rouge1": 51.3237, | |
| "eval_rouge2": 30.8584, | |
| "eval_rougeL": 51.0697, | |
| "eval_rougeLsum": 50.9947, | |
| "eval_runtime": 1538.5542, | |
| "eval_samples_per_second": 1.95, | |
| "eval_steps_per_second": 0.487, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 2.2788, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.4821877479553223, | |
| "eval_rouge1": 55.054, | |
| "eval_rouge2": 35.9558, | |
| "eval_rougeL": 54.885, | |
| "eval_rougeLsum": 54.8263, | |
| "eval_runtime": 1535.9732, | |
| "eval_samples_per_second": 1.953, | |
| "eval_steps_per_second": 0.488, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.9335804264972018e-05, | |
| "loss": 2.185, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.372607469558716, | |
| "eval_rouge1": 58.4125, | |
| "eval_rouge2": 39.7017, | |
| "eval_rougeL": 58.2864, | |
| "eval_rougeLsum": 58.2323, | |
| "eval_runtime": 1555.498, | |
| "eval_samples_per_second": 1.929, | |
| "eval_steps_per_second": 0.482, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 2.1024, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.2966315746307373, | |
| "eval_rouge1": 60.2269, | |
| "eval_rouge2": 42.343, | |
| "eval_rougeL": 60.1064, | |
| "eval_rougeLsum": 60.015, | |
| "eval_runtime": 1539.5016, | |
| "eval_samples_per_second": 1.949, | |
| "eval_steps_per_second": 0.487, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.891006524188368e-05, | |
| "loss": 2.0395, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.2079367637634277, | |
| "eval_rouge1": 63.9442, | |
| "eval_rouge2": 47.1262, | |
| "eval_rougeL": 63.8226, | |
| "eval_rougeLsum": 63.783, | |
| "eval_runtime": 1534.6718, | |
| "eval_samples_per_second": 1.955, | |
| "eval_steps_per_second": 0.489, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 1.9929, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.142320156097412, | |
| "eval_rouge1": 66.0535, | |
| "eval_rouge2": 49.403, | |
| "eval_rougeL": 65.9837, | |
| "eval_rougeLsum": 65.9295, | |
| "eval_runtime": 1531.6986, | |
| "eval_samples_per_second": 1.959, | |
| "eval_steps_per_second": 0.49, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.8386705679454243e-05, | |
| "loss": 1.944, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.094369888305664, | |
| "eval_rouge1": 67.4662, | |
| "eval_rouge2": 50.9242, | |
| "eval_rougeL": 67.3906, | |
| "eval_rougeLsum": 67.3416, | |
| "eval_runtime": 1527.1607, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.491, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 1.902, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.0382838249206543, | |
| "eval_rouge1": 69.3267, | |
| "eval_rouge2": 53.8395, | |
| "eval_rougeL": 69.2759, | |
| "eval_rougeLsum": 69.2151, | |
| "eval_runtime": 1532.3017, | |
| "eval_samples_per_second": 1.958, | |
| "eval_steps_per_second": 0.489, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.777145961456971e-05, | |
| "loss": 1.8712, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 2.010657548904419, | |
| "eval_rouge1": 70.2771, | |
| "eval_rouge2": 54.5208, | |
| "eval_rougeL": 70.2492, | |
| "eval_rougeLsum": 70.2095, | |
| "eval_runtime": 1563.3117, | |
| "eval_samples_per_second": 1.919, | |
| "eval_steps_per_second": 0.48, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 1.8387, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.9761910438537598, | |
| "eval_rouge1": 71.145, | |
| "eval_rouge2": 56.4319, | |
| "eval_rougeL": 71.1008, | |
| "eval_rougeLsum": 71.0876, | |
| "eval_runtime": 1552.4923, | |
| "eval_samples_per_second": 1.932, | |
| "eval_steps_per_second": 0.483, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 1.7558, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.9575979709625244, | |
| "eval_rouge1": 72.527, | |
| "eval_rouge2": 58.0461, | |
| "eval_rougeL": 72.4801, | |
| "eval_rougeLsum": 72.461, | |
| "eval_runtime": 1522.5751, | |
| "eval_samples_per_second": 1.97, | |
| "eval_steps_per_second": 0.493, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 1.7363, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.9305455684661865, | |
| "eval_rouge1": 73.3884, | |
| "eval_rouge2": 59.6248, | |
| "eval_rougeL": 73.3396, | |
| "eval_rougeLsum": 73.3362, | |
| "eval_runtime": 1541.3792, | |
| "eval_samples_per_second": 1.946, | |
| "eval_steps_per_second": 0.487, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.6293203910498375e-05, | |
| "loss": 1.7245, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.9158198833465576, | |
| "eval_rouge1": 73.3565, | |
| "eval_rouge2": 58.7585, | |
| "eval_rougeL": 73.3541, | |
| "eval_rougeLsum": 73.3668, | |
| "eval_runtime": 1546.9117, | |
| "eval_samples_per_second": 1.939, | |
| "eval_steps_per_second": 0.485, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 1.7147, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.898065447807312, | |
| "eval_rouge1": 74.1688, | |
| "eval_rouge2": 59.9465, | |
| "eval_rougeL": 74.1934, | |
| "eval_rougeLsum": 74.1447, | |
| "eval_runtime": 1537.688, | |
| "eval_samples_per_second": 1.951, | |
| "eval_steps_per_second": 0.488, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.5446390350150272e-05, | |
| "loss": 1.7013, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.8747327327728271, | |
| "eval_rouge1": 75.1266, | |
| "eval_rouge2": 61.394, | |
| "eval_rougeL": 75.128, | |
| "eval_rougeLsum": 75.0856, | |
| "eval_runtime": 1526.768, | |
| "eval_samples_per_second": 1.965, | |
| "eval_steps_per_second": 0.491, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.6906, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.8567513227462769, | |
| "eval_rouge1": 75.8503, | |
| "eval_rouge2": 62.2772, | |
| "eval_rougeL": 75.8449, | |
| "eval_rougeLsum": 75.8138, | |
| "eval_runtime": 1518.2689, | |
| "eval_samples_per_second": 1.976, | |
| "eval_steps_per_second": 0.494, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.4539904997395468e-05, | |
| "loss": 1.6827, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.8478548526763916, | |
| "eval_rouge1": 75.7687, | |
| "eval_rouge2": 62.3363, | |
| "eval_rougeL": 75.7808, | |
| "eval_rougeLsum": 75.7533, | |
| "eval_runtime": 1520.7572, | |
| "eval_samples_per_second": 1.973, | |
| "eval_steps_per_second": 0.493, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 1.6808, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.8268691301345825, | |
| "eval_rouge1": 76.5635, | |
| "eval_rouge2": 63.5572, | |
| "eval_rougeL": 76.5759, | |
| "eval_rougeLsum": 76.5281, | |
| "eval_runtime": 1529.0949, | |
| "eval_samples_per_second": 1.962, | |
| "eval_steps_per_second": 0.49, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.3583679495453e-05, | |
| "loss": 1.6747, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.8204782009124756, | |
| "eval_rouge1": 76.0665, | |
| "eval_rouge2": 62.7626, | |
| "eval_rougeL": 76.0441, | |
| "eval_rougeLsum": 76.0155, | |
| "eval_runtime": 1521.0486, | |
| "eval_samples_per_second": 1.972, | |
| "eval_steps_per_second": 0.493, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 1.6628, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.8059669733047485, | |
| "eval_rouge1": 76.6687, | |
| "eval_rouge2": 63.8953, | |
| "eval_rougeL": 76.678, | |
| "eval_rougeLsum": 76.6457, | |
| "eval_runtime": 1519.6043, | |
| "eval_samples_per_second": 1.974, | |
| "eval_steps_per_second": 0.494, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.2588190451025209e-05, | |
| "loss": 1.6517, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7973886728286743, | |
| "eval_rouge1": 77.5432, | |
| "eval_rouge2": 64.831, | |
| "eval_rougeL": 77.5477, | |
| "eval_rougeLsum": 77.5112, | |
| "eval_runtime": 1514.3733, | |
| "eval_samples_per_second": 1.981, | |
| "eval_steps_per_second": 0.495, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 1.6493, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7867239713668823, | |
| "eval_rouge1": 77.6195, | |
| "eval_rouge2": 64.9393, | |
| "eval_rougeL": 77.5908, | |
| "eval_rougeLsum": 77.5498, | |
| "eval_runtime": 1514.8609, | |
| "eval_samples_per_second": 1.98, | |
| "eval_steps_per_second": 0.495, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.156434465040231e-05, | |
| "loss": 1.6435, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.780102252960205, | |
| "eval_rouge1": 77.8512, | |
| "eval_rouge2": 65.2471, | |
| "eval_rougeL": 77.8573, | |
| "eval_rougeLsum": 77.8118, | |
| "eval_runtime": 1516.9222, | |
| "eval_samples_per_second": 1.978, | |
| "eval_steps_per_second": 0.494, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 1.6189, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7743651866912842, | |
| "eval_rouge1": 78.5967, | |
| "eval_rouge2": 66.4212, | |
| "eval_rougeL": 78.6125, | |
| "eval_rougeLsum": 78.5741, | |
| "eval_runtime": 1518.2132, | |
| "eval_samples_per_second": 1.976, | |
| "eval_steps_per_second": 0.494, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.0523359562429441e-05, | |
| "loss": 1.5746, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7696142196655273, | |
| "eval_rouge1": 78.7375, | |
| "eval_rouge2": 67.0042, | |
| "eval_rougeL": 78.7704, | |
| "eval_rougeLsum": 78.6912, | |
| "eval_runtime": 1504.5573, | |
| "eval_samples_per_second": 1.994, | |
| "eval_steps_per_second": 0.498, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5767, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7685412168502808, | |
| "eval_rouge1": 78.1583, | |
| "eval_rouge2": 66.0184, | |
| "eval_rougeL": 78.1256, | |
| "eval_rougeLsum": 78.1273, | |
| "eval_runtime": 1504.2381, | |
| "eval_samples_per_second": 1.994, | |
| "eval_steps_per_second": 0.499, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 9.476640437570562e-06, | |
| "loss": 1.5713, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7626044750213623, | |
| "eval_rouge1": 78.6909, | |
| "eval_rouge2": 66.7862, | |
| "eval_rougeL": 78.7168, | |
| "eval_rougeLsum": 78.671, | |
| "eval_runtime": 1509.684, | |
| "eval_samples_per_second": 1.987, | |
| "eval_steps_per_second": 0.497, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 1.5731, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.752744436264038, | |
| "eval_rouge1": 78.9605, | |
| "eval_rouge2": 67.084, | |
| "eval_rougeL": 78.9504, | |
| "eval_rougeLsum": 78.9289, | |
| "eval_runtime": 1512.7838, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 0.496, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.43565534959769e-06, | |
| "loss": 1.5683, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.748329758644104, | |
| "eval_rouge1": 79.0099, | |
| "eval_rouge2": 67.1613, | |
| "eval_rougeL": 79.0228, | |
| "eval_rougeLsum": 79.0093, | |
| "eval_runtime": 1516.6027, | |
| "eval_samples_per_second": 1.978, | |
| "eval_steps_per_second": 0.495, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.92088309182241e-06, | |
| "loss": 1.5684, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7434362173080444, | |
| "eval_rouge1": 78.9853, | |
| "eval_rouge2": 67.0167, | |
| "eval_rougeL": 78.9846, | |
| "eval_rougeLsum": 78.9721, | |
| "eval_runtime": 1523.8295, | |
| "eval_samples_per_second": 1.969, | |
| "eval_steps_per_second": 0.492, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.411809548974792e-06, | |
| "loss": 1.5653, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_gen_len": 6.267666666666667, | |
| "eval_loss": 1.7393466234207153, | |
| "eval_rouge1": 79.413, | |
| "eval_rouge2": 67.6295, | |
| "eval_rougeL": 79.4249, | |
| "eval_rougeLsum": 79.4027, | |
| "eval_runtime": 1511.8366, | |
| "eval_samples_per_second": 1.984, | |
| "eval_steps_per_second": 0.496, | |
| "step": 17500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 30000, | |
| "num_train_epochs": 5, | |
| "save_steps": 2500, | |
| "total_flos": 7.200705320688427e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |