| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 49.09090909090909, | |
| "eval_steps": 500, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_loss": 2.495208501815796, | |
| "eval_runtime": 2.7046, | |
| "eval_samples_per_second": 86.518, | |
| "eval_steps_per_second": 2.958, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002999814948722491, | |
| "loss": 2.5615, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.527021646499634, | |
| "eval_runtime": 2.6357, | |
| "eval_samples_per_second": 88.78, | |
| "eval_steps_per_second": 3.035, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.5362284183502197, | |
| "eval_runtime": 2.6589, | |
| "eval_samples_per_second": 88.005, | |
| "eval_steps_per_second": 3.009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 2.5341787338256836, | |
| "eval_runtime": 2.6589, | |
| "eval_samples_per_second": 88.007, | |
| "eval_steps_per_second": 3.009, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 2.2734625339508057, | |
| "eval_runtime": 2.6648, | |
| "eval_samples_per_second": 87.812, | |
| "eval_steps_per_second": 3.002, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 2.3209266662597656, | |
| "eval_runtime": 2.6531, | |
| "eval_samples_per_second": 88.198, | |
| "eval_steps_per_second": 3.015, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 2.1017019748687744, | |
| "eval_runtime": 2.6605, | |
| "eval_samples_per_second": 87.954, | |
| "eval_steps_per_second": 3.007, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.00029953760005996916, | |
| "loss": 2.363, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "eval_loss": 2.012136697769165, | |
| "eval_runtime": 2.6573, | |
| "eval_samples_per_second": 88.061, | |
| "eval_steps_per_second": 3.011, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "eval_loss": 2.0751442909240723, | |
| "eval_runtime": 2.6638, | |
| "eval_samples_per_second": 87.844, | |
| "eval_steps_per_second": 3.003, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 1.964595079421997, | |
| "eval_runtime": 2.7098, | |
| "eval_samples_per_second": 86.353, | |
| "eval_steps_per_second": 2.952, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 1.8911688327789307, | |
| "eval_runtime": 2.6643, | |
| "eval_samples_per_second": 87.829, | |
| "eval_steps_per_second": 3.003, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 1.809972882270813, | |
| "eval_runtime": 2.6547, | |
| "eval_samples_per_second": 88.146, | |
| "eval_steps_per_second": 3.014, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "eval_loss": 1.8143646717071533, | |
| "eval_runtime": 2.6683, | |
| "eval_samples_per_second": 87.697, | |
| "eval_steps_per_second": 2.998, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "eval_loss": 1.7983335256576538, | |
| "eval_runtime": 2.6503, | |
| "eval_samples_per_second": 88.291, | |
| "eval_steps_per_second": 3.018, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "eval_loss": 1.7633870840072632, | |
| "eval_runtime": 2.6612, | |
| "eval_samples_per_second": 87.931, | |
| "eval_steps_per_second": 3.006, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 0.00029815325108927063, | |
| "loss": 1.9009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "eval_loss": 1.762792706489563, | |
| "eval_runtime": 2.6498, | |
| "eval_samples_per_second": 88.31, | |
| "eval_steps_per_second": 3.019, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "eval_loss": 1.7354298830032349, | |
| "eval_runtime": 2.6595, | |
| "eval_samples_per_second": 87.986, | |
| "eval_steps_per_second": 3.008, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "eval_loss": 1.7343316078186035, | |
| "eval_runtime": 2.6543, | |
| "eval_samples_per_second": 88.159, | |
| "eval_steps_per_second": 3.014, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "eval_loss": 1.7231522798538208, | |
| "eval_runtime": 2.6679, | |
| "eval_samples_per_second": 87.709, | |
| "eval_steps_per_second": 2.999, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "eval_loss": 1.6737045049667358, | |
| "eval_runtime": 2.6731, | |
| "eval_samples_per_second": 87.538, | |
| "eval_steps_per_second": 2.993, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "eval_loss": 1.6417571306228638, | |
| "eval_runtime": 2.6611, | |
| "eval_samples_per_second": 87.935, | |
| "eval_steps_per_second": 3.006, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "eval_loss": 1.663546085357666, | |
| "eval_runtime": 2.7084, | |
| "eval_samples_per_second": 86.399, | |
| "eval_steps_per_second": 2.954, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "eval_loss": 1.6280120611190796, | |
| "eval_runtime": 2.6541, | |
| "eval_samples_per_second": 88.166, | |
| "eval_steps_per_second": 3.014, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 23.15, | |
| "learning_rate": 0.0002958554880596515, | |
| "loss": 1.7031, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 23.15, | |
| "eval_loss": 1.6042001247406006, | |
| "eval_runtime": 2.6431, | |
| "eval_samples_per_second": 88.533, | |
| "eval_steps_per_second": 3.027, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 23.15, | |
| "eval_loss": 1.6120343208312988, | |
| "eval_runtime": 2.6568, | |
| "eval_samples_per_second": 88.076, | |
| "eval_steps_per_second": 3.011, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "eval_loss": 1.579213261604309, | |
| "eval_runtime": 2.6609, | |
| "eval_samples_per_second": 87.94, | |
| "eval_steps_per_second": 3.007, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "eval_loss": 1.6127510070800781, | |
| "eval_runtime": 2.6566, | |
| "eval_samples_per_second": 88.082, | |
| "eval_steps_per_second": 3.011, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "eval_loss": 1.5467751026153564, | |
| "eval_runtime": 2.655, | |
| "eval_samples_per_second": 88.136, | |
| "eval_steps_per_second": 3.013, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "eval_loss": 1.530348539352417, | |
| "eval_runtime": 2.6531, | |
| "eval_samples_per_second": 88.197, | |
| "eval_steps_per_second": 3.015, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "eval_loss": 1.5159918069839478, | |
| "eval_runtime": 2.6518, | |
| "eval_samples_per_second": 88.241, | |
| "eval_steps_per_second": 3.017, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 30.06, | |
| "eval_loss": 1.5194865465164185, | |
| "eval_runtime": 2.6595, | |
| "eval_samples_per_second": 87.987, | |
| "eval_steps_per_second": 3.008, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 31.15, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 1.5968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 31.15, | |
| "eval_loss": 1.5098381042480469, | |
| "eval_runtime": 2.6396, | |
| "eval_samples_per_second": 88.651, | |
| "eval_steps_per_second": 3.031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 31.15, | |
| "eval_loss": 1.4774686098098755, | |
| "eval_runtime": 2.6606, | |
| "eval_samples_per_second": 87.951, | |
| "eval_steps_per_second": 3.007, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 33.09, | |
| "eval_loss": 1.4770317077636719, | |
| "eval_runtime": 2.6523, | |
| "eval_samples_per_second": 88.225, | |
| "eval_steps_per_second": 3.016, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 33.09, | |
| "eval_loss": 1.4588351249694824, | |
| "eval_runtime": 2.6529, | |
| "eval_samples_per_second": 88.205, | |
| "eval_steps_per_second": 3.016, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 35.03, | |
| "eval_loss": 1.4474384784698486, | |
| "eval_runtime": 2.6678, | |
| "eval_samples_per_second": 87.711, | |
| "eval_steps_per_second": 2.999, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 36.12, | |
| "eval_loss": 1.424033761024475, | |
| "eval_runtime": 2.6514, | |
| "eval_samples_per_second": 88.254, | |
| "eval_steps_per_second": 3.017, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 36.12, | |
| "eval_loss": 1.4164339303970337, | |
| "eval_runtime": 2.6554, | |
| "eval_samples_per_second": 88.121, | |
| "eval_steps_per_second": 3.013, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 38.06, | |
| "eval_loss": 1.4059854745864868, | |
| "eval_runtime": 2.6536, | |
| "eval_samples_per_second": 88.181, | |
| "eval_steps_per_second": 3.015, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "learning_rate": 0.000288581929876693, | |
| "loss": 1.4776, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "eval_loss": 1.3752561807632446, | |
| "eval_runtime": 2.6459, | |
| "eval_samples_per_second": 88.439, | |
| "eval_steps_per_second": 3.024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "eval_loss": 1.385780930519104, | |
| "eval_runtime": 2.667, | |
| "eval_samples_per_second": 87.738, | |
| "eval_steps_per_second": 3.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 41.09, | |
| "eval_loss": 1.3821604251861572, | |
| "eval_runtime": 2.6548, | |
| "eval_samples_per_second": 88.141, | |
| "eval_steps_per_second": 3.013, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 41.09, | |
| "eval_loss": 1.3268494606018066, | |
| "eval_runtime": 2.6901, | |
| "eval_samples_per_second": 86.986, | |
| "eval_steps_per_second": 2.974, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 43.03, | |
| "eval_loss": 1.3443068265914917, | |
| "eval_runtime": 2.6512, | |
| "eval_samples_per_second": 88.263, | |
| "eval_steps_per_second": 3.018, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "eval_loss": 1.3258930444717407, | |
| "eval_runtime": 2.6544, | |
| "eval_samples_per_second": 88.156, | |
| "eval_steps_per_second": 3.014, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "eval_loss": 1.311697006225586, | |
| "eval_runtime": 2.6815, | |
| "eval_samples_per_second": 87.264, | |
| "eval_steps_per_second": 2.983, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 46.06, | |
| "eval_loss": 1.3104833364486694, | |
| "eval_runtime": 2.6829, | |
| "eval_samples_per_second": 87.218, | |
| "eval_steps_per_second": 2.982, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 47.15, | |
| "learning_rate": 0.00028365097862825513, | |
| "loss": 1.3585, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 47.15, | |
| "eval_loss": 1.2553305625915527, | |
| "eval_runtime": 2.8251, | |
| "eval_samples_per_second": 82.83, | |
| "eval_steps_per_second": 2.832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 47.15, | |
| "eval_loss": 1.275472640991211, | |
| "eval_runtime": 2.6596, | |
| "eval_samples_per_second": 87.983, | |
| "eval_steps_per_second": 3.008, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 49.09, | |
| "eval_loss": 1.2036432027816772, | |
| "eval_runtime": 2.6726, | |
| "eval_samples_per_second": 87.554, | |
| "eval_steps_per_second": 2.993, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 49.09, | |
| "step": 31, | |
| "total_flos": 8700902454067200.0, | |
| "train_loss": 1.7344687215743526, | |
| "train_runtime": 3811.391, | |
| "train_samples_per_second": 27.51, | |
| "train_steps_per_second": 0.052 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 8700902454067200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |