| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.822824812681584, | |
| "global_step": 150000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 0.8907, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 0.7216, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.9141247272491455, | |
| "eval_runtime": 1.2377, | |
| "eval_samples_per_second": 807.918, | |
| "eval_steps_per_second": 12.927, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 0.7122, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 0.7114, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.9156034588813782, | |
| "eval_runtime": 1.1631, | |
| "eval_samples_per_second": 859.777, | |
| "eval_steps_per_second": 13.756, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.7111, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 0.711, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.915696918964386, | |
| "eval_runtime": 1.149, | |
| "eval_samples_per_second": 870.294, | |
| "eval_steps_per_second": 13.925, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.7107, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 0.7102, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.8820520043373108, | |
| "eval_runtime": 1.2331, | |
| "eval_samples_per_second": 810.943, | |
| "eval_steps_per_second": 12.975, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 0.7096, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.709, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.8773962259292603, | |
| "eval_runtime": 1.22, | |
| "eval_samples_per_second": 819.664, | |
| "eval_steps_per_second": 13.115, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.599999999999999e-05, | |
| "loss": 0.7087, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 0.7083, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.8944988250732422, | |
| "eval_runtime": 1.1878, | |
| "eval_samples_per_second": 841.893, | |
| "eval_steps_per_second": 13.47, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.8e-05, | |
| "loss": 0.6868, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.6516, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.8944807648658752, | |
| "eval_runtime": 1.2213, | |
| "eval_samples_per_second": 818.801, | |
| "eval_steps_per_second": 13.101, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.6267, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 0.6042, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.8855597972869873, | |
| "eval_runtime": 1.1662, | |
| "eval_samples_per_second": 857.462, | |
| "eval_steps_per_second": 13.719, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000102, | |
| "loss": 0.5883, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 0.5732, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.8907042741775513, | |
| "eval_runtime": 1.2023, | |
| "eval_samples_per_second": 831.767, | |
| "eval_steps_per_second": 13.308, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 0.559, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.5506, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.8921875953674316, | |
| "eval_runtime": 1.197, | |
| "eval_samples_per_second": 835.455, | |
| "eval_steps_per_second": 13.367, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00012599999999999997, | |
| "loss": 0.5444, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00013199999999999998, | |
| "loss": 0.5385, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.8903993964195251, | |
| "eval_runtime": 1.1996, | |
| "eval_samples_per_second": 833.63, | |
| "eval_steps_per_second": 13.338, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000138, | |
| "loss": 0.532, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 0.5276, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.8864779472351074, | |
| "eval_runtime": 1.1846, | |
| "eval_samples_per_second": 844.173, | |
| "eval_steps_per_second": 13.507, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00015, | |
| "loss": 0.5218, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.000156, | |
| "loss": 0.517, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.88374263048172, | |
| "eval_runtime": 1.1943, | |
| "eval_samples_per_second": 837.343, | |
| "eval_steps_per_second": 13.397, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.000162, | |
| "loss": 0.5124, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.000168, | |
| "loss": 0.5077, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.8863275647163391, | |
| "eval_runtime": 1.1844, | |
| "eval_samples_per_second": 844.316, | |
| "eval_steps_per_second": 13.509, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 0.5027, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.498, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.8769687414169312, | |
| "eval_runtime": 1.1484, | |
| "eval_samples_per_second": 870.806, | |
| "eval_steps_per_second": 13.933, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.000186, | |
| "loss": 0.4938, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019199999999999998, | |
| "loss": 0.4897, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.8793530464172363, | |
| "eval_runtime": 1.2247, | |
| "eval_samples_per_second": 816.516, | |
| "eval_steps_per_second": 13.064, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.000198, | |
| "loss": 0.4849, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.000204, | |
| "loss": 0.4791, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.879580557346344, | |
| "eval_runtime": 1.1672, | |
| "eval_samples_per_second": 856.75, | |
| "eval_steps_per_second": 13.708, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.4744, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00021599999999999996, | |
| "loss": 0.4698, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.8753651976585388, | |
| "eval_runtime": 1.1516, | |
| "eval_samples_per_second": 868.392, | |
| "eval_steps_per_second": 13.894, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00022199999999999998, | |
| "loss": 0.4644, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00022799999999999999, | |
| "loss": 0.4592, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.8825145363807678, | |
| "eval_runtime": 1.2668, | |
| "eval_samples_per_second": 789.404, | |
| "eval_steps_per_second": 12.63, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.000234, | |
| "loss": 0.4542, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.4489, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.878689169883728, | |
| "eval_runtime": 1.1589, | |
| "eval_samples_per_second": 862.885, | |
| "eval_steps_per_second": 13.806, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00024599999999999996, | |
| "loss": 0.4437, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00025199999999999995, | |
| "loss": 0.439, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.8742354512214661, | |
| "eval_runtime": 1.1831, | |
| "eval_samples_per_second": 845.245, | |
| "eval_steps_per_second": 13.524, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.000258, | |
| "loss": 0.4339, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 0.4292, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.8848758935928345, | |
| "eval_runtime": 1.1886, | |
| "eval_samples_per_second": 841.313, | |
| "eval_steps_per_second": 13.461, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00027, | |
| "loss": 0.4251, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000276, | |
| "loss": 0.4212, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.8841528296470642, | |
| "eval_runtime": 1.2211, | |
| "eval_samples_per_second": 818.95, | |
| "eval_steps_per_second": 13.103, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 0.4175, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00028799999999999995, | |
| "loss": 0.4142, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.8811973929405212, | |
| "eval_runtime": 1.275, | |
| "eval_samples_per_second": 784.285, | |
| "eval_steps_per_second": 12.549, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.000294, | |
| "loss": 0.4109, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003, | |
| "loss": 0.4076, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.8659318089485168, | |
| "eval_runtime": 1.2881, | |
| "eval_samples_per_second": 776.338, | |
| "eval_steps_per_second": 12.421, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00029999920715161553, | |
| "loss": 0.4045, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002999968286151326, | |
| "loss": 0.4017, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.874371349811554, | |
| "eval_runtime": 1.2282, | |
| "eval_samples_per_second": 814.215, | |
| "eval_steps_per_second": 13.027, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002999928644165624, | |
| "loss": 0.3987, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002999873145992569, | |
| "loss": 0.3958, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.8821514844894409, | |
| "eval_runtime": 1.1414, | |
| "eval_samples_per_second": 876.15, | |
| "eval_steps_per_second": 14.018, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.000299980179223908, | |
| "loss": 0.3933, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002999714583685469, | |
| "loss": 0.3907, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.8762433528900146, | |
| "eval_runtime": 1.2113, | |
| "eval_samples_per_second": 825.526, | |
| "eval_steps_per_second": 13.208, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00029996115212854366, | |
| "loss": 0.3886, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00029994926061660554, | |
| "loss": 0.3863, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.8757530450820923, | |
| "eval_runtime": 1.1818, | |
| "eval_samples_per_second": 846.134, | |
| "eval_steps_per_second": 13.538, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002999357839627762, | |
| "loss": 0.3841, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00029992072231443425, | |
| "loss": 0.382, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.8755055069923401, | |
| "eval_runtime": 1.2044, | |
| "eval_samples_per_second": 830.296, | |
| "eval_steps_per_second": 13.285, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002999040758362914, | |
| "loss": 0.3804, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00029988584471039094, | |
| "loss": 0.378, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.8780514001846313, | |
| "eval_runtime": 1.1913, | |
| "eval_samples_per_second": 839.425, | |
| "eval_steps_per_second": 13.431, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002998660291361054, | |
| "loss": 0.3763, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002998446293301349, | |
| "loss": 0.3748, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.8814873099327087, | |
| "eval_runtime": 1.3032, | |
| "eval_samples_per_second": 767.316, | |
| "eval_steps_per_second": 12.277, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002998216455265042, | |
| "loss": 0.3735, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00029979707797656046, | |
| "loss": 0.3716, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.868879497051239, | |
| "eval_runtime": 1.2062, | |
| "eval_samples_per_second": 829.022, | |
| "eval_steps_per_second": 13.264, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00029977092694897053, | |
| "loss": 0.3702, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002997431927297178, | |
| "loss": 0.3689, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.8758594989776611, | |
| "eval_runtime": 1.2131, | |
| "eval_samples_per_second": 824.364, | |
| "eval_steps_per_second": 13.19, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00029971387562209936, | |
| "loss": 0.3677, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00029968297594672226, | |
| "loss": 0.3665, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.8690294623374939, | |
| "eval_runtime": 1.1601, | |
| "eval_samples_per_second": 861.986, | |
| "eval_steps_per_second": 13.792, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002996504940415005, | |
| "loss": 0.365, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00029961643026165096, | |
| "loss": 0.364, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.8695961236953735, | |
| "eval_runtime": 1.2184, | |
| "eval_samples_per_second": 820.732, | |
| "eval_steps_per_second": 13.132, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00029958078497968973, | |
| "loss": 0.3627, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002995435585854278, | |
| "loss": 0.3614, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.8684411644935608, | |
| "eval_runtime": 1.2551, | |
| "eval_samples_per_second": 796.719, | |
| "eval_steps_per_second": 12.747, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002995047514859671, | |
| "loss": 0.3603, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002994643641056959, | |
| "loss": 0.3592, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.8597822189331055, | |
| "eval_runtime": 1.198, | |
| "eval_samples_per_second": 834.721, | |
| "eval_steps_per_second": 13.356, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.000299422396886284, | |
| "loss": 0.358, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002993788502866783, | |
| "loss": 0.3571, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.8572097420692444, | |
| "eval_runtime": 1.21, | |
| "eval_samples_per_second": 826.463, | |
| "eval_steps_per_second": 13.223, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00029933372478309746, | |
| "loss": 0.3562, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00029928702086902664, | |
| "loss": 0.3555, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.8637193441390991, | |
| "eval_runtime": 1.4051, | |
| "eval_samples_per_second": 711.674, | |
| "eval_steps_per_second": 11.387, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00029923873905521244, | |
| "loss": 0.3545, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.000299188879869657, | |
| "loss": 0.3535, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 0.8638287782669067, | |
| "eval_runtime": 1.2182, | |
| "eval_samples_per_second": 820.876, | |
| "eval_steps_per_second": 13.134, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00029913744385761244, | |
| "loss": 0.3524, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00029908443158157465, | |
| "loss": 0.3518, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.8664878606796265, | |
| "eval_runtime": 1.2547, | |
| "eval_samples_per_second": 796.987, | |
| "eval_steps_per_second": 12.752, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002990298436212775, | |
| "loss": 0.3511, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002989736805736861, | |
| "loss": 0.3502, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.8559480905532837, | |
| "eval_runtime": 1.2272, | |
| "eval_samples_per_second": 814.861, | |
| "eval_steps_per_second": 13.038, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00029891594305299065, | |
| "loss": 0.3494, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00029885663169059926, | |
| "loss": 0.3488, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.859957754611969, | |
| "eval_runtime": 1.2944, | |
| "eval_samples_per_second": 772.587, | |
| "eval_steps_per_second": 12.361, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002987957471351316, | |
| "loss": 0.3478, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00029873329005241137, | |
| "loss": 0.3469, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.852756917476654, | |
| "eval_runtime": 1.2478, | |
| "eval_samples_per_second": 801.439, | |
| "eval_steps_per_second": 12.823, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00029866926112545925, | |
| "loss": 0.3464, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00029860366105448534, | |
| "loss": 0.3459, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.8597527146339417, | |
| "eval_runtime": 1.1814, | |
| "eval_samples_per_second": 846.435, | |
| "eval_steps_per_second": 13.543, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00029853649055688143, | |
| "loss": 0.3451, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00029846775036721337, | |
| "loss": 0.3444, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.860701322555542, | |
| "eval_runtime": 1.2083, | |
| "eval_samples_per_second": 827.633, | |
| "eval_steps_per_second": 13.242, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0002983974412372129, | |
| "loss": 0.3438, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00029832556393576934, | |
| "loss": 0.3428, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 0.865045964717865, | |
| "eval_runtime": 1.2493, | |
| "eval_samples_per_second": 800.445, | |
| "eval_steps_per_second": 12.807, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002982521192489214, | |
| "loss": 0.3425, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002981771079798483, | |
| "loss": 0.342, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.8640099167823792, | |
| "eval_runtime": 1.2369, | |
| "eval_samples_per_second": 808.489, | |
| "eval_steps_per_second": 12.936, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00029810053094886136, | |
| "loss": 0.3417, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00029802238899339473, | |
| "loss": 0.3408, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.8549481630325317, | |
| "eval_runtime": 1.3108, | |
| "eval_samples_per_second": 762.871, | |
| "eval_steps_per_second": 12.206, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002979426829679962, | |
| "loss": 0.3403, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002978614137443183, | |
| "loss": 0.3398, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 0.8630042672157288, | |
| "eval_runtime": 1.1917, | |
| "eval_samples_per_second": 839.116, | |
| "eval_steps_per_second": 13.426, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.000297778582211108, | |
| "loss": 0.3391, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00029769418927419786, | |
| "loss": 0.3387, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.8540878891944885, | |
| "eval_runtime": 1.2825, | |
| "eval_samples_per_second": 779.707, | |
| "eval_steps_per_second": 12.475, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002976082358564954, | |
| "loss": 0.338, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00029752072289797353, | |
| "loss": 0.3373, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.8587937355041504, | |
| "eval_runtime": 1.3038, | |
| "eval_samples_per_second": 766.964, | |
| "eval_steps_per_second": 12.271, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00029743165135565986, | |
| "loss": 0.3373, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00029734102220362654, | |
| "loss": 0.3368, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.8638780117034912, | |
| "eval_runtime": 1.2508, | |
| "eval_samples_per_second": 799.458, | |
| "eval_steps_per_second": 12.791, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00029724883643297937, | |
| "loss": 0.3362, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002971550950518473, | |
| "loss": 0.3357, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.8546432256698608, | |
| "eval_runtime": 1.2572, | |
| "eval_samples_per_second": 795.415, | |
| "eval_steps_per_second": 12.727, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.000297059799085371, | |
| "loss": 0.3351, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00029696294957569196, | |
| "loss": 0.335, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.8535034656524658, | |
| "eval_runtime": 1.2455, | |
| "eval_samples_per_second": 802.916, | |
| "eval_steps_per_second": 12.847, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00029686454758194076, | |
| "loss": 0.3343, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00029676459418022594, | |
| "loss": 0.334, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.8510599136352539, | |
| "eval_runtime": 1.2497, | |
| "eval_samples_per_second": 800.205, | |
| "eval_steps_per_second": 12.803, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002966630904636219, | |
| "loss": 0.3335, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0002965600375421569, | |
| "loss": 0.333, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.8525308966636658, | |
| "eval_runtime": 1.285, | |
| "eval_samples_per_second": 778.223, | |
| "eval_steps_per_second": 12.452, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0002964554365428013, | |
| "loss": 0.3328, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00029634928860945486, | |
| "loss": 0.3322, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 0.8536081910133362, | |
| "eval_runtime": 1.2803, | |
| "eval_samples_per_second": 781.08, | |
| "eval_steps_per_second": 12.497, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002962415949029343, | |
| "loss": 0.3319, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00029613235660096084, | |
| "loss": 0.3314, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.8421887159347534, | |
| "eval_runtime": 1.3286, | |
| "eval_samples_per_second": 752.666, | |
| "eval_steps_per_second": 12.043, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00029602157489814693, | |
| "loss": 0.3311, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00029590925100598365, | |
| "loss": 0.3307, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 0.8626954555511475, | |
| "eval_runtime": 1.268, | |
| "eval_samples_per_second": 788.647, | |
| "eval_steps_per_second": 12.618, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.000295795386152827, | |
| "loss": 0.3302, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0002956799815838848, | |
| "loss": 0.3298, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.8434558510780334, | |
| "eval_runtime": 1.2564, | |
| "eval_samples_per_second": 795.92, | |
| "eval_steps_per_second": 12.735, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002955630385612029, | |
| "loss": 0.3294, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002954445583636515, | |
| "loss": 0.3292, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.8569065928459167, | |
| "eval_runtime": 1.2969, | |
| "eval_samples_per_second": 771.061, | |
| "eval_steps_per_second": 12.337, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00029532454228691103, | |
| "loss": 0.3288, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002952029916434581, | |
| "loss": 0.3287, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.8517204523086548, | |
| "eval_runtime": 1.2275, | |
| "eval_samples_per_second": 814.648, | |
| "eval_steps_per_second": 13.034, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00029507990776255107, | |
| "loss": 0.3282, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00029495529199021555, | |
| "loss": 0.3278, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.8487727046012878, | |
| "eval_runtime": 1.2356, | |
| "eval_samples_per_second": 809.327, | |
| "eval_steps_per_second": 12.949, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002948291456892296, | |
| "loss": 0.3273, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00029470147023910907, | |
| "loss": 0.3269, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.8469608426094055, | |
| "eval_runtime": 1.2425, | |
| "eval_samples_per_second": 804.832, | |
| "eval_steps_per_second": 12.877, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002945722670360921, | |
| "loss": 0.3265, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002944415374931243, | |
| "loss": 0.3262, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.8486921191215515, | |
| "eval_runtime": 1.2218, | |
| "eval_samples_per_second": 818.455, | |
| "eval_steps_per_second": 13.095, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00029430928303984295, | |
| "loss": 0.326, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002941755051225616, | |
| "loss": 0.3257, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.8429991602897644, | |
| "eval_runtime": 1.2262, | |
| "eval_samples_per_second": 815.556, | |
| "eval_steps_per_second": 13.049, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00029404020520425417, | |
| "loss": 0.3253, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002939033847645388, | |
| "loss": 0.325, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.8381994366645813, | |
| "eval_runtime": 1.2665, | |
| "eval_samples_per_second": 789.582, | |
| "eval_steps_per_second": 12.633, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00029376504529966195, | |
| "loss": 0.3246, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00029362518832248184, | |
| "loss": 0.3248, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.848027229309082, | |
| "eval_runtime": 1.243, | |
| "eval_samples_per_second": 804.488, | |
| "eval_steps_per_second": 12.872, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0002934838153624519, | |
| "loss": 0.3243, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00029334092796560427, | |
| "loss": 0.3238, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.8432244658470154, | |
| "eval_runtime": 1.2842, | |
| "eval_samples_per_second": 778.669, | |
| "eval_steps_per_second": 12.459, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002931965276945326, | |
| "loss": 0.3235, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002930506161283751, | |
| "loss": 0.3235, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.8572074174880981, | |
| "eval_runtime": 1.2536, | |
| "eval_samples_per_second": 797.713, | |
| "eval_steps_per_second": 12.763, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00029290319486279724, | |
| "loss": 0.3229, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002927542655099744, | |
| "loss": 0.3227, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.8465535044670105, | |
| "eval_runtime": 1.184, | |
| "eval_samples_per_second": 844.583, | |
| "eval_steps_per_second": 13.513, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00029260382969857417, | |
| "loss": 0.3223, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00029245188907373845, | |
| "loss": 0.3224, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.8523721694946289, | |
| "eval_runtime": 1.247, | |
| "eval_samples_per_second": 801.902, | |
| "eval_steps_per_second": 12.83, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0002922984452970655, | |
| "loss": 0.3219, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.000292143500046592, | |
| "loss": 0.3217, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.8451367616653442, | |
| "eval_runtime": 1.266, | |
| "eval_samples_per_second": 789.893, | |
| "eval_steps_per_second": 12.638, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002919870550167743, | |
| "loss": 0.3216, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002918291119184702, | |
| "loss": 0.321, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.8452543020248413, | |
| "eval_runtime": 1.2406, | |
| "eval_samples_per_second": 806.062, | |
| "eval_steps_per_second": 12.897, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002916696724789201, | |
| "loss": 0.321, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00029150873844172823, | |
| "loss": 0.3207, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.8388876914978027, | |
| "eval_runtime": 1.2429, | |
| "eval_samples_per_second": 804.592, | |
| "eval_steps_per_second": 12.873, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00029134631156684334, | |
| "loss": 0.3204, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002911823936305398, | |
| "loss": 0.3202, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.8390601873397827, | |
| "eval_runtime": 1.2051, | |
| "eval_samples_per_second": 829.802, | |
| "eval_steps_per_second": 13.277, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002910169864253979, | |
| "loss": 0.3198, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0002908500917602842, | |
| "loss": 0.3195, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.853469729423523, | |
| "eval_runtime": 1.2478, | |
| "eval_samples_per_second": 801.439, | |
| "eval_steps_per_second": 12.823, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00029068171146033226, | |
| "loss": 0.3196, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002905118473669218, | |
| "loss": 0.3194, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.8577731847763062, | |
| "eval_runtime": 1.1943, | |
| "eval_samples_per_second": 837.345, | |
| "eval_steps_per_second": 13.398, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00029034050133765947, | |
| "loss": 0.319, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00029016767524635804, | |
| "loss": 0.3194, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.851713240146637, | |
| "eval_runtime": 1.28, | |
| "eval_samples_per_second": 781.247, | |
| "eval_steps_per_second": 12.5, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00028999337098301585, | |
| "loss": 0.3187, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0002898175904537964, | |
| "loss": 0.3185, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.8537120223045349, | |
| "eval_runtime": 1.24, | |
| "eval_samples_per_second": 806.425, | |
| "eval_steps_per_second": 12.903, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0002896403355810075, | |
| "loss": 0.3179, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00028946160830307997, | |
| "loss": 0.3183, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.8353117108345032, | |
| "eval_runtime": 1.2534, | |
| "eval_samples_per_second": 797.829, | |
| "eval_steps_per_second": 12.765, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00028928141057454665, | |
| "loss": 0.3182, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002890997443660211, | |
| "loss": 0.3177, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 0.845744252204895, | |
| "eval_runtime": 1.2558, | |
| "eval_samples_per_second": 796.305, | |
| "eval_steps_per_second": 12.741, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00028891661166417586, | |
| "loss": 0.3174, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00028873201447172074, | |
| "loss": 0.3174, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.8514609932899475, | |
| "eval_runtime": 1.2468, | |
| "eval_samples_per_second": 802.073, | |
| "eval_steps_per_second": 12.833, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002885459548073812, | |
| "loss": 0.3173, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002883584347058758, | |
| "loss": 0.3165, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 0.8357125520706177, | |
| "eval_runtime": 1.221, | |
| "eval_samples_per_second": 818.991, | |
| "eval_steps_per_second": 13.104, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00028816945621789437, | |
| "loss": 0.3166, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002879790214100753, | |
| "loss": 0.3164, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.855523943901062, | |
| "eval_runtime": 1.2726, | |
| "eval_samples_per_second": 785.803, | |
| "eval_steps_per_second": 12.573, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0002877871323649833, | |
| "loss": 0.3161, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0002875937911810861, | |
| "loss": 0.3159, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.842631995677948, | |
| "eval_runtime": 1.2074, | |
| "eval_samples_per_second": 828.219, | |
| "eval_steps_per_second": 13.252, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.000287398999972732, | |
| "loss": 0.3159, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00028720276087012636, | |
| "loss": 0.3159, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.8528951406478882, | |
| "eval_runtime": 1.2566, | |
| "eval_samples_per_second": 795.823, | |
| "eval_steps_per_second": 12.733, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002870050760193086, | |
| "loss": 0.3152, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00028680594758212854, | |
| "loss": 0.3152, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.8297361135482788, | |
| "eval_runtime": 1.2298, | |
| "eval_samples_per_second": 813.129, | |
| "eval_steps_per_second": 13.01, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00028660537773622294, | |
| "loss": 0.3158, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00028640336867499143, | |
| "loss": 0.3149, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.8462135195732117, | |
| "eval_runtime": 1.1973, | |
| "eval_samples_per_second": 835.246, | |
| "eval_steps_per_second": 13.364, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0002861999226075728, | |
| "loss": 0.3148, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002859950417588206, | |
| "loss": 0.3144, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.8435172438621521, | |
| "eval_runtime": 1.2492, | |
| "eval_samples_per_second": 800.501, | |
| "eval_steps_per_second": 12.808, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00028578872836927904, | |
| "loss": 0.3144, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002855809846951582, | |
| "loss": 0.3141, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.8363200426101685, | |
| "eval_runtime": 1.2168, | |
| "eval_samples_per_second": 821.803, | |
| "eval_steps_per_second": 13.149, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00028537181300830963, | |
| "loss": 0.3138, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002851612155962014, | |
| "loss": 0.3139, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.8434939384460449, | |
| "eval_runtime": 1.2528, | |
| "eval_samples_per_second": 798.238, | |
| "eval_steps_per_second": 12.772, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002849491947618932, | |
| "loss": 0.3139, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002847357528240107, | |
| "loss": 0.3139, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.8472431898117065, | |
| "eval_runtime": 1.2611, | |
| "eval_samples_per_second": 792.952, | |
| "eval_steps_per_second": 12.687, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0002845208921167208, | |
| "loss": 0.3137, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.00028430461498970584, | |
| "loss": 0.3131, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.8395859599113464, | |
| "eval_runtime": 1.2301, | |
| "eval_samples_per_second": 812.96, | |
| "eval_steps_per_second": 13.007, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.00028408692380813775, | |
| "loss": 0.3125, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00028386782095265247, | |
| "loss": 0.3125, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 0.8419870734214783, | |
| "eval_runtime": 1.245, | |
| "eval_samples_per_second": 803.234, | |
| "eval_steps_per_second": 12.852, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0002836473088193237, | |
| "loss": 0.313, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00028342538981963677, | |
| "loss": 0.3128, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.8410093784332275, | |
| "eval_runtime": 1.2759, | |
| "eval_samples_per_second": 783.735, | |
| "eval_steps_per_second": 12.54, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002832020663804624, | |
| "loss": 0.3124, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.00028297734094402986, | |
| "loss": 0.3121, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.8417559862136841, | |
| "eval_runtime": 1.2688, | |
| "eval_samples_per_second": 788.14, | |
| "eval_steps_per_second": 12.61, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0002827512159679005, | |
| "loss": 0.3122, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.00028252369392494086, | |
| "loss": 0.3118, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 0.8400096893310547, | |
| "eval_runtime": 1.2486, | |
| "eval_samples_per_second": 800.914, | |
| "eval_steps_per_second": 12.815, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002822947773032956, | |
| "loss": 0.3117, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0002820644686063602, | |
| "loss": 0.3112, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.8347204327583313, | |
| "eval_runtime": 1.2512, | |
| "eval_samples_per_second": 799.226, | |
| "eval_steps_per_second": 12.788, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.00028183277035275363, | |
| "loss": 0.3117, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002815996850762909, | |
| "loss": 0.3112, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.8288648724555969, | |
| "eval_runtime": 1.2077, | |
| "eval_samples_per_second": 828.045, | |
| "eval_steps_per_second": 13.249, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.00028136521532595515, | |
| "loss": 0.311, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00028112936366587023, | |
| "loss": 0.3112, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.8455829620361328, | |
| "eval_runtime": 1.2774, | |
| "eval_samples_per_second": 782.835, | |
| "eval_steps_per_second": 12.525, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00028089213267527184, | |
| "loss": 0.311, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0002806535249484803, | |
| "loss": 0.3107, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.8414435982704163, | |
| "eval_runtime": 1.2285, | |
| "eval_samples_per_second": 813.99, | |
| "eval_steps_per_second": 13.024, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.00028041354309487135, | |
| "loss": 0.3108, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0002801721897388482, | |
| "loss": 0.3101, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.8326617479324341, | |
| "eval_runtime": 1.214, | |
| "eval_samples_per_second": 823.726, | |
| "eval_steps_per_second": 13.18, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002799294675198124, | |
| "loss": 0.3102, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00027968537909213524, | |
| "loss": 0.3107, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.837422251701355, | |
| "eval_runtime": 1.2383, | |
| "eval_samples_per_second": 807.572, | |
| "eval_steps_per_second": 12.921, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0002794399271251287, | |
| "loss": 0.3102, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0002791931143030162, | |
| "loss": 0.3103, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 0.8471120595932007, | |
| "eval_runtime": 1.2736, | |
| "eval_samples_per_second": 785.146, | |
| "eval_steps_per_second": 12.562, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00027894494332490315, | |
| "loss": 0.3104, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0002786954169047476, | |
| "loss": 0.3095, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 0.845231831073761, | |
| "eval_runtime": 1.222, | |
| "eval_samples_per_second": 818.338, | |
| "eval_steps_per_second": 13.093, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0002784445377713306, | |
| "loss": 0.3093, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002781923086682261, | |
| "loss": 0.3094, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 0.8512564301490784, | |
| "eval_runtime": 1.2211, | |
| "eval_samples_per_second": 818.908, | |
| "eval_steps_per_second": 13.103, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002779387323537711, | |
| "loss": 0.3091, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002776838116010356, | |
| "loss": 0.3094, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.8348438739776611, | |
| "eval_runtime": 1.2126, | |
| "eval_samples_per_second": 824.682, | |
| "eval_steps_per_second": 13.195, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002774275491977922, | |
| "loss": 0.3111, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0002771699479464853, | |
| "loss": 0.3089, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 0.8333858847618103, | |
| "eval_runtime": 1.2664, | |
| "eval_samples_per_second": 789.664, | |
| "eval_steps_per_second": 12.635, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00027691101066420104, | |
| "loss": 0.3091, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002766507401826361, | |
| "loss": 0.3089, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 0.8437691330909729, | |
| "eval_runtime": 1.2859, | |
| "eval_samples_per_second": 777.686, | |
| "eval_steps_per_second": 12.443, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0002763891393480666, | |
| "loss": 0.3086, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002761262110213175, | |
| "loss": 0.3088, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.8328044414520264, | |
| "eval_runtime": 1.2617, | |
| "eval_samples_per_second": 792.564, | |
| "eval_steps_per_second": 12.681, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00027586195807773083, | |
| "loss": 0.308, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00027559638340713435, | |
| "loss": 0.3085, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.831738293170929, | |
| "eval_runtime": 1.2398, | |
| "eval_samples_per_second": 806.55, | |
| "eval_steps_per_second": 12.905, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.00027532948991381025, | |
| "loss": 0.3079, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.00027506128051646287, | |
| "loss": 0.3097, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.8462249636650085, | |
| "eval_runtime": 1.2264, | |
| "eval_samples_per_second": 815.428, | |
| "eval_steps_per_second": 13.047, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00027479175814818733, | |
| "loss": 0.3082, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.000274520925756437, | |
| "loss": 0.3082, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.8435738682746887, | |
| "eval_runtime": 1.3152, | |
| "eval_samples_per_second": 760.322, | |
| "eval_steps_per_second": 12.165, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.00027424878630299157, | |
| "loss": 0.3074, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002739753427639244, | |
| "loss": 0.3077, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.8435785174369812, | |
| "eval_runtime": 1.2302, | |
| "eval_samples_per_second": 812.844, | |
| "eval_steps_per_second": 13.006, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0002737005981295704, | |
| "loss": 0.3078, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0002734245554044927, | |
| "loss": 0.3086, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_loss": 0.8482502698898315, | |
| "eval_runtime": 1.3338, | |
| "eval_samples_per_second": 749.745, | |
| "eval_steps_per_second": 11.996, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0002731472176074504, | |
| "loss": 0.307, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0002728685877713653, | |
| "loss": 0.3072, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 0.8354719281196594, | |
| "eval_runtime": 1.4002, | |
| "eval_samples_per_second": 714.17, | |
| "eval_steps_per_second": 11.427, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0002725886689432884, | |
| "loss": 0.3075, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0002723074641843674, | |
| "loss": 0.3066, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_loss": 0.8281124234199524, | |
| "eval_runtime": 1.3099, | |
| "eval_samples_per_second": 763.433, | |
| "eval_steps_per_second": 12.215, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0002720249765698123, | |
| "loss": 0.3066, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0002717412091888626, | |
| "loss": 0.3072, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 0.8392689824104309, | |
| "eval_runtime": 1.2716, | |
| "eval_samples_per_second": 786.397, | |
| "eval_steps_per_second": 12.582, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00027145616514475274, | |
| "loss": 0.3067, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0002711698475546788, | |
| "loss": 0.3063, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 0.8436251282691956, | |
| "eval_runtime": 1.2483, | |
| "eval_samples_per_second": 801.08, | |
| "eval_steps_per_second": 12.817, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00027088225954976407, | |
| "loss": 0.3067, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0002705934042750249, | |
| "loss": 0.3061, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_loss": 0.8345765471458435, | |
| "eval_runtime": 1.2507, | |
| "eval_samples_per_second": 799.522, | |
| "eval_steps_per_second": 12.792, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.00027030328488933625, | |
| "loss": 0.3071, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00027001190456539726, | |
| "loss": 0.3059, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "eval_loss": 0.8408392071723938, | |
| "eval_runtime": 1.3349, | |
| "eval_samples_per_second": 749.093, | |
| "eval_steps_per_second": 11.985, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.0002697192664896965, | |
| "loss": 0.3062, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.00026942537386247706, | |
| "loss": 0.3062, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.8384091854095459, | |
| "eval_runtime": 1.3159, | |
| "eval_samples_per_second": 759.918, | |
| "eval_steps_per_second": 12.159, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0002691302298977016, | |
| "loss": 0.3058, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0002688338378230173, | |
| "loss": 0.307, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_loss": 0.837376594543457, | |
| "eval_runtime": 1.3811, | |
| "eval_samples_per_second": 724.072, | |
| "eval_steps_per_second": 11.585, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00026853620087972035, | |
| "loss": 0.3067, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00026823732232272065, | |
| "loss": 0.3056, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_loss": 0.8240262269973755, | |
| "eval_runtime": 1.3027, | |
| "eval_samples_per_second": 767.62, | |
| "eval_steps_per_second": 12.282, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0002679372054205063, | |
| "loss": 0.305, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.0002676358534551076, | |
| "loss": 0.3049, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 0.8262757658958435, | |
| "eval_runtime": 1.3606, | |
| "eval_samples_per_second": 734.996, | |
| "eval_steps_per_second": 11.76, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00026733326972206133, | |
| "loss": 0.306, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.0002670294575303748, | |
| "loss": 0.3068, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_loss": 0.8301039934158325, | |
| "eval_runtime": 1.2964, | |
| "eval_samples_per_second": 771.396, | |
| "eval_steps_per_second": 12.342, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.0002667244202024894, | |
| "loss": 0.305, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.00026641816107424453, | |
| "loss": 0.3053, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "eval_loss": 0.8349767923355103, | |
| "eval_runtime": 1.3045, | |
| "eval_samples_per_second": 766.596, | |
| "eval_steps_per_second": 12.266, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0002661106834948409, | |
| "loss": 0.3058, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.0002658019908268041, | |
| "loss": 0.3048, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "eval_loss": 0.8294724822044373, | |
| "eval_runtime": 1.2682, | |
| "eval_samples_per_second": 788.537, | |
| "eval_steps_per_second": 12.617, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.00026549208644594766, | |
| "loss": 0.305, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00026518097374133627, | |
| "loss": 0.3051, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 0.8296982049942017, | |
| "eval_runtime": 1.3247, | |
| "eval_samples_per_second": 754.912, | |
| "eval_steps_per_second": 12.079, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.00026486865611524853, | |
| "loss": 0.3045, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.00026455513698314003, | |
| "loss": 0.3045, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 0.8295329213142395, | |
| "eval_runtime": 1.3528, | |
| "eval_samples_per_second": 739.189, | |
| "eval_steps_per_second": 11.827, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.0002642404197736058, | |
| "loss": 0.3045, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.0002639245079283428, | |
| "loss": 0.3043, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "eval_loss": 0.8244909644126892, | |
| "eval_runtime": 1.3196, | |
| "eval_samples_per_second": 757.824, | |
| "eval_steps_per_second": 12.125, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.00026360740490211234, | |
| "loss": 0.3038, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0002632891141627023, | |
| "loss": 0.3037, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 0.8188607096672058, | |
| "eval_runtime": 1.2963, | |
| "eval_samples_per_second": 771.439, | |
| "eval_steps_per_second": 12.343, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.00026296963919088923, | |
| "loss": 0.304, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.00026264898348040024, | |
| "loss": 0.3042, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.8286353349685669, | |
| "eval_runtime": 1.3187, | |
| "eval_samples_per_second": 758.324, | |
| "eval_steps_per_second": 12.133, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.0002623271505378748, | |
| "loss": 0.3038, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00026200414388282637, | |
| "loss": 0.3038, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_loss": 0.8326404690742493, | |
| "eval_runtime": 1.3251, | |
| "eval_samples_per_second": 754.645, | |
| "eval_steps_per_second": 12.074, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.00026167996704760406, | |
| "loss": 0.3058, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.00026135462357735375, | |
| "loss": 0.3033, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 0.8183851838111877, | |
| "eval_runtime": 1.3581, | |
| "eval_samples_per_second": 736.344, | |
| "eval_steps_per_second": 11.782, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.0002610281170299795, | |
| "loss": 0.3035, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00026070045097610465, | |
| "loss": 0.3035, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_loss": 0.8135998249053955, | |
| "eval_runtime": 1.309, | |
| "eval_samples_per_second": 763.92, | |
| "eval_steps_per_second": 12.223, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0002603716289990326, | |
| "loss": 0.3026, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.00026004165469470787, | |
| "loss": 0.3027, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 0.8287385106086731, | |
| "eval_runtime": 1.2779, | |
| "eval_samples_per_second": 782.532, | |
| "eval_steps_per_second": 12.521, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.0002597105316716766, | |
| "loss": 0.3038, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 0.000259378263551047, | |
| "loss": 0.303, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_loss": 0.8184419870376587, | |
| "eval_runtime": 1.2761, | |
| "eval_samples_per_second": 783.611, | |
| "eval_steps_per_second": 12.538, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.0002590448539664501, | |
| "loss": 0.3026, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 0.00025871030656399966, | |
| "loss": 0.3027, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_loss": 0.8444017171859741, | |
| "eval_runtime": 1.2977, | |
| "eval_samples_per_second": 770.565, | |
| "eval_steps_per_second": 12.329, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.00025837462500225255, | |
| "loss": 0.3026, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.0002580378129521685, | |
| "loss": 0.3024, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 0.8401538133621216, | |
| "eval_runtime": 1.3317, | |
| "eval_samples_per_second": 750.939, | |
| "eval_steps_per_second": 12.015, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0002576998740970701, | |
| "loss": 0.3031, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00025736081213260253, | |
| "loss": 0.3027, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 0.8279548287391663, | |
| "eval_runtime": 1.3186, | |
| "eval_samples_per_second": 758.406, | |
| "eval_steps_per_second": 12.134, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.0002570206307666931, | |
| "loss": 0.3038, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.0002566793337195108, | |
| "loss": 0.3029, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_loss": 0.8254837393760681, | |
| "eval_runtime": 1.2997, | |
| "eval_samples_per_second": 769.407, | |
| "eval_steps_per_second": 12.311, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0002563369247234254, | |
| "loss": 0.3038, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.0002559934075229669, | |
| "loss": 0.3023, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_loss": 0.8286687135696411, | |
| "eval_runtime": 1.2798, | |
| "eval_samples_per_second": 781.358, | |
| "eval_steps_per_second": 12.502, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.0002556487858747843, | |
| "loss": 0.3023, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.00025530306354760464, | |
| "loss": 0.3024, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.8175866007804871, | |
| "eval_runtime": 1.2628, | |
| "eval_samples_per_second": 791.915, | |
| "eval_steps_per_second": 12.671, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.000254956244322192, | |
| "loss": 0.3022, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.00025460833199130595, | |
| "loss": 0.302, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 0.8372282385826111, | |
| "eval_runtime": 1.3637, | |
| "eval_samples_per_second": 733.286, | |
| "eval_steps_per_second": 11.733, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.00025425933035965983, | |
| "loss": 0.3031, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.00025390924324387965, | |
| "loss": 0.3019, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_loss": 0.8220604658126831, | |
| "eval_runtime": 1.363, | |
| "eval_samples_per_second": 733.669, | |
| "eval_steps_per_second": 11.739, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.0002535580744724621, | |
| "loss": 0.3021, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.00025320582788573246, | |
| "loss": 0.3016, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "eval_loss": 0.8250831365585327, | |
| "eval_runtime": 1.3782, | |
| "eval_samples_per_second": 725.588, | |
| "eval_steps_per_second": 11.609, | |
| "step": 150000 | |
| } | |
| ], | |
| "max_steps": 500000, | |
| "num_train_epochs": 13, | |
| "total_flos": 4.792266644878365e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |