| { | |
| "best_metric": 1.3539438247680664, | |
| "best_model_checkpoint": "longt5_xl_gov_bp_20/checkpoint-34", | |
| "epoch": 4.983967017865323, | |
| "eval_steps": 500, | |
| "global_step": 170, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.001, | |
| "loss": 1.0271, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.001, | |
| "loss": 1.2091, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.001, | |
| "loss": 0.8029, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.8061, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.8036, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.7449, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.776, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.8082, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.001, | |
| "loss": 0.8653, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.001, | |
| "loss": 0.7104, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.8144, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.7039, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.001, | |
| "loss": 0.6056, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.6466, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.001, | |
| "loss": 0.6258, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.001, | |
| "loss": 0.7159, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.001, | |
| "loss": 0.6879, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3539438247680664, | |
| "eval_runtime": 343.3833, | |
| "eval_samples_per_second": 2.831, | |
| "eval_steps_per_second": 0.355, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.001, | |
| "loss": 0.591, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.5727, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.5399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.5328, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.5348, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.5264, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.5156, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.5209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.5102, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.4935, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.5006, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.5027, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.001, | |
| "loss": 0.4907, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.5059, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.001, | |
| "loss": 0.5053, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.4862, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.4865, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.3666499853134155, | |
| "eval_runtime": 344.5818, | |
| "eval_samples_per_second": 2.821, | |
| "eval_steps_per_second": 0.354, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.4426, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.4408, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.4258, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.4243, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.4235, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.4426, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.4366, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.4253, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.4443, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.4301, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.4368, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.4403, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.001, | |
| "loss": 0.3899, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.406, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.001, | |
| "loss": 0.4295, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.4463, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.436, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 1.5058249235153198, | |
| "eval_runtime": 343.8598, | |
| "eval_samples_per_second": 2.827, | |
| "eval_steps_per_second": 0.355, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.3902, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.3745, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.375, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.001, | |
| "loss": 0.382, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.001, | |
| "loss": 0.3798, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.001, | |
| "loss": 0.3777, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.3884, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.3915, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.3898, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.3833, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.3831, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3778, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.001, | |
| "loss": 0.3774, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.3883, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.001, | |
| "loss": 0.3943, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.395, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.3893, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 1.4799894094467163, | |
| "eval_runtime": 343.1889, | |
| "eval_samples_per_second": 2.832, | |
| "eval_steps_per_second": 0.355, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.3537, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.001, | |
| "loss": 0.3376, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.001, | |
| "loss": 0.334, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.001, | |
| "loss": 0.3429, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.001, | |
| "loss": 0.3464, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 0.001, | |
| "loss": 0.3483, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.3407, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.3501, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.001, | |
| "loss": 0.3409, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.3493, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.3402, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3446, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.001, | |
| "loss": 0.3483, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.3511, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.001, | |
| "loss": 0.3515, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.3471, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.001, | |
| "loss": 0.3517, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "eval_loss": 1.5910658836364746, | |
| "eval_runtime": 343.3017, | |
| "eval_samples_per_second": 2.831, | |
| "eval_steps_per_second": 0.355, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "step": 170, | |
| "total_flos": 5.953337981380067e+18, | |
| "train_loss": 0.493012877071605, | |
| "train_runtime": 118230.4451, | |
| "train_samples_per_second": 0.738, | |
| "train_steps_per_second": 0.001 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 170, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 5.953337981380067e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |