| { | |
| "best_metric": 1.487816572189331, | |
| "best_model_checkpoint": "longt5_xl_gov_report_bp_10_continue/checkpoint-68", | |
| "epoch": 3.9871736142922583, | |
| "eval_steps": 500, | |
| "global_step": 272, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.001, | |
| "loss": 0.6441, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.001, | |
| "loss": 0.6068, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.001, | |
| "loss": 0.6344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.001, | |
| "loss": 0.6447, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.001, | |
| "loss": 0.6177, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.001, | |
| "loss": 0.615, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.001, | |
| "loss": 0.6113, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.6076, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.001, | |
| "loss": 0.5993, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.6105, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.6164, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.6188, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.001, | |
| "loss": 0.617, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.6007, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.001, | |
| "loss": 0.6138, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.6189, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.001, | |
| "loss": 0.6087, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.001, | |
| "loss": 0.6234, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.001, | |
| "loss": 0.6588, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.001, | |
| "loss": 0.6542, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.001, | |
| "loss": 0.6255, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.6007, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.001, | |
| "loss": 0.6116, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.6159, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.001, | |
| "loss": 0.6497, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.001, | |
| "loss": 0.6595, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.6221, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.6243, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.5897, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.001, | |
| "loss": 0.5845, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.6273, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.001, | |
| "loss": 0.5985, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.6252, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.001, | |
| "loss": 0.6226, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 833.0318930041152, | |
| "eval_loss": 1.487816572189331, | |
| "eval_rouge1": 71.9439, | |
| "eval_rouge2": 43.7031, | |
| "eval_rougeL": 41.8301, | |
| "eval_rougeLsum": 69.1853, | |
| "eval_runtime": 5182.0273, | |
| "eval_samples_per_second": 0.188, | |
| "eval_steps_per_second": 0.024, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.001, | |
| "loss": 0.5449, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.001, | |
| "loss": 0.4986, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.518, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.5077, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.001, | |
| "loss": 0.5037, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.5092, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.001, | |
| "loss": 0.5303, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.5167, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.001, | |
| "loss": 0.5016, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.5096, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.5177, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.5035, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.001, | |
| "loss": 0.5163, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.5284, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.001, | |
| "loss": 0.513, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.4994, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.001, | |
| "loss": 0.653, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.5039, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.001, | |
| "loss": 0.5044, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.5153, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.001, | |
| "loss": 0.5094, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.5041, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.001, | |
| "loss": 0.5047, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.4967, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.001, | |
| "loss": 0.5125, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.001, | |
| "loss": 0.5047, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.4937, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.5005, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.4989, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.001, | |
| "loss": 0.5631, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.4991, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.4786, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.4918, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.4983, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_gen_len": 627.5030864197531, | |
| "eval_loss": 1.5908194780349731, | |
| "eval_rouge1": 70.6191, | |
| "eval_rouge2": 43.2627, | |
| "eval_rougeL": 42.581, | |
| "eval_rougeLsum": 68.0871, | |
| "eval_runtime": 4338.9375, | |
| "eval_samples_per_second": 0.224, | |
| "eval_steps_per_second": 0.028, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.4259, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.3974, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.4039, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.3859, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.001, | |
| "loss": 0.3938, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.4126, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.001, | |
| "loss": 0.3954, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.3978, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.001, | |
| "loss": 0.3894, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.3894, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.402, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.4169, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.412, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.4095, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.001, | |
| "loss": 0.3844, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.3901, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.001, | |
| "loss": 0.4013, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.4001, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.001, | |
| "loss": 0.4127, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.4019, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.001, | |
| "loss": 0.4057, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.4049, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.001, | |
| "loss": 0.4242, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.4293, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.001, | |
| "loss": 0.4003, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.001, | |
| "loss": 0.4089, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.418, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.4329, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.001, | |
| "loss": 0.4341, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.001, | |
| "loss": 0.4535, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.433, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.4192, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.4163, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.4175, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_gen_len": 737.4351851851852, | |
| "eval_loss": 1.6406528949737549, | |
| "eval_rouge1": 71.6704, | |
| "eval_rouge2": 43.1655, | |
| "eval_rougeL": 41.9746, | |
| "eval_rougeLsum": 68.992, | |
| "eval_runtime": 4895.6396, | |
| "eval_samples_per_second": 0.199, | |
| "eval_steps_per_second": 0.025, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.3648, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.3583, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.3338, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.3452, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.001, | |
| "loss": 0.3704, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.3507, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.001, | |
| "loss": 0.3698, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.001, | |
| "loss": 0.3549, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.3476, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.001, | |
| "loss": 0.3557, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.001, | |
| "loss": 0.3791, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.001, | |
| "loss": 0.3737, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.3744, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.3663, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.001, | |
| "loss": 0.3585, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.3718, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.001, | |
| "loss": 0.3703, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.3746, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.001, | |
| "loss": 0.3684, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.358, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.001, | |
| "loss": 0.3735, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.3927, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.001, | |
| "loss": 0.3775, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3643, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.001, | |
| "loss": 0.3714, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.001, | |
| "loss": 0.3723, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.001, | |
| "loss": 0.397, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.3953, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.001, | |
| "loss": 0.3786, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.001, | |
| "loss": 0.3756, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.391, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.3809, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.3818, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.3958, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_gen_len": 671.4938271604939, | |
| "eval_loss": 1.8738882541656494, | |
| "eval_rouge1": 70.7685, | |
| "eval_rouge2": 42.5122, | |
| "eval_rougeL": 41.7454, | |
| "eval_rougeLsum": 68.0785, | |
| "eval_runtime": 4528.4783, | |
| "eval_samples_per_second": 0.215, | |
| "eval_steps_per_second": 0.027, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "step": 272, | |
| "total_flos": 1.2383608053121597e+18, | |
| "train_loss": 0.47826748297495003, | |
| "train_runtime": 56154.1614, | |
| "train_samples_per_second": 1.244, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 272, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 1.2383608053121597e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |