| { | |
| "best_metric": 2.255647659301758, | |
| "best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_sfd_memsum_30/checkpoint-43", | |
| "epoch": 29.217391304347824, | |
| "eval_steps": 500, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.001, | |
| "loss": 3.2355, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.001, | |
| "loss": 3.0785, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.001, | |
| "loss": 3.0423, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.001, | |
| "loss": 2.9059, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.001, | |
| "loss": 2.777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.001, | |
| "loss": 2.6848, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.001, | |
| "loss": 2.6697, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 2.4168484210968018, | |
| "eval_runtime": 14.3646, | |
| "eval_samples_per_second": 23.53, | |
| "eval_steps_per_second": 2.993, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.001, | |
| "loss": 2.4413, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.001, | |
| "loss": 2.3287, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.001, | |
| "loss": 2.3054, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.001, | |
| "loss": 2.3458, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.001, | |
| "loss": 2.3942, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.001, | |
| "loss": 2.3186, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.001, | |
| "loss": 2.2272, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 2.264381170272827, | |
| "eval_runtime": 14.3433, | |
| "eval_samples_per_second": 23.565, | |
| "eval_steps_per_second": 2.998, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.001, | |
| "loss": 2.0385, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.001, | |
| "loss": 1.9493, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.001, | |
| "loss": 1.9811, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.001, | |
| "loss": 1.9783, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.001, | |
| "loss": 1.9534, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.001, | |
| "loss": 1.9822, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.001, | |
| "loss": 1.9024, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 2.255647659301758, | |
| "eval_runtime": 14.349, | |
| "eval_samples_per_second": 23.556, | |
| "eval_steps_per_second": 2.997, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.001, | |
| "loss": 1.7788, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.001, | |
| "loss": 1.6545, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.001, | |
| "loss": 1.633, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.001, | |
| "loss": 1.6763, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 0.001, | |
| "loss": 1.6571, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.001, | |
| "loss": 1.6333, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.001, | |
| "loss": 1.6554, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 2.4007155895233154, | |
| "eval_runtime": 14.3209, | |
| "eval_samples_per_second": 23.602, | |
| "eval_steps_per_second": 3.003, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.001, | |
| "loss": 1.5927, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.001, | |
| "loss": 1.3606, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.001, | |
| "loss": 1.3576, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.001, | |
| "loss": 1.4079, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 0.001, | |
| "loss": 1.4133, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.001, | |
| "loss": 1.3712, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.001, | |
| "loss": 1.3619, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 2.423330545425415, | |
| "eval_runtime": 14.334, | |
| "eval_samples_per_second": 23.58, | |
| "eval_steps_per_second": 3.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.001, | |
| "loss": 1.3071, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 0.001, | |
| "loss": 1.0472, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.001, | |
| "loss": 1.1038, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.001, | |
| "loss": 1.1355, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.001, | |
| "loss": 1.1239, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.001, | |
| "loss": 1.1464, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.001, | |
| "loss": 1.1564, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 0.001, | |
| "loss": 1.1577, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_loss": 2.679687976837158, | |
| "eval_runtime": 14.3396, | |
| "eval_samples_per_second": 23.571, | |
| "eval_steps_per_second": 2.999, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.001, | |
| "loss": 0.9042, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.001, | |
| "loss": 0.882, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.9122, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 0.001, | |
| "loss": 0.8572, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 0.001, | |
| "loss": 0.8929, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.9316, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.9584, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_loss": 2.8448543548583984, | |
| "eval_runtime": 14.3357, | |
| "eval_samples_per_second": 23.578, | |
| "eval_steps_per_second": 3.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.001, | |
| "loss": 0.7378, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.7519, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.6793, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 0.001, | |
| "loss": 0.7177, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 0.001, | |
| "loss": 0.7523, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.7479, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.7197, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 3.025547504425049, | |
| "eval_runtime": 14.3269, | |
| "eval_samples_per_second": 23.592, | |
| "eval_steps_per_second": 3.001, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 0.001, | |
| "loss": 0.6231, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 0.001, | |
| "loss": 0.5361, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.5926, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 0.001, | |
| "loss": 0.5732, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.6658, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.001, | |
| "loss": 0.803, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.5756, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_loss": 3.146686553955078, | |
| "eval_runtime": 14.3236, | |
| "eval_samples_per_second": 23.597, | |
| "eval_steps_per_second": 3.002, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 0.001, | |
| "loss": 0.5221, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 0.001, | |
| "loss": 0.4466, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.4909, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.4707, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 0.001, | |
| "loss": 0.4588, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 0.001, | |
| "loss": 0.4693, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 0.001, | |
| "loss": 0.485, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "eval_loss": 3.2976272106170654, | |
| "eval_runtime": 14.3283, | |
| "eval_samples_per_second": 23.59, | |
| "eval_steps_per_second": 3.001, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.4447, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.001, | |
| "loss": 0.3447, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.3563, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.001, | |
| "loss": 0.3578, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.3623, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 0.001, | |
| "loss": 0.383, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.3717, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.4027, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_loss": 3.8110954761505127, | |
| "eval_runtime": 14.3426, | |
| "eval_samples_per_second": 23.566, | |
| "eval_steps_per_second": 2.998, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.001, | |
| "loss": 0.2821, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 0.001, | |
| "loss": 0.2735, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.3073, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 0.001, | |
| "loss": 0.3386, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3426, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.001, | |
| "loss": 0.3111, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.2938, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "eval_loss": 3.7330400943756104, | |
| "eval_runtime": 14.3561, | |
| "eval_samples_per_second": 23.544, | |
| "eval_steps_per_second": 2.995, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.001, | |
| "loss": 0.2443, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 0.001, | |
| "loss": 0.2312, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 0.001, | |
| "loss": 0.2253, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.243, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 0.001, | |
| "loss": 0.2582, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.001, | |
| "loss": 0.2449, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 0.001, | |
| "loss": 0.2665, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "eval_loss": 4.141729831695557, | |
| "eval_runtime": 14.3523, | |
| "eval_samples_per_second": 23.55, | |
| "eval_steps_per_second": 2.996, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.2176, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 0.001, | |
| "loss": 0.1728, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 0.001, | |
| "loss": 0.1807, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 0.001, | |
| "loss": 0.2002, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.1975, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 0.001, | |
| "loss": 0.1973, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.2019, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_loss": 4.03155517578125, | |
| "eval_runtime": 14.3514, | |
| "eval_samples_per_second": 23.552, | |
| "eval_steps_per_second": 2.996, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.19, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.001, | |
| "loss": 0.1599, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 0.001, | |
| "loss": 0.1647, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.1506, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 0.001, | |
| "loss": 0.1551, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 0.001, | |
| "loss": 0.1628, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.001, | |
| "loss": 0.1706, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_loss": 4.135679244995117, | |
| "eval_runtime": 14.348, | |
| "eval_samples_per_second": 23.557, | |
| "eval_steps_per_second": 2.997, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 0.001, | |
| "loss": 0.1729, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.1421, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.1398, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 0.001, | |
| "loss": 0.1377, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.1307, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 0.001, | |
| "loss": 0.1284, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 0.001, | |
| "loss": 0.1384, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 0.001, | |
| "loss": 0.1418, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 4.10220193862915, | |
| "eval_runtime": 14.3626, | |
| "eval_samples_per_second": 23.533, | |
| "eval_steps_per_second": 2.994, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 0.001, | |
| "loss": 0.1085, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 0.001, | |
| "loss": 0.1024, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 0.001, | |
| "loss": 0.1073, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 0.001, | |
| "loss": 0.1075, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.1193, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 0.001, | |
| "loss": 0.1191, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.1286, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "eval_loss": 4.119844436645508, | |
| "eval_runtime": 14.3458, | |
| "eval_samples_per_second": 23.561, | |
| "eval_steps_per_second": 2.997, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.1073, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.0944, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 0.001, | |
| "loss": 0.0973, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 0.001, | |
| "loss": 0.0922, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 17.67, | |
| "learning_rate": 0.001, | |
| "loss": 0.0969, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.096, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 0.001, | |
| "loss": 0.1022, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "eval_loss": 4.186199188232422, | |
| "eval_runtime": 14.357, | |
| "eval_samples_per_second": 23.543, | |
| "eval_steps_per_second": 2.995, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 0.001, | |
| "loss": 0.0902, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.083, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.0826, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 0.001, | |
| "loss": 0.0955, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.0997, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 0.001, | |
| "loss": 0.1227, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 0.001, | |
| "loss": 0.1122, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_loss": 4.638622760772705, | |
| "eval_runtime": 14.3606, | |
| "eval_samples_per_second": 23.537, | |
| "eval_steps_per_second": 2.994, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 19.06, | |
| "learning_rate": 0.001, | |
| "loss": 0.0904, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 0.001, | |
| "loss": 0.0891, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 0.001, | |
| "loss": 0.0887, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 0.001, | |
| "loss": 0.0976, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 0.001, | |
| "loss": 0.1121, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 19.76, | |
| "learning_rate": 0.001, | |
| "loss": 0.09, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.093, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 19.97, | |
| "eval_loss": 4.682866096496582, | |
| "eval_runtime": 14.3499, | |
| "eval_samples_per_second": 23.554, | |
| "eval_steps_per_second": 2.997, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 20.03, | |
| "learning_rate": 0.001, | |
| "loss": 0.0847, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 20.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.0754, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 20.31, | |
| "learning_rate": 0.001, | |
| "loss": 0.0757, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 0.001, | |
| "loss": 0.0688, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 20.59, | |
| "learning_rate": 0.001, | |
| "loss": 0.0723, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 0.001, | |
| "loss": 0.079, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 20.87, | |
| "learning_rate": 0.001, | |
| "loss": 0.0783, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 20.94, | |
| "eval_loss": 4.663684844970703, | |
| "eval_runtime": 14.3504, | |
| "eval_samples_per_second": 23.553, | |
| "eval_steps_per_second": 2.996, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 0.001, | |
| "loss": 0.0779, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "learning_rate": 0.001, | |
| "loss": 0.0648, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.0594, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 0.001, | |
| "loss": 0.0644, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.0682, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.0702, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 21.84, | |
| "learning_rate": 0.001, | |
| "loss": 0.0686, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "learning_rate": 0.001, | |
| "loss": 0.0698, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_loss": 4.718987941741943, | |
| "eval_runtime": 14.3394, | |
| "eval_samples_per_second": 23.571, | |
| "eval_steps_per_second": 2.999, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 22.12, | |
| "learning_rate": 0.001, | |
| "loss": 0.0702, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 22.26, | |
| "learning_rate": 0.001, | |
| "loss": 0.0713, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.0606, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "learning_rate": 0.001, | |
| "loss": 0.0599, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 22.68, | |
| "learning_rate": 0.001, | |
| "loss": 0.0652, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 22.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.0643, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.0688, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "eval_loss": 5.020025253295898, | |
| "eval_runtime": 14.3306, | |
| "eval_samples_per_second": 23.586, | |
| "eval_steps_per_second": 3.001, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "learning_rate": 0.001, | |
| "loss": 0.0584, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.0565, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 23.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.0551, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 23.51, | |
| "learning_rate": 0.001, | |
| "loss": 0.056, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 23.65, | |
| "learning_rate": 0.001, | |
| "loss": 0.0585, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 23.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.0589, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.0633, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 4.757626056671143, | |
| "eval_runtime": 14.3331, | |
| "eval_samples_per_second": 23.582, | |
| "eval_steps_per_second": 3.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 24.07, | |
| "learning_rate": 0.001, | |
| "loss": 0.0617, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 0.001, | |
| "loss": 0.0524, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 24.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.0506, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "learning_rate": 0.001, | |
| "loss": 0.0482, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 24.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.0543, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 24.77, | |
| "learning_rate": 0.001, | |
| "loss": 0.0563, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.0609, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 24.97, | |
| "eval_loss": 4.7804856300354, | |
| "eval_runtime": 14.3386, | |
| "eval_samples_per_second": 23.573, | |
| "eval_steps_per_second": 2.999, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "learning_rate": 0.001, | |
| "loss": 0.054, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 0.001, | |
| "loss": 0.0577, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.052, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 25.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.0472, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 0.001, | |
| "loss": 0.0527, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 25.74, | |
| "learning_rate": 0.001, | |
| "loss": 0.0516, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 25.88, | |
| "learning_rate": 0.001, | |
| "loss": 0.0553, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "eval_loss": 4.733786582946777, | |
| "eval_runtime": 14.3354, | |
| "eval_samples_per_second": 23.578, | |
| "eval_steps_per_second": 3.0, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.0575, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 26.16, | |
| "learning_rate": 0.001, | |
| "loss": 0.0579, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 26.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.0598, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 0.001, | |
| "loss": 0.0647, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.0486, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 26.71, | |
| "learning_rate": 0.001, | |
| "loss": 0.0434, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.0523, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.0503, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_loss": 5.140863418579102, | |
| "eval_runtime": 14.327, | |
| "eval_samples_per_second": 23.592, | |
| "eval_steps_per_second": 3.001, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 27.13, | |
| "learning_rate": 0.001, | |
| "loss": 0.0393, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 0.001, | |
| "loss": 0.038, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 27.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.0407, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "learning_rate": 0.001, | |
| "loss": 0.0417, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.0437, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 27.83, | |
| "learning_rate": 0.001, | |
| "loss": 0.0448, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 27.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.0471, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 27.97, | |
| "eval_loss": 5.14629602432251, | |
| "eval_runtime": 14.3389, | |
| "eval_samples_per_second": 23.572, | |
| "eval_steps_per_second": 2.999, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 28.1, | |
| "learning_rate": 0.001, | |
| "loss": 0.041, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 0.001, | |
| "loss": 0.0391, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 28.38, | |
| "learning_rate": 0.001, | |
| "loss": 0.0429, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.0472, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 0.001, | |
| "loss": 0.0458, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 0.001, | |
| "loss": 0.0451, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "learning_rate": 0.001, | |
| "loss": 0.0472, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "eval_loss": 5.163626194000244, | |
| "eval_runtime": 14.3465, | |
| "eval_samples_per_second": 23.56, | |
| "eval_steps_per_second": 2.997, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 29.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.0403, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "learning_rate": 0.001, | |
| "loss": 0.0376, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "eval_loss": 5.132218360900879, | |
| "eval_runtime": 14.3004, | |
| "eval_samples_per_second": 23.636, | |
| "eval_steps_per_second": 3.007, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "step": 420, | |
| "total_flos": 8.206795539988808e+17, | |
| "train_loss": 0.5600467140298514, | |
| "train_runtime": 18789.4517, | |
| "train_samples_per_second": 5.864, | |
| "train_steps_per_second": 0.022 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 420, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 8.206795539988808e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |