| { | |
| "best_metric": 1.5011385679244995, | |
| "best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_sfd_bp_10/checkpoint-43", | |
| "epoch": 19.47826086956522, | |
| "eval_steps": 500, | |
| "global_step": 280, | |
| "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": 2.9672, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.001, | |
| "loss": 3.0162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.001, | |
| "loss": 3.1689, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.001, | |
| "loss": 2.902, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.001, | |
| "loss": 2.4891, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.001, | |
| "loss": 2.8498, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.001, | |
| "loss": 2.3973, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.9026896953582764, | |
| "eval_runtime": 84.3252, | |
| "eval_samples_per_second": 4.008, | |
| "eval_steps_per_second": 0.51, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.001, | |
| "loss": 2.1921, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.001, | |
| "loss": 2.0091, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.001, | |
| "loss": 1.8884, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.001, | |
| "loss": 1.7955, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.001, | |
| "loss": 1.7023, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.001, | |
| "loss": 1.8178, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.001, | |
| "loss": 1.9188, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 1.694077968597412, | |
| "eval_runtime": 84.303, | |
| "eval_samples_per_second": 4.009, | |
| "eval_steps_per_second": 0.51, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.001, | |
| "loss": 1.6461, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.001, | |
| "loss": 1.552, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.001, | |
| "loss": 1.4914, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.001, | |
| "loss": 1.457, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.001, | |
| "loss": 1.4499, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.001, | |
| "loss": 1.4868, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.001, | |
| "loss": 1.4297, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 1.5011385679244995, | |
| "eval_runtime": 84.2558, | |
| "eval_samples_per_second": 4.012, | |
| "eval_steps_per_second": 0.51, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.001, | |
| "loss": 1.3757, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.001, | |
| "loss": 1.2701, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.001, | |
| "loss": 1.2826, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.001, | |
| "loss": 1.2945, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 0.001, | |
| "loss": 1.2963, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.001, | |
| "loss": 1.2933, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.001, | |
| "loss": 1.2759, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 1.5048083066940308, | |
| "eval_runtime": 84.2663, | |
| "eval_samples_per_second": 4.011, | |
| "eval_steps_per_second": 0.51, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.001, | |
| "loss": 1.2446, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.001, | |
| "loss": 1.0992, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.001, | |
| "loss": 1.0771, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.001, | |
| "loss": 1.1254, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 0.001, | |
| "loss": 1.1644, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.001, | |
| "loss": 1.1485, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.001, | |
| "loss": 1.1421, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 1.5463248491287231, | |
| "eval_runtime": 84.2507, | |
| "eval_samples_per_second": 4.012, | |
| "eval_steps_per_second": 0.51, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.001, | |
| "loss": 1.1233, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 0.001, | |
| "loss": 0.8919, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.9349, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.001, | |
| "loss": 0.9363, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.9203, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.9429, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.001, | |
| "loss": 0.9495, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 0.001, | |
| "loss": 0.9605, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_loss": 1.6269720792770386, | |
| "eval_runtime": 84.2452, | |
| "eval_samples_per_second": 4.012, | |
| "eval_steps_per_second": 0.51, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.001, | |
| "loss": 0.7747, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.001, | |
| "loss": 0.7664, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.7998, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 0.001, | |
| "loss": 0.7715, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 0.001, | |
| "loss": 0.8038, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.8059, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.8082, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_loss": 1.7645633220672607, | |
| "eval_runtime": 84.2691, | |
| "eval_samples_per_second": 4.011, | |
| "eval_steps_per_second": 0.51, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.001, | |
| "loss": 0.6708, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.6186, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.6101, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 0.001, | |
| "loss": 0.6328, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 0.001, | |
| "loss": 0.6529, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.6312, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.664, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.78783118724823, | |
| "eval_runtime": 84.2285, | |
| "eval_samples_per_second": 4.013, | |
| "eval_steps_per_second": 0.511, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 0.001, | |
| "loss": 0.6177, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 0.001, | |
| "loss": 0.5241, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.5173, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 0.001, | |
| "loss": 0.5241, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.5546, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.001, | |
| "loss": 0.5401, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.5471, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_loss": 1.9499958753585815, | |
| "eval_runtime": 84.3243, | |
| "eval_samples_per_second": 4.008, | |
| "eval_steps_per_second": 0.51, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 0.001, | |
| "loss": 0.526, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 0.001, | |
| "loss": 0.409, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.4163, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.4304, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 0.001, | |
| "loss": 0.4512, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 0.001, | |
| "loss": 0.4396, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 0.001, | |
| "loss": 0.4349, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "eval_loss": 1.9656596183776855, | |
| "eval_runtime": 84.2136, | |
| "eval_samples_per_second": 4.014, | |
| "eval_steps_per_second": 0.511, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.4077, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.001, | |
| "loss": 0.3439, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.3503, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.001, | |
| "loss": 0.3572, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.3643, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 0.001, | |
| "loss": 0.3516, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.377, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.4338, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_loss": 2.135113477706909, | |
| "eval_runtime": 84.161, | |
| "eval_samples_per_second": 4.016, | |
| "eval_steps_per_second": 0.511, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.001, | |
| "loss": 0.2715, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 0.001, | |
| "loss": 0.2391, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.2958, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 0.001, | |
| "loss": 0.3101, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3417, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.001, | |
| "loss": 0.3292, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.2887, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "eval_loss": 2.11661434173584, | |
| "eval_runtime": 84.1912, | |
| "eval_samples_per_second": 4.015, | |
| "eval_steps_per_second": 0.511, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.001, | |
| "loss": 0.2532, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 0.001, | |
| "loss": 0.2565, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 0.001, | |
| "loss": 0.2791, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.2803, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 0.001, | |
| "loss": 0.3015, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.001, | |
| "loss": 0.2764, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 0.001, | |
| "loss": 0.2753, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "eval_loss": 2.4357352256774902, | |
| "eval_runtime": 84.1848, | |
| "eval_samples_per_second": 4.015, | |
| "eval_steps_per_second": 0.511, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.2563, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 0.001, | |
| "loss": 0.2024, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 0.001, | |
| "loss": 0.2252, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 0.001, | |
| "loss": 0.2487, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.2086, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 0.001, | |
| "loss": 0.2181, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.2114, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_loss": 2.5789217948913574, | |
| "eval_runtime": 84.14, | |
| "eval_samples_per_second": 4.017, | |
| "eval_steps_per_second": 0.511, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.1828, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.001, | |
| "loss": 0.2025, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 0.001, | |
| "loss": 0.1991, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.1844, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 0.001, | |
| "loss": 0.1934, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 0.001, | |
| "loss": 0.2, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.001, | |
| "loss": 0.1805, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_loss": 2.6075170040130615, | |
| "eval_runtime": 84.2554, | |
| "eval_samples_per_second": 4.012, | |
| "eval_steps_per_second": 0.51, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 0.001, | |
| "loss": 0.1739, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 0.001, | |
| "loss": 0.1504, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.1431, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 0.001, | |
| "loss": 0.152, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.142, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 0.001, | |
| "loss": 0.145, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 0.001, | |
| "loss": 0.1476, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 0.001, | |
| "loss": 0.1543, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 2.5597331523895264, | |
| "eval_runtime": 84.1535, | |
| "eval_samples_per_second": 4.016, | |
| "eval_steps_per_second": 0.511, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 0.001, | |
| "loss": 0.1245, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 0.001, | |
| "loss": 0.1204, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 0.001, | |
| "loss": 0.2117, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 0.001, | |
| "loss": 0.6894, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 0.001, | |
| "loss": 0.35, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 0.001, | |
| "loss": 0.8395, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.5166, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "eval_loss": 2.5066745281219482, | |
| "eval_runtime": 84.1866, | |
| "eval_samples_per_second": 4.015, | |
| "eval_steps_per_second": 0.511, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 0.001, | |
| "loss": 0.202, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.1247, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 0.001, | |
| "loss": 0.1368, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 0.001, | |
| "loss": 0.1096, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 17.67, | |
| "learning_rate": 0.001, | |
| "loss": 0.1066, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.1078, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 0.001, | |
| "loss": 0.1117, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "eval_loss": 2.808701515197754, | |
| "eval_runtime": 84.1837, | |
| "eval_samples_per_second": 4.015, | |
| "eval_steps_per_second": 0.511, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 0.001, | |
| "loss": 0.0934, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 0.001, | |
| "loss": 0.0793, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.0887, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 0.001, | |
| "loss": 0.103, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.0847, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 0.001, | |
| "loss": 0.0869, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 0.001, | |
| "loss": 0.0895, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_loss": 2.7578108310699463, | |
| "eval_runtime": 84.2046, | |
| "eval_samples_per_second": 4.014, | |
| "eval_steps_per_second": 0.511, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 19.06, | |
| "learning_rate": 0.001, | |
| "loss": 0.0884, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 0.001, | |
| "loss": 0.0838, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 0.001, | |
| "loss": 0.0731, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 0.001, | |
| "loss": 0.0779, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "eval_loss": 2.892078161239624, | |
| "eval_runtime": 84.2063, | |
| "eval_samples_per_second": 4.014, | |
| "eval_steps_per_second": 0.511, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "step": 280, | |
| "total_flos": 4.895224157149471e+18, | |
| "train_loss": 0.722327525381531, | |
| "train_runtime": 70402.3599, | |
| "train_samples_per_second": 1.043, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 280, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 4.895224157149471e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |