| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 232, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00013638815138477438, | |
| "loss": 2.534, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013397182122930294, | |
| "loss": 2.1207, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001300082017869573, | |
| "loss": 1.9437, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00012459110818763681, | |
| "loss": 2.0463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.9048744440078735, | |
| "eval_runtime": 2.5437, | |
| "eval_samples_per_second": 44.03, | |
| "eval_steps_per_second": 5.504, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011784875792222071, | |
| "loss": 1.953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000109940736055617, | |
| "loss": 2.0751, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001010542179989503, | |
| "loss": 1.9436, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.139953924430466e-05, | |
| "loss": 1.8745, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.7966899871826172, | |
| "eval_runtime": 2.5987, | |
| "eval_samples_per_second": 43.099, | |
| "eval_steps_per_second": 5.387, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.120521692221673e-05, | |
| "loss": 1.8989, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.071254101695329e-05, | |
| "loss": 1.8346, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 6.016986326040062e-05, | |
| "loss": 1.8576, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.982671888105512e-05, | |
| "loss": 1.8876, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.760327935218811, | |
| "eval_runtime": 2.6932, | |
| "eval_samples_per_second": 41.586, | |
| "eval_steps_per_second": 5.198, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.992792034076668e-05, | |
| "loss": 1.7386, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0707762854909304e-05, | |
| "loss": 1.9309, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.2384478845846175e-05, | |
| "loss": 1.6283, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5155072587539005e-05, | |
| "loss": 1.9742, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.7276561260223389, | |
| "eval_runtime": 2.6936, | |
| "eval_samples_per_second": 41.581, | |
| "eval_steps_per_second": 5.198, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 1.8267, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.6324050628611986e-06, | |
| "loss": 1.7887, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5882054016913933e-06, | |
| "loss": 1.8381, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.3011164863877445e-07, | |
| "loss": 1.8954, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.7208999395370483, | |
| "eval_runtime": 2.7574, | |
| "eval_samples_per_second": 40.618, | |
| "eval_steps_per_second": 5.077, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.0216830127274476e-06, | |
| "loss": 1.8376, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.037005536513067e-07, | |
| "loss": 1.7024, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.515656508272057e-08, | |
| "loss": 1.7911, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.0213613921093164e-07, | |
| "loss": 1.8512, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.0277372298297e-06, | |
| "loss": 1.7573, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.8721970205680935e-06, | |
| "loss": 1.7902, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.88343684654658e-06, | |
| "loss": 1.7602, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.3988015692592823e-05, | |
| "loss": 1.8606, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.009247481060283e-05, | |
| "loss": 1.6102, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.708504883770769e-05, | |
| "loss": 1.8574, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.483771208671411e-05, | |
| "loss": 1.6927, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.320852254368187e-05, | |
| "loss": 1.7203, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.204422065684016e-05, | |
| "loss": 1.8592, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 6.118303533611755e-05, | |
| "loss": 1.7338, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.045764578878282e-05, | |
| "loss": 1.7386, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.969824496351964e-05, | |
| "loss": 1.6874, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.873564851492995e-05, | |
| "loss": 1.8691, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.740439236703416e-05, | |
| "loss": 1.7808, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00010554576216307802, | |
| "loss": 1.8296, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00011301069913603334, | |
| "loss": 1.737, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0001196625291967717, | |
| "loss": 1.8, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012537946527356269, | |
| "loss": 1.6787, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.000130056837088046, | |
| "loss": 1.664, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00013360900754314024, | |
| "loss": 1.5839, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0001359709406361119, | |
| "loss": 1.8525, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001370993921901871, | |
| "loss": 1.7228, | |
| "step": 230 | |
| } | |
| ], | |
| "max_steps": 232, | |
| "num_train_epochs": 2, | |
| "total_flos": 241695129600000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |