| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993906154783668, | |
| "eval_steps": 500, | |
| "global_step": 410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02437538086532602, | |
| "grad_norm": 0.381931334733963, | |
| "learning_rate": 1.2195121951219513e-05, | |
| "loss": 3.6679, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04875076173065204, | |
| "grad_norm": 0.19698743522167206, | |
| "learning_rate": 2.4390243902439026e-05, | |
| "loss": 3.5098, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07312614259597806, | |
| "grad_norm": 0.26034015417099, | |
| "learning_rate": 3.6585365853658535e-05, | |
| "loss": 3.3353, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09750152346130408, | |
| "grad_norm": 0.29549556970596313, | |
| "learning_rate": 4.878048780487805e-05, | |
| "loss": 3.2342, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1218769043266301, | |
| "grad_norm": 0.2754429578781128, | |
| "learning_rate": 4.992664502959351e-05, | |
| "loss": 3.1812, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14625228519195613, | |
| "grad_norm": 0.3207014799118042, | |
| "learning_rate": 4.967362490933723e-05, | |
| "loss": 3.1661, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17062766605728213, | |
| "grad_norm": 0.30315226316452026, | |
| "learning_rate": 4.924186648858207e-05, | |
| "loss": 3.0649, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19500304692260817, | |
| "grad_norm": 0.26564204692840576, | |
| "learning_rate": 4.863449747015384e-05, | |
| "loss": 3.0024, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21937842778793418, | |
| "grad_norm": 0.3084321618080139, | |
| "learning_rate": 4.7855917698280054e-05, | |
| "loss": 2.9751, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2437538086532602, | |
| "grad_norm": 0.2992245554924011, | |
| "learning_rate": 4.691176728566159e-05, | |
| "loss": 3.0007, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2681291895185862, | |
| "grad_norm": 0.3074418306350708, | |
| "learning_rate": 4.580888575591068e-05, | |
| "loss": 2.9229, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29250457038391225, | |
| "grad_norm": 0.2845458984375, | |
| "learning_rate": 4.455526249733178e-05, | |
| "loss": 2.8955, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3168799512492383, | |
| "grad_norm": 0.3487965166568756, | |
| "learning_rate": 4.3159978886963226e-05, | |
| "loss": 2.8837, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34125533211456427, | |
| "grad_norm": 0.307179719209671, | |
| "learning_rate": 4.163314250413913e-05, | |
| "loss": 2.8862, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3656307129798903, | |
| "grad_norm": 0.3133622407913208, | |
| "learning_rate": 3.9985813910135304e-05, | |
| "loss": 2.9099, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39000609384521634, | |
| "grad_norm": 0.3793308138847351, | |
| "learning_rate": 3.8229926524315016e-05, | |
| "loss": 2.8219, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4143814747105424, | |
| "grad_norm": 0.3438339829444885, | |
| "learning_rate": 3.6378200177200224e-05, | |
| "loss": 2.7811, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43875685557586835, | |
| "grad_norm": 0.33851078152656555, | |
| "learning_rate": 3.444404896669865e-05, | |
| "loss": 2.8869, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4631322364411944, | |
| "grad_norm": 0.3436271846294403, | |
| "learning_rate": 3.2441484084985865e-05, | |
| "loss": 2.8078, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4875076173065204, | |
| "grad_norm": 0.29718300700187683, | |
| "learning_rate": 3.0385012319974537e-05, | |
| "loss": 2.8488, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5118829981718465, | |
| "grad_norm": 0.3266434073448181, | |
| "learning_rate": 2.8289530966636625e-05, | |
| "loss": 2.7989, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5362583790371724, | |
| "grad_norm": 0.3141980767250061, | |
| "learning_rate": 2.617021990945197e-05, | |
| "loss": 2.7921, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5606337599024985, | |
| "grad_norm": 0.3401101231575012, | |
| "learning_rate": 2.4042431657749117e-05, | |
| "loss": 2.8359, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5850091407678245, | |
| "grad_norm": 0.31733494997024536, | |
| "learning_rate": 2.1921580130533827e-05, | |
| "loss": 2.7748, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6093845216331505, | |
| "grad_norm": 0.3072984218597412, | |
| "learning_rate": 1.9823028996459486e-05, | |
| "loss": 2.7994, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6337599024984766, | |
| "grad_norm": 0.35069364309310913, | |
| "learning_rate": 1.7761980377816287e-05, | |
| "loss": 2.7459, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6581352833638026, | |
| "grad_norm": 0.3242040276527405, | |
| "learning_rate": 1.5753364724779092e-05, | |
| "loss": 2.838, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6825106642291285, | |
| "grad_norm": 0.3111414611339569, | |
| "learning_rate": 1.381173265767623e-05, | |
| "loss": 2.7298, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7068860450944546, | |
| "grad_norm": 0.3313029408454895, | |
| "learning_rate": 1.1951149560785167e-05, | |
| "loss": 2.7464, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7312614259597806, | |
| "grad_norm": 0.31917551159858704, | |
| "learning_rate": 1.0185093691228534e-05, | |
| "loss": 2.7118, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7556368068251066, | |
| "grad_norm": 0.3485548496246338, | |
| "learning_rate": 8.526358541080173e-06, | |
| "loss": 2.6857, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7800121876904327, | |
| "grad_norm": 0.31290727853775024, | |
| "learning_rate": 6.986960159980327e-06, | |
| "loss": 2.71, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8043875685557587, | |
| "grad_norm": 0.2982420325279236, | |
| "learning_rate": 5.578050109624511e-06, | |
| "loss": 2.8041, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8287629494210847, | |
| "grad_norm": 0.29485708475112915, | |
| "learning_rate": 4.309834680692832e-06, | |
| "loss": 2.6818, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8531383302864107, | |
| "grad_norm": 0.29043450951576233, | |
| "learning_rate": 3.1915009574206262e-06, | |
| "loss": 2.6666, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8775137111517367, | |
| "grad_norm": 0.32468873262405396, | |
| "learning_rate": 2.231150265406512e-06, | |
| "loss": 2.7277, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9018890920170628, | |
| "grad_norm": 0.3383389413356781, | |
| "learning_rate": 1.435739484768603e-06, | |
| "loss": 2.7256, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9262644728823888, | |
| "grad_norm": 0.31536731123924255, | |
| "learning_rate": 8.110306537826601e-07, | |
| "loss": 2.7143, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9506398537477148, | |
| "grad_norm": 0.30096814036369324, | |
| "learning_rate": 3.6154922807863643e-07, | |
| "loss": 2.7688, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9750152346130408, | |
| "grad_norm": 0.2999325096607208, | |
| "learning_rate": 9.055129777021665e-08, | |
| "loss": 2.7355, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9993906154783668, | |
| "grad_norm": 0.31551599502563477, | |
| "learning_rate": 0.0, | |
| "loss": 2.751, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9993906154783668, | |
| "step": 410, | |
| "total_flos": 6.066570733918618e+17, | |
| "train_loss": 2.8908857531663847, | |
| "train_runtime": 5592.6214, | |
| "train_samples_per_second": 2.346, | |
| "train_steps_per_second": 0.073 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 410, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.066570733918618e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |