| { | |
| "best_metric": 0.6934562921524048, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3631411711302769, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007262823422605538, | |
| "grad_norm": 757.0447387695312, | |
| "learning_rate": 5e-05, | |
| "loss": 135.1837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007262823422605538, | |
| "eval_loss": 8.22868537902832, | |
| "eval_runtime": 39.8556, | |
| "eval_samples_per_second": 23.284, | |
| "eval_steps_per_second": 2.911, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014525646845211076, | |
| "grad_norm": 747.141357421875, | |
| "learning_rate": 0.0001, | |
| "loss": 131.3447, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.021788470267816613, | |
| "grad_norm": 548.4541625976562, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 91.2526, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029051293690422152, | |
| "grad_norm": 472.23724365234375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 36.9233, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03631411711302769, | |
| "grad_norm": 139.50637817382812, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 15.9416, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04357694053563323, | |
| "grad_norm": 146.060546875, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 13.3003, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05083976395823876, | |
| "grad_norm": 171.13265991210938, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 13.0267, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.058102587380844305, | |
| "grad_norm": 96.99691772460938, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.6702, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06536541080344985, | |
| "grad_norm": 79.12115478515625, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 12.0797, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07262823422605538, | |
| "grad_norm": 48.217872619628906, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.7645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07989105764866092, | |
| "grad_norm": 55.47645950317383, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.6196, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08715388107126645, | |
| "grad_norm": 42.153377532958984, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.127, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09441670449387199, | |
| "grad_norm": 52.46333694458008, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.4603, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10167952791647752, | |
| "grad_norm": 68.24935913085938, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.1835, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10894235133908307, | |
| "grad_norm": 125.4776611328125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 12.2181, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11620517476168861, | |
| "grad_norm": 19.295351028442383, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.147, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12346799818429414, | |
| "grad_norm": 12.639065742492676, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.0682, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1307308216068997, | |
| "grad_norm": 24.26004981994629, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.1338, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13799364502950523, | |
| "grad_norm": 27.72160530090332, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.9968, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14525646845211077, | |
| "grad_norm": 6.638045787811279, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.0286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1525192918747163, | |
| "grad_norm": 17.952770233154297, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.879, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15978211529732184, | |
| "grad_norm": 17.280000686645508, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.8849, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16704493871992737, | |
| "grad_norm": 33.57490158081055, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.2934, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1743077621425329, | |
| "grad_norm": 30.653684616088867, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.4397, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18157058556513844, | |
| "grad_norm": 30.588258743286133, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.1079, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18157058556513844, | |
| "eval_loss": 0.699822187423706, | |
| "eval_runtime": 39.8658, | |
| "eval_samples_per_second": 23.278, | |
| "eval_steps_per_second": 2.91, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18883340898774398, | |
| "grad_norm": 31.9716796875, | |
| "learning_rate": 5e-05, | |
| "loss": 11.1079, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1960962324103495, | |
| "grad_norm": 439.19219970703125, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 12.9629, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.20335905583295505, | |
| "grad_norm": 19.925203323364258, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.2184, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2106218792555606, | |
| "grad_norm": 22.091087341308594, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.253, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.21788470267816615, | |
| "grad_norm": 15.780365943908691, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.1041, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22514752610077168, | |
| "grad_norm": 22.305627822875977, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.3212, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23241034952337722, | |
| "grad_norm": 14.443148612976074, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.0897, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.23967317294598275, | |
| "grad_norm": 20.79016876220703, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.3697, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2469359963685883, | |
| "grad_norm": 15.159466743469238, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.9596, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.25419881979119385, | |
| "grad_norm": 9.283771514892578, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.1473, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2614616432137994, | |
| "grad_norm": 10.101941108703613, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.1644, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2687244666364049, | |
| "grad_norm": 7.609732627868652, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.0647, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.27598729005901046, | |
| "grad_norm": 11.511059761047363, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.1036, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.283250113481616, | |
| "grad_norm": 13.059183120727539, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.1317, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.29051293690422153, | |
| "grad_norm": 12.633243560791016, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.2251, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29777576032682707, | |
| "grad_norm": 18.697067260742188, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.1338, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3050385837494326, | |
| "grad_norm": 11.478179931640625, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.1041, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.31230140717203814, | |
| "grad_norm": 15.045670509338379, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.9997, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3195642305946437, | |
| "grad_norm": 12.63309097290039, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.0959, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3268270540172492, | |
| "grad_norm": 17.579280853271484, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.1073, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.33408987743985474, | |
| "grad_norm": 6.669552803039551, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.0868, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3413527008624603, | |
| "grad_norm": 12.905702590942383, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.1601, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3486155242850658, | |
| "grad_norm": 10.452112197875977, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.0427, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.35587834770767135, | |
| "grad_norm": 5.756313800811768, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.0349, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3631411711302769, | |
| "grad_norm": 21.877653121948242, | |
| "learning_rate": 0.0, | |
| "loss": 11.1446, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3631411711302769, | |
| "eval_loss": 0.6934562921524048, | |
| "eval_runtime": 39.8532, | |
| "eval_samples_per_second": 23.285, | |
| "eval_steps_per_second": 2.911, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |