| { | |
| "best_metric": 1.203839659690857, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0025062656641603, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020050125313283207, | |
| "grad_norm": 57.44169235229492, | |
| "learning_rate": 5e-05, | |
| "loss": 29.8366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020050125313283207, | |
| "eval_loss": 1.9029018878936768, | |
| "eval_runtime": 9.9409, | |
| "eval_samples_per_second": 33.9, | |
| "eval_steps_per_second": 4.326, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.040100250626566414, | |
| "grad_norm": 62.32249450683594, | |
| "learning_rate": 0.0001, | |
| "loss": 30.5166, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 40.93547439575195, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 28.2018, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08020050125313283, | |
| "grad_norm": 35.38791275024414, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 25.9546, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10025062656641603, | |
| "grad_norm": 30.719402313232422, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 25.0195, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 35.03739547729492, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 22.8198, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 29.763837814331055, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 22.2005, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16040100250626566, | |
| "grad_norm": 23.81924057006836, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 21.9555, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": 21.821434020996094, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 21.521, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20050125313283207, | |
| "grad_norm": 14.969664573669434, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 20.8567, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22055137844611528, | |
| "grad_norm": 19.6236629486084, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 20.5385, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 15.633776664733887, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 21.3676, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2606516290726817, | |
| "grad_norm": 33.97491455078125, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 23.071, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 15.651145935058594, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 21.781, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 13.02273941040039, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 21.533, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3208020050125313, | |
| "grad_norm": 14.293069839477539, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 20.4337, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3408521303258145, | |
| "grad_norm": 11.110389709472656, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 19.9471, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3609022556390977, | |
| "grad_norm": 11.43124008178711, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 20.304, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 11.99350643157959, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 19.5163, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.40100250626566414, | |
| "grad_norm": 13.006141662597656, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 19.8078, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 12.299336433410645, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 19.1809, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44110275689223055, | |
| "grad_norm": 11.828144073486328, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 18.9601, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46115288220551376, | |
| "grad_norm": 11.213993072509766, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 19.4147, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48120300751879697, | |
| "grad_norm": 14.069252014160156, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 19.2054, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5012531328320802, | |
| "grad_norm": 13.004934310913086, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 20.1735, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5012531328320802, | |
| "eval_loss": 1.2464126348495483, | |
| "eval_runtime": 9.9182, | |
| "eval_samples_per_second": 33.978, | |
| "eval_steps_per_second": 4.335, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5213032581453634, | |
| "grad_norm": 20.708337783813477, | |
| "learning_rate": 5e-05, | |
| "loss": 20.6249, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5413533834586466, | |
| "grad_norm": 14.630321502685547, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 20.1283, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 11.598976135253906, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 19.5277, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.581453634085213, | |
| "grad_norm": 10.321036338806152, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 19.5442, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 10.965967178344727, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 19.2867, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6215538847117794, | |
| "grad_norm": 9.994596481323242, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 18.7013, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6416040100250626, | |
| "grad_norm": 11.583439826965332, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 19.2353, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6616541353383458, | |
| "grad_norm": 12.465306282043457, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 18.7672, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.681704260651629, | |
| "grad_norm": 11.203810691833496, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 18.2869, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 10.080780982971191, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 18.5907, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7218045112781954, | |
| "grad_norm": 10.475844383239746, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 18.5747, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7418546365914787, | |
| "grad_norm": 11.891578674316406, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 19.9692, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 10.97635269165039, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 20.1444, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7819548872180451, | |
| "grad_norm": 11.852622032165527, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 19.685, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8020050125313283, | |
| "grad_norm": 10.152228355407715, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 19.6661, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8220551378446115, | |
| "grad_norm": 10.249006271362305, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 19.1814, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 10.233469009399414, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 19.5634, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8621553884711779, | |
| "grad_norm": 9.331937789916992, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 18.4871, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8822055137844611, | |
| "grad_norm": 9.316566467285156, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 18.9376, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9022556390977443, | |
| "grad_norm": 8.677919387817383, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 18.0602, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9223057644110275, | |
| "grad_norm": 9.441269874572754, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 18.3775, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9423558897243107, | |
| "grad_norm": 9.658053398132324, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 19.1163, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9624060150375939, | |
| "grad_norm": 9.905299186706543, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 18.5178, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 14.224577903747559, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 18.3975, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0025062656641603, | |
| "grad_norm": 9.416265487670898, | |
| "learning_rate": 0.0, | |
| "loss": 19.4254, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0025062656641603, | |
| "eval_loss": 1.203839659690857, | |
| "eval_runtime": 9.9323, | |
| "eval_samples_per_second": 33.93, | |
| "eval_steps_per_second": 4.329, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.658027780734976e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |