| { | |
| "best_metric": 2.710082769393921, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4581901489117984, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009163802978235968, | |
| "grad_norm": 2.739647150039673, | |
| "learning_rate": 5e-05, | |
| "loss": 5.957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009163802978235968, | |
| "eval_loss": 7.1486029624938965, | |
| "eval_runtime": 20.1126, | |
| "eval_samples_per_second": 36.544, | |
| "eval_steps_per_second": 4.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018327605956471937, | |
| "grad_norm": 2.6440541744232178, | |
| "learning_rate": 0.0001, | |
| "loss": 6.1652, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027491408934707903, | |
| "grad_norm": 1.9897960424423218, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.4135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03665521191294387, | |
| "grad_norm": 1.768525242805481, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.3757, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.045819014891179836, | |
| "grad_norm": 1.59767484664917, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.2466, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.054982817869415807, | |
| "grad_norm": 1.9405611753463745, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.4542, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06414662084765177, | |
| "grad_norm": 1.861006259918213, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.3458, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07331042382588775, | |
| "grad_norm": 2.1879544258117676, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.2434, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 1.9717111587524414, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.6999, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09163802978235967, | |
| "grad_norm": 2.4638028144836426, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 7.0218, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10080183276059565, | |
| "grad_norm": 2.9938299655914307, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 7.0497, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10996563573883161, | |
| "grad_norm": 3.223071336746216, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.917, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11912943871706758, | |
| "grad_norm": 3.207354784011841, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.9554, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12829324169530354, | |
| "grad_norm": 4.494226932525635, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.2911, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 3.629237174987793, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 5.6371, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1466208476517755, | |
| "grad_norm": 2.391883373260498, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.6656, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15578465063001146, | |
| "grad_norm": 2.5527169704437256, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 5.6105, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 3.839158535003662, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.2919, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17411225658648338, | |
| "grad_norm": 5.692999839782715, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 5.0472, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18327605956471935, | |
| "grad_norm": 8.748204231262207, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.9327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19243986254295534, | |
| "grad_norm": 4.1157941818237305, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 5.1645, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2016036655211913, | |
| "grad_norm": 7.310372829437256, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 5.9125, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21076746849942726, | |
| "grad_norm": 8.642070770263672, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 5.1201, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21993127147766323, | |
| "grad_norm": 9.681233406066895, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.7367, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2290950744558992, | |
| "grad_norm": 10.773985862731934, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.3683, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2290950744558992, | |
| "eval_loss": 4.320591449737549, | |
| "eval_runtime": 20.1553, | |
| "eval_samples_per_second": 36.467, | |
| "eval_steps_per_second": 4.565, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23825887743413515, | |
| "grad_norm": 14.602640151977539, | |
| "learning_rate": 5e-05, | |
| "loss": 4.5919, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 16.663705825805664, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 5.5504, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2565864833906071, | |
| "grad_norm": 14.454683303833008, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 5.3415, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.26575028636884307, | |
| "grad_norm": 9.233696937561035, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 4.6802, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.27491408934707906, | |
| "grad_norm": 7.224252700805664, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 4.4319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.284077892325315, | |
| "grad_norm": 7.030068874359131, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.4814, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.293241695303551, | |
| "grad_norm": 6.364577293395996, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4798, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3024054982817869, | |
| "grad_norm": 6.61119270324707, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.2206, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3115693012600229, | |
| "grad_norm": 7.3994035720825195, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.4515, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3207331042382589, | |
| "grad_norm": 12.4517240524292, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.4029, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 10.87969970703125, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.2815, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.33906071019473083, | |
| "grad_norm": 11.173131942749023, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.9704, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.34822451317296677, | |
| "grad_norm": 9.83188247680664, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1668, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.35738831615120276, | |
| "grad_norm": 10.8068265914917, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.6899, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3665521191294387, | |
| "grad_norm": 10.032576560974121, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 4.7501, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3757159221076747, | |
| "grad_norm": 9.974946022033691, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.5821, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3848797250859107, | |
| "grad_norm": 9.801668167114258, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.4434, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3940435280641466, | |
| "grad_norm": 9.01752758026123, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2707, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4032073310423826, | |
| "grad_norm": 9.52054214477539, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7401, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 8.228753089904785, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.2554, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4215349369988545, | |
| "grad_norm": 13.116497039794922, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.9396, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4306987399770905, | |
| "grad_norm": 14.946843147277832, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.3675, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.43986254295532645, | |
| "grad_norm": 7.809497833251953, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3153, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.44902634593356244, | |
| "grad_norm": 8.037880897521973, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1886, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4581901489117984, | |
| "grad_norm": 7.643946647644043, | |
| "learning_rate": 0.0, | |
| "loss": 2.1599, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4581901489117984, | |
| "eval_loss": 2.710082769393921, | |
| "eval_runtime": 20.1677, | |
| "eval_samples_per_second": 36.444, | |
| "eval_steps_per_second": 4.562, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |