| { | |
| "best_metric": 0.7085694074630737, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5475701574264202, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010951403148528405, | |
| "grad_norm": 0.20585939288139343, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6359, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010951403148528405, | |
| "eval_loss": 0.9495000243186951, | |
| "eval_runtime": 19.4613, | |
| "eval_samples_per_second": 31.601, | |
| "eval_steps_per_second": 3.957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02190280629705681, | |
| "grad_norm": 0.26404446363449097, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7533, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03285420944558522, | |
| "grad_norm": 0.32248711585998535, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7996, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04380561259411362, | |
| "grad_norm": 0.2888813316822052, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.7914, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05475701574264202, | |
| "grad_norm": 0.28381863236427307, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7477, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06570841889117043, | |
| "grad_norm": 0.33031395077705383, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7889, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07665982203969883, | |
| "grad_norm": 0.3351472020149231, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8139, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08761122518822724, | |
| "grad_norm": 0.3188571333885193, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7988, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09856262833675565, | |
| "grad_norm": 0.33074623346328735, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8385, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10951403148528405, | |
| "grad_norm": 0.32532212138175964, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8273, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12046543463381246, | |
| "grad_norm": 0.36339515447616577, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7568, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13141683778234087, | |
| "grad_norm": 0.39483535289764404, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.79, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14236824093086928, | |
| "grad_norm": 0.37402844429016113, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6161, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15331964407939766, | |
| "grad_norm": 0.33068445324897766, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7154, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16427104722792607, | |
| "grad_norm": 0.23060770332813263, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.692, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17522245037645448, | |
| "grad_norm": 0.22112268209457397, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7209, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1861738535249829, | |
| "grad_norm": 0.22095592319965363, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7102, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1971252566735113, | |
| "grad_norm": 0.242837056517601, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2080766598220397, | |
| "grad_norm": 0.2691846489906311, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7722, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2190280629705681, | |
| "grad_norm": 0.3350595235824585, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8121, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2299794661190965, | |
| "grad_norm": 0.2727764844894409, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7631, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24093086926762491, | |
| "grad_norm": 0.2959577143192291, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.811, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2518822724161533, | |
| "grad_norm": 0.3004992604255676, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7445, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.26283367556468173, | |
| "grad_norm": 0.3429405093193054, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7474, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2737850787132101, | |
| "grad_norm": 0.4970060884952545, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2737850787132101, | |
| "eval_loss": 0.7228643894195557, | |
| "eval_runtime": 19.4812, | |
| "eval_samples_per_second": 31.569, | |
| "eval_steps_per_second": 3.953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28473648186173856, | |
| "grad_norm": 0.20670099556446075, | |
| "learning_rate": 5e-05, | |
| "loss": 0.58, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29568788501026694, | |
| "grad_norm": 0.35974618792533875, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6536, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3066392881587953, | |
| "grad_norm": 0.2486371546983719, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6827, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31759069130732376, | |
| "grad_norm": 0.23610734939575195, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6706, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32854209445585214, | |
| "grad_norm": 0.2577800154685974, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7499, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3394934976043806, | |
| "grad_norm": 0.22855328023433685, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7138, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.35044490075290896, | |
| "grad_norm": 0.2566169500350952, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7411, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3613963039014374, | |
| "grad_norm": 0.2585206627845764, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7747, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3723477070499658, | |
| "grad_norm": 0.26253750920295715, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7487, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.38329911019849416, | |
| "grad_norm": 0.28885534405708313, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7874, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3942505133470226, | |
| "grad_norm": 0.334803968667984, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7935, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.405201916495551, | |
| "grad_norm": 0.4043166935443878, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.712, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4161533196440794, | |
| "grad_norm": 0.15596741437911987, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5926, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4271047227926078, | |
| "grad_norm": 0.14685985445976257, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6451, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4380561259411362, | |
| "grad_norm": 0.1911505162715912, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6359, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4490075290896646, | |
| "grad_norm": 0.20567315816879272, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6526, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.459958932238193, | |
| "grad_norm": 0.17049774527549744, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7154, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.47091033538672145, | |
| "grad_norm": 0.18450334668159485, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6847, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.48186173853524983, | |
| "grad_norm": 0.2177756428718567, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.743, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4928131416837782, | |
| "grad_norm": 0.21047337353229523, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7845, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5037645448323066, | |
| "grad_norm": 0.226828470826149, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.748, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5147159479808351, | |
| "grad_norm": 0.22788920998573303, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7197, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5256673511293635, | |
| "grad_norm": 0.2771904468536377, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7575, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5366187542778919, | |
| "grad_norm": 0.31342819333076477, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8068, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5475701574264202, | |
| "grad_norm": 0.4300288259983063, | |
| "learning_rate": 0.0, | |
| "loss": 0.7112, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5475701574264202, | |
| "eval_loss": 0.7085694074630737, | |
| "eval_runtime": 19.4794, | |
| "eval_samples_per_second": 31.572, | |
| "eval_steps_per_second": 3.953, | |
| "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": 5.969948642440643e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |