| { | |
| "best_metric": 0.7039269208908081, | |
| "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": 0.26986071467399597, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6051, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010951403148528405, | |
| "eval_loss": 0.8239226937294006, | |
| "eval_runtime": 9.5849, | |
| "eval_samples_per_second": 64.163, | |
| "eval_steps_per_second": 8.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02190280629705681, | |
| "grad_norm": 0.3838704228401184, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6805, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03285420944558522, | |
| "grad_norm": 0.375266432762146, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7333, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04380561259411362, | |
| "grad_norm": 0.41876211762428284, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.734, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05475701574264202, | |
| "grad_norm": 0.4403587877750397, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7199, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06570841889117043, | |
| "grad_norm": 0.43424153327941895, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7105, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07665982203969883, | |
| "grad_norm": 0.45333054661750793, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7663, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08761122518822724, | |
| "grad_norm": 0.48293498158454895, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7875, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09856262833675565, | |
| "grad_norm": 0.4727921187877655, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7718, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10951403148528405, | |
| "grad_norm": 0.5101667046546936, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7961, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12046543463381246, | |
| "grad_norm": 0.5675897598266602, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7384, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13141683778234087, | |
| "grad_norm": 0.657037079334259, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7595, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14236824093086928, | |
| "grad_norm": 0.3988194465637207, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6365, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15331964407939766, | |
| "grad_norm": 0.42828720808029175, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.708, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16427104722792607, | |
| "grad_norm": 0.40163448452949524, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.709, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17522245037645448, | |
| "grad_norm": 0.36469730734825134, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7123, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1861738535249829, | |
| "grad_norm": 0.3585062026977539, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7037, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1971252566735113, | |
| "grad_norm": 0.35936301946640015, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7925, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2080766598220397, | |
| "grad_norm": 0.3914806842803955, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7094, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2190280629705681, | |
| "grad_norm": 0.41733092069625854, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6991, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2299794661190965, | |
| "grad_norm": 0.46973565220832825, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24093086926762491, | |
| "grad_norm": 0.5212298631668091, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.75, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2518822724161533, | |
| "grad_norm": 0.5571466684341431, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7327, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.26283367556468173, | |
| "grad_norm": 0.6130120754241943, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7344, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2737850787132101, | |
| "grad_norm": 0.8431180119514465, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6917, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2737850787132101, | |
| "eval_loss": 0.7081851363182068, | |
| "eval_runtime": 9.5906, | |
| "eval_samples_per_second": 64.125, | |
| "eval_steps_per_second": 8.029, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28473648186173856, | |
| "grad_norm": 0.22181300818920135, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6229, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29568788501026694, | |
| "grad_norm": 0.2770335376262665, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7119, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3066392881587953, | |
| "grad_norm": 0.2974836230278015, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6554, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31759069130732376, | |
| "grad_norm": 0.3229321837425232, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6485, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32854209445585214, | |
| "grad_norm": 0.3643602430820465, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.709, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3394934976043806, | |
| "grad_norm": 0.3989682197570801, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7386, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.35044490075290896, | |
| "grad_norm": 0.38096320629119873, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7503, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3613963039014374, | |
| "grad_norm": 0.41845908761024475, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7321, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3723477070499658, | |
| "grad_norm": 0.4356347322463989, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7387, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.38329911019849416, | |
| "grad_norm": 0.43814530968666077, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7351, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3942505133470226, | |
| "grad_norm": 0.49377891421318054, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7211, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.405201916495551, | |
| "grad_norm": 0.5536242723464966, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6815, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4161533196440794, | |
| "grad_norm": 0.21757011115550995, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5761, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4271047227926078, | |
| "grad_norm": 0.19792011380195618, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6702, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4380561259411362, | |
| "grad_norm": 0.23511400818824768, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7169, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4490075290896646, | |
| "grad_norm": 0.25927504897117615, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7027, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.459958932238193, | |
| "grad_norm": 0.29216915369033813, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6958, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.47091033538672145, | |
| "grad_norm": 0.31128939986228943, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7234, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.48186173853524983, | |
| "grad_norm": 0.3309127390384674, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6975, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4928131416837782, | |
| "grad_norm": 0.35349705815315247, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7576, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5037645448323066, | |
| "grad_norm": 0.39280784130096436, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.752, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5147159479808351, | |
| "grad_norm": 0.43009769916534424, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7541, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5256673511293635, | |
| "grad_norm": 0.46160510182380676, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7342, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5366187542778919, | |
| "grad_norm": 0.5528345108032227, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7234, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5475701574264202, | |
| "grad_norm": 0.6566212177276611, | |
| "learning_rate": 0.0, | |
| "loss": 0.6891, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5475701574264202, | |
| "eval_loss": 0.7039269208908081, | |
| "eval_runtime": 9.6057, | |
| "eval_samples_per_second": 64.024, | |
| "eval_steps_per_second": 8.016, | |
| "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": 2.955777588540211e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |