| { | |
| "best_metric": 0.5104753375053406, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1869436201780414, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02373887240356083, | |
| "grad_norm": 3.5102996826171875, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02373887240356083, | |
| "eval_loss": 5.237868309020996, | |
| "eval_runtime": 8.767, | |
| "eval_samples_per_second": 32.394, | |
| "eval_steps_per_second": 4.106, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 4.559767246246338, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7757, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0712166172106825, | |
| "grad_norm": 4.716976642608643, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8715, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09495548961424333, | |
| "grad_norm": 4.503242492675781, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.0717, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11869436201780416, | |
| "grad_norm": 4.489711761474609, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4133, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.142433234421365, | |
| "grad_norm": 4.380321979522705, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0491, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1661721068249258, | |
| "grad_norm": 3.194972515106201, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.595, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18991097922848665, | |
| "grad_norm": 3.0650548934936523, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3748, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21364985163204747, | |
| "grad_norm": 3.3243539333343506, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.2336, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": 3.5708813667297363, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.586, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26112759643916916, | |
| "grad_norm": 9.686392784118652, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4781, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.28486646884273, | |
| "grad_norm": 6.2913007736206055, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.072, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3086053412462908, | |
| "grad_norm": 3.2259066104888916, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8298, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3323442136498516, | |
| "grad_norm": 2.2587642669677734, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7495, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3560830860534125, | |
| "grad_norm": 2.2915780544281006, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7299, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3798219584569733, | |
| "grad_norm": 1.7781018018722534, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7055, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4035608308605341, | |
| "grad_norm": 1.786233901977539, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6982, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.42729970326409494, | |
| "grad_norm": 1.9483314752578735, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6991, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45103857566765576, | |
| "grad_norm": 2.8124682903289795, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7169, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.47477744807121663, | |
| "grad_norm": 2.301152229309082, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7964, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49851632047477745, | |
| "grad_norm": 4.760052680969238, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4733, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5222551928783383, | |
| "grad_norm": 6.619479179382324, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7624, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5459940652818991, | |
| "grad_norm": 3.6511471271514893, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6398, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.56973293768546, | |
| "grad_norm": 2.3520805835723877, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5849, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5934718100890207, | |
| "grad_norm": 2.007878541946411, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.565, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5934718100890207, | |
| "eval_loss": 0.6730909943580627, | |
| "eval_runtime": 8.7496, | |
| "eval_samples_per_second": 32.459, | |
| "eval_steps_per_second": 4.114, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6172106824925816, | |
| "grad_norm": 1.8642336130142212, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5677, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6409495548961425, | |
| "grad_norm": 1.8692430257797241, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5663, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6646884272997032, | |
| "grad_norm": 2.416127920150757, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5687, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6884272997032641, | |
| "grad_norm": 1.7100437879562378, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5918, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.712166172106825, | |
| "grad_norm": 1.4614720344543457, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6241, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7359050445103857, | |
| "grad_norm": 2.4405622482299805, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8421, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7596439169139466, | |
| "grad_norm": 1.6119067668914795, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5922, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7833827893175074, | |
| "grad_norm": 1.8556543588638306, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4792, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8071216617210683, | |
| "grad_norm": 1.4979634284973145, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4877, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8308605341246291, | |
| "grad_norm": 1.6719619035720825, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4963, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8545994065281899, | |
| "grad_norm": 1.8531289100646973, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4981, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8783382789317508, | |
| "grad_norm": 2.033458709716797, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9020771513353115, | |
| "grad_norm": 1.2323706150054932, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5143, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9258160237388724, | |
| "grad_norm": 1.3141870498657227, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9495548961424333, | |
| "grad_norm": 0.759944498538971, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.973293768545994, | |
| "grad_norm": 1.223227858543396, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6341, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9970326409495549, | |
| "grad_norm": 4.528719902038574, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.2729, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0207715133531157, | |
| "grad_norm": 3.4317986965179443, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8869, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0445103857566767, | |
| "grad_norm": 1.5157424211502075, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3913, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0682492581602374, | |
| "grad_norm": 1.3632839918136597, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4234, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0919881305637982, | |
| "grad_norm": 1.201500654220581, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4253, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.115727002967359, | |
| "grad_norm": 0.8647660613059998, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4257, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.13946587537092, | |
| "grad_norm": 1.1541858911514282, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4601, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1632047477744807, | |
| "grad_norm": 1.447519302368164, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4637, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1869436201780414, | |
| "grad_norm": 1.8496657609939575, | |
| "learning_rate": 0.0, | |
| "loss": 0.5039, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1869436201780414, | |
| "eval_loss": 0.5104753375053406, | |
| "eval_runtime": 8.7309, | |
| "eval_samples_per_second": 32.528, | |
| "eval_steps_per_second": 4.123, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |