| { | |
| "best_metric": 2.345757484436035, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.31583103039873667, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006316620607974733, | |
| "grad_norm": 1.0546115636825562, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006316620607974733, | |
| "eval_loss": 4.693485736846924, | |
| "eval_runtime": 12.1496, | |
| "eval_samples_per_second": 87.822, | |
| "eval_steps_per_second": 11.029, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012633241215949467, | |
| "grad_norm": 1.034112811088562, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4964, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0189498618239242, | |
| "grad_norm": 1.0966734886169434, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.4648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025266482431898933, | |
| "grad_norm": 1.093819260597229, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03158310303987367, | |
| "grad_norm": 1.0864986181259155, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4582, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0378997236478484, | |
| "grad_norm": 1.3955763578414917, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.3022, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04421634425582313, | |
| "grad_norm": 1.4181126356124878, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.5895, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.050532964863797866, | |
| "grad_norm": 1.4454867839813232, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.3887, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0568495854717726, | |
| "grad_norm": 1.712357759475708, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.6758, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06316620607974734, | |
| "grad_norm": 1.7403721809387207, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.4681, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06948282668772207, | |
| "grad_norm": 1.7750122547149658, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5671, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0757994472956968, | |
| "grad_norm": 1.7761714458465576, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.612, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08211606790367154, | |
| "grad_norm": 1.295621633529663, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.9946, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08843268851164626, | |
| "grad_norm": 1.2954901456832886, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5626, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.094749309119621, | |
| "grad_norm": 1.24658203125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.456, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10106592972759573, | |
| "grad_norm": 1.1547346115112305, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.6964, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": 0.9776915311813354, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5982, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1136991709435452, | |
| "grad_norm": 0.916656494140625, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.7325, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12001579155151994, | |
| "grad_norm": 1.0522651672363281, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.449, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12633241215949467, | |
| "grad_norm": 1.15105402469635, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.6179, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1326490327674694, | |
| "grad_norm": 1.0923116207122803, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.4007, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13896565337544414, | |
| "grad_norm": 1.48521089553833, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.6068, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14528227398341886, | |
| "grad_norm": 1.5622447729110718, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.1056, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1515988945913936, | |
| "grad_norm": 1.3226696252822876, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.8389, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15791551519936833, | |
| "grad_norm": 1.5947855710983276, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.1764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15791551519936833, | |
| "eval_loss": 2.517580032348633, | |
| "eval_runtime": 12.3821, | |
| "eval_samples_per_second": 86.172, | |
| "eval_steps_per_second": 10.822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16423213580734308, | |
| "grad_norm": 0.7472804188728333, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1701, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1705487564153178, | |
| "grad_norm": 0.7590801119804382, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.3226, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17686537702329252, | |
| "grad_norm": 0.8624691367149353, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.1347, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18318199763126727, | |
| "grad_norm": 0.7706214189529419, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.2104, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.189498618239242, | |
| "grad_norm": 0.8338087201118469, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.4114, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19581523884721674, | |
| "grad_norm": 0.9004456996917725, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.487, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20213185945519146, | |
| "grad_norm": 0.9136253595352173, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4893, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2084484800631662, | |
| "grad_norm": 0.8845799565315247, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.2766, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21476510067114093, | |
| "grad_norm": 1.1320760250091553, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.6643, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22108172127911568, | |
| "grad_norm": 1.2713851928710938, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.7563, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2273983418870904, | |
| "grad_norm": 0.9692124128341675, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.7175, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23371496249506515, | |
| "grad_norm": 1.1749975681304932, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.5021, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24003158310303987, | |
| "grad_norm": 0.8900548219680786, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3335, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2463482037110146, | |
| "grad_norm": 0.689755916595459, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.1621, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.25266482431898935, | |
| "grad_norm": 0.7295820713043213, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.0389, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25898144492696407, | |
| "grad_norm": 0.7669286131858826, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2391, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2652980655349388, | |
| "grad_norm": 0.7550666332244873, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.0155, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.27161468614291356, | |
| "grad_norm": 0.7518640160560608, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2435, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2779313067508883, | |
| "grad_norm": 0.8904653191566467, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4775, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.284247927358863, | |
| "grad_norm": 0.891883134841919, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.4781, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2905645479668377, | |
| "grad_norm": 0.884515106678009, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.2253, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29688116857481245, | |
| "grad_norm": 1.0977036952972412, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.4993, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3031977891827872, | |
| "grad_norm": 1.0684934854507446, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.4539, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.30951440979076195, | |
| "grad_norm": 1.174559235572815, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.9581, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.31583103039873667, | |
| "grad_norm": 1.3068698644638062, | |
| "learning_rate": 0.0, | |
| "loss": 2.9451, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.31583103039873667, | |
| "eval_loss": 2.345757484436035, | |
| "eval_runtime": 12.1674, | |
| "eval_samples_per_second": 87.693, | |
| "eval_steps_per_second": 11.013, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |