| { | |
| "best_metric": 0.06591447442770004, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.297142857142857, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.045714285714285714, | |
| "grad_norm": 30.559879302978516, | |
| "learning_rate": 5e-05, | |
| "loss": 9.5855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045714285714285714, | |
| "eval_loss": 9.923667907714844, | |
| "eval_runtime": 5.0341, | |
| "eval_samples_per_second": 29.4, | |
| "eval_steps_per_second": 3.774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09142857142857143, | |
| "grad_norm": 31.74163055419922, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13714285714285715, | |
| "grad_norm": 31.216796875, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.977, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 18.54460906982422, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.5262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 15.97305965423584, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.0712, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2742857142857143, | |
| "grad_norm": 19.364259719848633, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7751, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 14.493821144104004, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7963, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3657142857142857, | |
| "grad_norm": 6.652883052825928, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3464, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4114285714285714, | |
| "grad_norm": 2.5194919109344482, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1942, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 3.323396682739258, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1913, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5028571428571429, | |
| "grad_norm": 8.00200366973877, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.206, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5485714285714286, | |
| "grad_norm": 6.022177219390869, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1759, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5942857142857143, | |
| "grad_norm": 2.013157367706299, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1574, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 8.512710571289062, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.8308360576629639, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7314285714285714, | |
| "grad_norm": 8.506197929382324, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2219, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7771428571428571, | |
| "grad_norm": 1.1248750686645508, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0869, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8228571428571428, | |
| "grad_norm": 6.81053352355957, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1161, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8685714285714285, | |
| "grad_norm": 3.1993627548217773, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1108, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 7.971470832824707, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1677, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.7401816844940186, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1145, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0114285714285713, | |
| "grad_norm": 3.9460668563842773, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1443, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0571428571428572, | |
| "grad_norm": 1.974686861038208, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0732, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1028571428571428, | |
| "grad_norm": 1.0119414329528809, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0658, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1485714285714286, | |
| "grad_norm": 1.9608573913574219, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0868, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1485714285714286, | |
| "eval_loss": 0.12119682133197784, | |
| "eval_runtime": 5.0424, | |
| "eval_samples_per_second": 29.351, | |
| "eval_steps_per_second": 3.768, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1942857142857144, | |
| "grad_norm": 1.4274019002914429, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0741, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 3.5917248725891113, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0649, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 2.621929407119751, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0699, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3314285714285714, | |
| "grad_norm": 7.4172587394714355, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0814, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3771428571428572, | |
| "grad_norm": 1.105510950088501, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4228571428571428, | |
| "grad_norm": 6.01181697845459, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0764, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4685714285714286, | |
| "grad_norm": 6.905984401702881, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0955, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5142857142857142, | |
| "grad_norm": 3.86792254447937, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0608, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 2.1256277561187744, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0715, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6057142857142859, | |
| "grad_norm": 1.1592352390289307, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0806, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6514285714285715, | |
| "grad_norm": 2.9074413776397705, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0529, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.697142857142857, | |
| "grad_norm": 0.9467344880104065, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0506, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7428571428571429, | |
| "grad_norm": 1.4687691926956177, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.044, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7885714285714287, | |
| "grad_norm": 3.692380905151367, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0465, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8342857142857143, | |
| "grad_norm": 1.5593693256378174, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0521, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 3.5100090503692627, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0833, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9257142857142857, | |
| "grad_norm": 2.3228797912597656, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0879, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9714285714285715, | |
| "grad_norm": 1.710174560546875, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0463, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0228571428571427, | |
| "grad_norm": 0.9889352321624756, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0852, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0685714285714285, | |
| "grad_norm": 0.7676489949226379, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.03, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.1142857142857143, | |
| "grad_norm": 1.2411009073257446, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0414, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 1.7227236032485962, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0425, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.2057142857142855, | |
| "grad_norm": 3.282838821411133, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0347, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.2514285714285713, | |
| "grad_norm": 1.625943899154663, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0295, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.297142857142857, | |
| "grad_norm": 0.8124039769172668, | |
| "learning_rate": 0.0, | |
| "loss": 0.0367, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.297142857142857, | |
| "eval_loss": 0.06591447442770004, | |
| "eval_runtime": 5.04, | |
| "eval_samples_per_second": 29.365, | |
| "eval_steps_per_second": 3.77, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |