| { | |
| "best_metric": 1.7126981019973755, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.024017467248908, | |
| "eval_steps": 25, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 7.276202201843262, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6181, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "eval_loss": 9.675775527954102, | |
| "eval_runtime": 4.7738, | |
| "eval_samples_per_second": 10.474, | |
| "eval_steps_per_second": 2.723, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13973799126637554, | |
| "grad_norm": 15.148102760314941, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5007, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2096069868995633, | |
| "grad_norm": 21.963546752929688, | |
| "learning_rate": 9.986796105326832e-05, | |
| "loss": 10.349, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2794759825327511, | |
| "grad_norm": 7.976142406463623, | |
| "learning_rate": 9.947261907011569e-05, | |
| "loss": 4.0854, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.34934497816593885, | |
| "grad_norm": 11.6079740524292, | |
| "learning_rate": 9.881629407450006e-05, | |
| "loss": 4.194, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4192139737991266, | |
| "grad_norm": 25.865581512451172, | |
| "learning_rate": 9.790283764247188e-05, | |
| "loss": 5.1507, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4890829694323144, | |
| "grad_norm": 52.45549774169922, | |
| "learning_rate": 9.673761029959427e-05, | |
| "loss": 6.001, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5589519650655022, | |
| "grad_norm": 7.9764790534973145, | |
| "learning_rate": 9.53274500632475e-05, | |
| "loss": 2.4012, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.62882096069869, | |
| "grad_norm": 4.158594131469727, | |
| "learning_rate": 9.368063231442406e-05, | |
| "loss": 2.2486, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6986899563318777, | |
| "grad_norm": 4.3454365730285645, | |
| "learning_rate": 9.18068212345023e-05, | |
| "loss": 2.2402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7685589519650655, | |
| "grad_norm": 6.039241790771484, | |
| "learning_rate": 8.971701309198744e-05, | |
| "loss": 2.0386, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8384279475982532, | |
| "grad_norm": 5.009244441986084, | |
| "learning_rate": 8.742347171203542e-05, | |
| "loss": 2.0645, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9082969432314411, | |
| "grad_norm": 6.780816078186035, | |
| "learning_rate": 8.493965650745043e-05, | |
| "loss": 2.1269, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9781659388646288, | |
| "grad_norm": 7.072220802307129, | |
| "learning_rate": 8.228014349349872e-05, | |
| "loss": 2.1961, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.054585152838428, | |
| "grad_norm": 5.04189395904541, | |
| "learning_rate": 7.946053975005496e-05, | |
| "loss": 3.4567, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1244541484716157, | |
| "grad_norm": 1.3596320152282715, | |
| "learning_rate": 7.649739183305184e-05, | |
| "loss": 1.8417, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1943231441048034, | |
| "grad_norm": 3.5074143409729004, | |
| "learning_rate": 7.34080886727103e-05, | |
| "loss": 1.8433, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2641921397379914, | |
| "grad_norm": 1.4482486248016357, | |
| "learning_rate": 7.021075952838262e-05, | |
| "loss": 1.621, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.334061135371179, | |
| "grad_norm": 1.9031111001968384, | |
| "learning_rate": 6.692416759884978e-05, | |
| "loss": 1.9068, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4039301310043668, | |
| "grad_norm": 1.749968409538269, | |
| "learning_rate": 6.356759991241008e-05, | |
| "loss": 1.7432, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4737991266375545, | |
| "grad_norm": 2.384965419769287, | |
| "learning_rate": 6.016075414292803e-05, | |
| "loss": 1.9039, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5436681222707422, | |
| "grad_norm": 1.4323326349258423, | |
| "learning_rate": 5.6723623016051596e-05, | |
| "loss": 1.6024, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6135371179039302, | |
| "grad_norm": 1.4713674783706665, | |
| "learning_rate": 5.3276376983948415e-05, | |
| "loss": 1.6041, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6834061135371179, | |
| "grad_norm": 2.0325393676757812, | |
| "learning_rate": 4.9839245857071994e-05, | |
| "loss": 1.6689, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7532751091703056, | |
| "grad_norm": 1.3920742273330688, | |
| "learning_rate": 4.643240008758992e-05, | |
| "loss": 1.4078, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7532751091703056, | |
| "eval_loss": 1.7126981019973755, | |
| "eval_runtime": 4.8406, | |
| "eval_samples_per_second": 10.329, | |
| "eval_steps_per_second": 2.686, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8231441048034935, | |
| "grad_norm": 1.3660728931427002, | |
| "learning_rate": 4.307583240115024e-05, | |
| "loss": 1.7941, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8930131004366813, | |
| "grad_norm": 1.4073928594589233, | |
| "learning_rate": 3.9789240471617385e-05, | |
| "loss": 1.6295, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.962882096069869, | |
| "grad_norm": 2.1648712158203125, | |
| "learning_rate": 3.659191132728971e-05, | |
| "loss": 1.7869, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.039301310043668, | |
| "grad_norm": 2.377962112426758, | |
| "learning_rate": 3.350260816694816e-05, | |
| "loss": 2.797, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.109170305676856, | |
| "grad_norm": 1.0877033472061157, | |
| "learning_rate": 3.0539460249945056e-05, | |
| "loss": 1.3597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.1790393013100435, | |
| "grad_norm": 1.52259361743927, | |
| "learning_rate": 2.7719856506501306e-05, | |
| "loss": 1.4955, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2489082969432315, | |
| "grad_norm": 0.9151427745819092, | |
| "learning_rate": 2.5060343492549566e-05, | |
| "loss": 0.9611, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3187772925764194, | |
| "grad_norm": 1.2203819751739502, | |
| "learning_rate": 2.257652828796459e-05, | |
| "loss": 1.9958, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.388646288209607, | |
| "grad_norm": 1.1448140144348145, | |
| "learning_rate": 2.0282986908012567e-05, | |
| "loss": 1.3613, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.458515283842795, | |
| "grad_norm": 1.8198349475860596, | |
| "learning_rate": 1.819317876549771e-05, | |
| "loss": 1.5567, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.5283842794759828, | |
| "grad_norm": 1.442224144935608, | |
| "learning_rate": 1.631936768557596e-05, | |
| "loss": 1.4807, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.5982532751091703, | |
| "grad_norm": 0.909432053565979, | |
| "learning_rate": 1.4672549936752506e-05, | |
| "loss": 1.3377, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.668122270742358, | |
| "grad_norm": 1.3751412630081177, | |
| "learning_rate": 1.3262389700405744e-05, | |
| "loss": 1.3987, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7379912663755457, | |
| "grad_norm": 0.9823693633079529, | |
| "learning_rate": 1.2097162357528127e-05, | |
| "loss": 0.8902, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.8078602620087336, | |
| "grad_norm": 1.2921277284622192, | |
| "learning_rate": 1.1183705925499948e-05, | |
| "loss": 1.981, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.8777292576419216, | |
| "grad_norm": 1.107571005821228, | |
| "learning_rate": 1.0527380929884324e-05, | |
| "loss": 1.401, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.947598253275109, | |
| "grad_norm": 1.6754684448242188, | |
| "learning_rate": 1.013203894673168e-05, | |
| "loss": 1.4869, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.024017467248908, | |
| "grad_norm": 2.1372737884521484, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5759, | |
| "step": 43 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 43, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.3100522362424525e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |