| { | |
| "best_metric": 0.12850531935691833, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.057777777777778, | |
| "eval_steps": 25, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07111111111111111, | |
| "grad_norm": 10.621946334838867, | |
| "learning_rate": 5e-05, | |
| "loss": 4.5986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07111111111111111, | |
| "eval_loss": 4.047070503234863, | |
| "eval_runtime": 2.2359, | |
| "eval_samples_per_second": 22.363, | |
| "eval_steps_per_second": 5.814, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14222222222222222, | |
| "grad_norm": 10.229170799255371, | |
| "learning_rate": 0.0001, | |
| "loss": 4.85, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 12.011947631835938, | |
| "learning_rate": 9.986796105326832e-05, | |
| "loss": 2.3845, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.28444444444444444, | |
| "grad_norm": 7.307332515716553, | |
| "learning_rate": 9.947261907011569e-05, | |
| "loss": 2.6661, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 7.8294291496276855, | |
| "learning_rate": 9.881629407450006e-05, | |
| "loss": 2.5517, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4266666666666667, | |
| "grad_norm": 5.950700759887695, | |
| "learning_rate": 9.790283764247188e-05, | |
| "loss": 1.8005, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.49777777777777776, | |
| "grad_norm": 4.527182102203369, | |
| "learning_rate": 9.673761029959427e-05, | |
| "loss": 0.7795, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5688888888888889, | |
| "grad_norm": 4.891347408294678, | |
| "learning_rate": 9.53274500632475e-05, | |
| "loss": 1.3151, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 5.132640361785889, | |
| "learning_rate": 9.368063231442406e-05, | |
| "loss": 1.0905, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 4.243228912353516, | |
| "learning_rate": 9.18068212345023e-05, | |
| "loss": 0.4051, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7822222222222223, | |
| "grad_norm": 4.6263041496276855, | |
| "learning_rate": 8.971701309198744e-05, | |
| "loss": 0.5899, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8533333333333334, | |
| "grad_norm": 4.224740505218506, | |
| "learning_rate": 8.742347171203542e-05, | |
| "loss": 0.6464, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9244444444444444, | |
| "grad_norm": 2.696065902709961, | |
| "learning_rate": 8.493965650745043e-05, | |
| "loss": 0.5189, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9955555555555555, | |
| "grad_norm": 1.992374062538147, | |
| "learning_rate": 8.228014349349872e-05, | |
| "loss": 0.3264, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 2.549997568130493, | |
| "learning_rate": 7.946053975005496e-05, | |
| "loss": 0.5291, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1377777777777778, | |
| "grad_norm": 1.320655345916748, | |
| "learning_rate": 7.649739183305184e-05, | |
| "loss": 0.3864, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.208888888888889, | |
| "grad_norm": 1.1979525089263916, | |
| "learning_rate": 7.34080886727103e-05, | |
| "loss": 0.2127, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.1645714044570923, | |
| "learning_rate": 7.021075952838262e-05, | |
| "loss": 0.2644, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3511111111111112, | |
| "grad_norm": 1.229156732559204, | |
| "learning_rate": 6.692416759884978e-05, | |
| "loss": 0.211, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 1.3347893953323364, | |
| "learning_rate": 6.356759991241008e-05, | |
| "loss": 0.2191, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4933333333333334, | |
| "grad_norm": 0.9744674563407898, | |
| "learning_rate": 6.016075414292803e-05, | |
| "loss": 0.2399, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5644444444444443, | |
| "grad_norm": 0.7805840969085693, | |
| "learning_rate": 5.6723623016051596e-05, | |
| "loss": 0.1956, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6355555555555554, | |
| "grad_norm": 0.9620563983917236, | |
| "learning_rate": 5.3276376983948415e-05, | |
| "loss": 0.262, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7066666666666666, | |
| "grad_norm": 1.2612390518188477, | |
| "learning_rate": 4.9839245857071994e-05, | |
| "loss": 0.1155, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.9804985523223877, | |
| "learning_rate": 4.643240008758992e-05, | |
| "loss": 0.3372, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "eval_loss": 0.12850531935691833, | |
| "eval_runtime": 0.8159, | |
| "eval_samples_per_second": 61.281, | |
| "eval_steps_per_second": 15.933, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8488888888888888, | |
| "grad_norm": 0.7657303214073181, | |
| "learning_rate": 4.307583240115024e-05, | |
| "loss": 0.1534, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.1523308753967285, | |
| "learning_rate": 3.9789240471617385e-05, | |
| "loss": 0.1398, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.991111111111111, | |
| "grad_norm": 0.6146386861801147, | |
| "learning_rate": 3.659191132728971e-05, | |
| "loss": 0.1803, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.062222222222222, | |
| "grad_norm": 5.423893451690674, | |
| "learning_rate": 3.350260816694816e-05, | |
| "loss": 0.8846, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.7562944293022156, | |
| "learning_rate": 3.0539460249945056e-05, | |
| "loss": 0.185, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.2044444444444444, | |
| "grad_norm": 0.599077582359314, | |
| "learning_rate": 2.7719856506501306e-05, | |
| "loss": 0.1333, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2755555555555556, | |
| "grad_norm": 0.5775408744812012, | |
| "learning_rate": 2.5060343492549566e-05, | |
| "loss": 0.1894, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3466666666666667, | |
| "grad_norm": 0.893593966960907, | |
| "learning_rate": 2.257652828796459e-05, | |
| "loss": 0.1983, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.417777777777778, | |
| "grad_norm": 0.8925317525863647, | |
| "learning_rate": 2.0282986908012567e-05, | |
| "loss": 0.1313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.6804959774017334, | |
| "learning_rate": 1.819317876549771e-05, | |
| "loss": 0.1761, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.6663115620613098, | |
| "learning_rate": 1.631936768557596e-05, | |
| "loss": 0.2367, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.631111111111111, | |
| "grad_norm": 0.5432018637657166, | |
| "learning_rate": 1.4672549936752506e-05, | |
| "loss": 0.1042, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.7022222222222223, | |
| "grad_norm": 0.5868009328842163, | |
| "learning_rate": 1.3262389700405744e-05, | |
| "loss": 0.1132, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7733333333333334, | |
| "grad_norm": 0.6464464068412781, | |
| "learning_rate": 1.2097162357528127e-05, | |
| "loss": 0.2215, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.779269814491272, | |
| "learning_rate": 1.1183705925499948e-05, | |
| "loss": 0.1072, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.9155555555555557, | |
| "grad_norm": 0.7263559699058533, | |
| "learning_rate": 1.0527380929884324e-05, | |
| "loss": 0.151, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.986666666666667, | |
| "grad_norm": 0.471716970205307, | |
| "learning_rate": 1.013203894673168e-05, | |
| "loss": 0.133, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.057777777777778, | |
| "grad_norm": 3.000406503677368, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4811, | |
| "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": 4.053927872744653e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |