| { | |
| "best_metric": 1.001587986946106, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6535947712418301, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013071895424836602, | |
| "grad_norm": 2.024016857147217, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013071895424836602, | |
| "eval_loss": 3.283088207244873, | |
| "eval_runtime": 2.7144, | |
| "eval_samples_per_second": 47.524, | |
| "eval_steps_per_second": 6.263, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 2.3143575191497803, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7268, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 2.6737165451049805, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9629, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 2.5872859954833984, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6804, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06535947712418301, | |
| "grad_norm": 2.5839314460754395, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4699, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 2.526000738143921, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.0778, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0915032679738562, | |
| "grad_norm": 1.995295524597168, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.7944, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 2.1024668216705322, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.56, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 2.581193685531616, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.5621, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 1.8163655996322632, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.281, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1437908496732026, | |
| "grad_norm": 1.7008858919143677, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.2388, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 1.6543329954147339, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.1626, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16993464052287582, | |
| "grad_norm": 1.3217284679412842, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.0142, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1830065359477124, | |
| "grad_norm": 1.454737901687622, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.9512, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": 1.725643515586853, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7694, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20915032679738563, | |
| "grad_norm": 1.3168126344680786, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.7206, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 1.338275671005249, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.7628, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.4728039503097534, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.8099, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24836601307189543, | |
| "grad_norm": 2.4031965732574463, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.7916, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26143790849673204, | |
| "grad_norm": 2.386781692504883, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27450980392156865, | |
| "grad_norm": 2.096789598464966, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.6239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2875816993464052, | |
| "grad_norm": 1.6584792137145996, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.4677, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3006535947712418, | |
| "grad_norm": 1.3251094818115234, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.4149, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 1.231120228767395, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.3364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "grad_norm": 1.1836411952972412, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.1848, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "eval_loss": 1.137049913406372, | |
| "eval_runtime": 2.7599, | |
| "eval_samples_per_second": 46.741, | |
| "eval_steps_per_second": 6.16, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33986928104575165, | |
| "grad_norm": 1.1448719501495361, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.1828, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 1.1801111698150635, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.3119, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3660130718954248, | |
| "grad_norm": 1.3355175256729126, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.1409, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3790849673202614, | |
| "grad_norm": 1.2064152956008911, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.0365, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 1.1076024770736694, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.9831, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40522875816993464, | |
| "grad_norm": 1.229954719543457, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.859, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41830065359477125, | |
| "grad_norm": 1.0919172763824463, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.9309, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.43137254901960786, | |
| "grad_norm": 1.1399344205856323, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.8323, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.083505392074585, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.8003, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45751633986928103, | |
| "grad_norm": 1.2402992248535156, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7761, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.1251118183135986, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.5939, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48366013071895425, | |
| "grad_norm": 1.2075703144073486, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.6067, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.49673202614379086, | |
| "grad_norm": 1.3176946640014648, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.6173, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5098039215686274, | |
| "grad_norm": 1.2353657484054565, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.3562, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "grad_norm": 1.0886991024017334, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.2615, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5359477124183006, | |
| "grad_norm": 1.1880528926849365, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.2867, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5490196078431373, | |
| "grad_norm": 1.164398431777954, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.2298, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5620915032679739, | |
| "grad_norm": 1.153171181678772, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.352, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5751633986928104, | |
| "grad_norm": 1.2491941452026367, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.2632, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 1.230054497718811, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.2392, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6013071895424836, | |
| "grad_norm": 1.2693663835525513, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.2007, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6143790849673203, | |
| "grad_norm": 1.1482421159744263, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.0283, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 1.1393154859542847, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.9656, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6405228758169934, | |
| "grad_norm": 1.2570338249206543, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.0083, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "grad_norm": 1.1813966035842896, | |
| "learning_rate": 0.0, | |
| "loss": 0.8914, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "eval_loss": 1.001587986946106, | |
| "eval_runtime": 2.7671, | |
| "eval_samples_per_second": 46.619, | |
| "eval_steps_per_second": 6.144, | |
| "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": 5, | |
| "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": 1.43327370412032e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |