| { | |
| "best_metric": 0.9741932153701782, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09285051067780872, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018570102135561746, | |
| "grad_norm": 0.47194573283195496, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018570102135561746, | |
| "eval_loss": 1.4481745958328247, | |
| "eval_runtime": 33.9472, | |
| "eval_samples_per_second": 26.718, | |
| "eval_steps_per_second": 3.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003714020427112349, | |
| "grad_norm": 0.49819284677505493, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0455, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "grad_norm": 0.5030564069747925, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0282, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007428040854224698, | |
| "grad_norm": 0.517458975315094, | |
| "learning_rate": 8e-05, | |
| "loss": 1.068, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009285051067780872, | |
| "grad_norm": 0.5054612755775452, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0048, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011142061281337047, | |
| "grad_norm": 0.5697569251060486, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.9944, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012999071494893221, | |
| "grad_norm": 0.34437480568885803, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8405, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014856081708449397, | |
| "grad_norm": 0.3470451533794403, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.9741, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016713091922005572, | |
| "grad_norm": 0.42112597823143005, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.9068, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018570102135561744, | |
| "grad_norm": 0.3286053538322449, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.8783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02042711234911792, | |
| "grad_norm": 0.33338308334350586, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.0133, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "grad_norm": 0.32179006934165955, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.9356, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02414113277623027, | |
| "grad_norm": 0.3683066964149475, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.0115, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.025998142989786442, | |
| "grad_norm": 0.3992704749107361, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.1339, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.027855153203342618, | |
| "grad_norm": 0.3542136549949646, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.947, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029712163416898793, | |
| "grad_norm": 0.3169046938419342, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.968, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.031569173630454965, | |
| "grad_norm": 0.34261420369148254, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.0831, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.033426183844011144, | |
| "grad_norm": 0.3178490698337555, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.0376, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.035283194057567316, | |
| "grad_norm": 0.31970250606536865, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.1084, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03714020427112349, | |
| "grad_norm": 0.3838099241256714, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9999, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03899721448467967, | |
| "grad_norm": 0.3478296995162964, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.1841, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04085422469823584, | |
| "grad_norm": 0.32308429479599, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.9192, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04271123491179202, | |
| "grad_norm": 0.38567522168159485, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.0335, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 0.3469473719596863, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.0549, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04642525533890436, | |
| "grad_norm": 0.3284890353679657, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.0766, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04642525533890436, | |
| "eval_loss": 0.9847307801246643, | |
| "eval_runtime": 34.4301, | |
| "eval_samples_per_second": 26.343, | |
| "eval_steps_per_second": 3.311, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04828226555246054, | |
| "grad_norm": 0.31770119071006775, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.033, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05013927576601671, | |
| "grad_norm": 0.3336591422557831, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.9795, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.051996285979572884, | |
| "grad_norm": 0.33222416043281555, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.0338, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05385329619312906, | |
| "grad_norm": 0.3766303062438965, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.924, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.055710306406685235, | |
| "grad_norm": 0.38656023144721985, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.0457, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.057567316620241414, | |
| "grad_norm": 0.33840376138687134, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.0402, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.059424326833797586, | |
| "grad_norm": 0.3422689437866211, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.8613, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06128133704735376, | |
| "grad_norm": 0.37541311979293823, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.0384, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06313834726090993, | |
| "grad_norm": 0.35279935598373413, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.0677, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06499535747446611, | |
| "grad_norm": 0.3602738082408905, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1696, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06685236768802229, | |
| "grad_norm": 0.38732782006263733, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.1272, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06870937790157845, | |
| "grad_norm": 0.40577706694602966, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.9577, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07056638811513463, | |
| "grad_norm": 0.3912973403930664, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.0817, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07242339832869081, | |
| "grad_norm": 0.39627373218536377, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.9677, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07428040854224698, | |
| "grad_norm": 0.4169067144393921, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.1588, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07613741875580315, | |
| "grad_norm": 0.4882132411003113, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.0261, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07799442896935933, | |
| "grad_norm": 0.3861491084098816, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.9622, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07985143918291551, | |
| "grad_norm": 0.4414755403995514, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.1227, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08170844939647168, | |
| "grad_norm": 0.40376952290534973, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.9981, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08356545961002786, | |
| "grad_norm": 0.4256540834903717, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.9615, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08542246982358404, | |
| "grad_norm": 0.40966448187828064, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.1133, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0872794800371402, | |
| "grad_norm": 0.47860437631607056, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.9517, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 0.4424186646938324, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.0732, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09099350046425256, | |
| "grad_norm": 0.5190861225128174, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.9601, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09285051067780872, | |
| "grad_norm": 0.6566285490989685, | |
| "learning_rate": 0.0, | |
| "loss": 0.8175, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09285051067780872, | |
| "eval_loss": 0.9741932153701782, | |
| "eval_runtime": 33.8942, | |
| "eval_samples_per_second": 26.76, | |
| "eval_steps_per_second": 3.363, | |
| "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": 3.661363364757504e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |