| { | |
| "best_metric": 1.7662628889083862, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08406893652795293, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016813787305590584, | |
| "grad_norm": 10.135553359985352, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016813787305590584, | |
| "eval_loss": 3.21144437789917, | |
| "eval_runtime": 53.0035, | |
| "eval_samples_per_second": 18.904, | |
| "eval_steps_per_second": 2.377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003362757461118117, | |
| "grad_norm": 13.88785171508789, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1329, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005044136191677175, | |
| "grad_norm": 12.898653984069824, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1041, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006725514922236234, | |
| "grad_norm": 9.094704627990723, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8054, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008406893652795292, | |
| "grad_norm": 7.46572732925415, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5505, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01008827238335435, | |
| "grad_norm": 7.371476650238037, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.1935, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011769651113913409, | |
| "grad_norm": 7.186361789703369, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.3779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013451029844472467, | |
| "grad_norm": 11.818228721618652, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.1594, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015132408575031526, | |
| "grad_norm": 7.285848140716553, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.9909, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016813787305590584, | |
| "grad_norm": 8.513412475585938, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.8339, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018495166036149643, | |
| "grad_norm": 7.990869522094727, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.8169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0201765447667087, | |
| "grad_norm": 7.474752426147461, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.8376, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02185792349726776, | |
| "grad_norm": 6.102835178375244, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.7897, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023539302227826818, | |
| "grad_norm": 8.088296890258789, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.8382, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025220680958385876, | |
| "grad_norm": 6.149331092834473, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.4226, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026902059688944935, | |
| "grad_norm": 6.285677909851074, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.4337, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028583438419503993, | |
| "grad_norm": 12.84572982788086, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.9918, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03026481715006305, | |
| "grad_norm": 7.258878231048584, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.7715, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.031946195880622114, | |
| "grad_norm": 6.156888961791992, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.8406, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03362757461118117, | |
| "grad_norm": 4.980958461761475, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4166, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03530895334174023, | |
| "grad_norm": 4.382655620574951, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.5156, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036990332072299285, | |
| "grad_norm": 4.707004070281982, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.602, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03867171080285835, | |
| "grad_norm": 4.767475128173828, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6445, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0403530895334174, | |
| "grad_norm": 5.48907995223999, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.8305, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042034468263976464, | |
| "grad_norm": 4.800668239593506, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5833, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042034468263976464, | |
| "eval_loss": 1.8236191272735596, | |
| "eval_runtime": 54.1125, | |
| "eval_samples_per_second": 18.517, | |
| "eval_steps_per_second": 2.328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04371584699453552, | |
| "grad_norm": 5.956356048583984, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.0353, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04539722572509458, | |
| "grad_norm": 4.612515449523926, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.6238, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.047078604455653636, | |
| "grad_norm": 4.8809123039245605, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.9787, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0487599831862127, | |
| "grad_norm": 3.906742811203003, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.485, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05044136191677175, | |
| "grad_norm": 4.447406768798828, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.7703, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.052122740647330815, | |
| "grad_norm": 4.723405361175537, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.8074, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05380411937788987, | |
| "grad_norm": 4.21617317199707, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.551, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05548549810844893, | |
| "grad_norm": 4.369323253631592, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.7616, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.057166876839007986, | |
| "grad_norm": 4.459974765777588, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6983, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05884825556956705, | |
| "grad_norm": 4.366460800170898, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.511, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0605296343001261, | |
| "grad_norm": 4.228405952453613, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.783, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.062211013030685165, | |
| "grad_norm": 5.334435939788818, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.7047, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06389239176124423, | |
| "grad_norm": 4.155223846435547, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.5862, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 4.632593154907227, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8208, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06725514922236234, | |
| "grad_norm": 3.9671783447265625, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.5067, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06893652795292139, | |
| "grad_norm": 4.850368022918701, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6973, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07061790668348046, | |
| "grad_norm": 4.238636016845703, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.475, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07229928541403952, | |
| "grad_norm": 4.3667311668396, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7199, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07398066414459857, | |
| "grad_norm": 4.188448429107666, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.6647, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07566204287515763, | |
| "grad_norm": 4.366857528686523, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.5364, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0773434216057167, | |
| "grad_norm": 3.411229372024536, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.2497, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07902480033627575, | |
| "grad_norm": 4.079202651977539, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.5037, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0807061790668348, | |
| "grad_norm": 4.219734191894531, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.255, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08238755779739386, | |
| "grad_norm": 4.017161846160889, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.2695, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08406893652795293, | |
| "grad_norm": 4.850399017333984, | |
| "learning_rate": 0.0, | |
| "loss": 1.3426, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08406893652795293, | |
| "eval_loss": 1.7662628889083862, | |
| "eval_runtime": 54.1007, | |
| "eval_samples_per_second": 18.521, | |
| "eval_steps_per_second": 2.329, | |
| "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": 4.86582113009664e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |