| { | |
| "best_metric": 1.2940391302108765, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.1605839416058394, | |
| "eval_steps": 25, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07785888077858881, | |
| "grad_norm": 1.1597152948379517, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9417, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07785888077858881, | |
| "eval_loss": 2.3890843391418457, | |
| "eval_runtime": 0.9732, | |
| "eval_samples_per_second": 51.378, | |
| "eval_steps_per_second": 13.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15571776155717762, | |
| "grad_norm": 1.4161957502365112, | |
| "learning_rate": 0.0001, | |
| "loss": 2.156, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23357664233576642, | |
| "grad_norm": 2.1230530738830566, | |
| "learning_rate": 9.983788698441369e-05, | |
| "loss": 2.498, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.31143552311435524, | |
| "grad_norm": 0.6756812930107117, | |
| "learning_rate": 9.935271596564688e-05, | |
| "loss": 1.8508, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.38929440389294406, | |
| "grad_norm": 0.8647328019142151, | |
| "learning_rate": 9.854798261200746e-05, | |
| "loss": 1.9281, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.46715328467153283, | |
| "grad_norm": 1.298797607421875, | |
| "learning_rate": 9.74294850457488e-05, | |
| "loss": 2.1033, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5450121654501217, | |
| "grad_norm": 0.7344125509262085, | |
| "learning_rate": 9.600528206746612e-05, | |
| "loss": 1.7068, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6228710462287105, | |
| "grad_norm": 1.1638606786727905, | |
| "learning_rate": 9.428563509225347e-05, | |
| "loss": 1.7034, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7007299270072993, | |
| "grad_norm": 1.5177010297775269, | |
| "learning_rate": 9.22829342159729e-05, | |
| "loss": 1.8685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7785888077858881, | |
| "grad_norm": 0.8456931114196777, | |
| "learning_rate": 9.001160894432978e-05, | |
| "loss": 1.518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8564476885644768, | |
| "grad_norm": 1.1930115222930908, | |
| "learning_rate": 8.74880242279536e-05, | |
| "loss": 1.569, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9343065693430657, | |
| "grad_norm": 1.5629873275756836, | |
| "learning_rate": 8.473036255255366e-05, | |
| "loss": 1.6445, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0535279805352797, | |
| "grad_norm": 1.1714144945144653, | |
| "learning_rate": 8.175849293369291e-05, | |
| "loss": 2.489, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1313868613138687, | |
| "grad_norm": 0.8845990300178528, | |
| "learning_rate": 7.859382776007543e-05, | |
| "loss": 1.3716, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2092457420924574, | |
| "grad_norm": 1.3474788665771484, | |
| "learning_rate": 7.525916851679529e-05, | |
| "loss": 1.4771, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.287104622871046, | |
| "grad_norm": 1.5304101705551147, | |
| "learning_rate": 7.177854150011389e-05, | |
| "loss": 1.3313, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.364963503649635, | |
| "grad_norm": 0.6706894040107727, | |
| "learning_rate": 6.817702470744477e-05, | |
| "loss": 1.2673, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.442822384428224, | |
| "grad_norm": 0.7693089842796326, | |
| "learning_rate": 6.448056714980767e-05, | |
| "loss": 1.2907, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.5206812652068127, | |
| "grad_norm": 0.6204941868782043, | |
| "learning_rate": 6.071580188860955e-05, | |
| "loss": 1.3099, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.5985401459854014, | |
| "grad_norm": 0.5506797432899475, | |
| "learning_rate": 5.690985414382668e-05, | |
| "loss": 1.186, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.67639902676399, | |
| "grad_norm": 0.7013995051383972, | |
| "learning_rate": 5.3090145856173346e-05, | |
| "loss": 1.3578, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.754257907542579, | |
| "grad_norm": 0.5334713459014893, | |
| "learning_rate": 4.9284198111390456e-05, | |
| "loss": 1.1875, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.832116788321168, | |
| "grad_norm": 0.6609035134315491, | |
| "learning_rate": 4.551943285019234e-05, | |
| "loss": 1.1562, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.9099756690997567, | |
| "grad_norm": 0.723108172416687, | |
| "learning_rate": 4.182297529255525e-05, | |
| "loss": 1.22, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0291970802919708, | |
| "grad_norm": 0.9732814431190491, | |
| "learning_rate": 3.822145849988612e-05, | |
| "loss": 2.0469, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0291970802919708, | |
| "eval_loss": 1.2940391302108765, | |
| "eval_runtime": 0.9708, | |
| "eval_samples_per_second": 51.505, | |
| "eval_steps_per_second": 13.391, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1070559610705595, | |
| "grad_norm": 0.4368249177932739, | |
| "learning_rate": 3.474083148320469e-05, | |
| "loss": 1.0774, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.1849148418491486, | |
| "grad_norm": 0.6278235912322998, | |
| "learning_rate": 3.1406172239924584e-05, | |
| "loss": 1.1516, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.2627737226277373, | |
| "grad_norm": 0.5482242703437805, | |
| "learning_rate": 2.8241507066307104e-05, | |
| "loss": 1.0975, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.340632603406326, | |
| "grad_norm": 0.45156601071357727, | |
| "learning_rate": 2.5269637447446348e-05, | |
| "loss": 1.0717, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.4184914841849148, | |
| "grad_norm": 0.5456267595291138, | |
| "learning_rate": 2.2511975772046403e-05, | |
| "loss": 1.1172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.4963503649635035, | |
| "grad_norm": 0.5466234683990479, | |
| "learning_rate": 1.9988391055670233e-05, | |
| "loss": 1.1527, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.574209245742092, | |
| "grad_norm": 0.4269847571849823, | |
| "learning_rate": 1.771706578402711e-05, | |
| "loss": 1.0926, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.6520681265206814, | |
| "grad_norm": 0.5346320867538452, | |
| "learning_rate": 1.5714364907746536e-05, | |
| "loss": 1.0923, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.72992700729927, | |
| "grad_norm": 0.5671536326408386, | |
| "learning_rate": 1.3994717932533891e-05, | |
| "loss": 1.1694, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.807785888077859, | |
| "grad_norm": 0.4398534297943115, | |
| "learning_rate": 1.257051495425121e-05, | |
| "loss": 1.1125, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.885644768856448, | |
| "grad_norm": 0.560420572757721, | |
| "learning_rate": 1.1452017387992552e-05, | |
| "loss": 1.1148, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.004866180048662, | |
| "grad_norm": 0.9056612253189087, | |
| "learning_rate": 1.064728403435312e-05, | |
| "loss": 1.7632, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.0827250608272507, | |
| "grad_norm": 0.3938903212547302, | |
| "learning_rate": 1.0162113015586309e-05, | |
| "loss": 1.144, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.1605839416058394, | |
| "grad_norm": 0.48829081654548645, | |
| "learning_rate": 1e-05, | |
| "loss": 1.045, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 39, | |
| "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": 1.738816801115996e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |