| { | |
| "best_metric": 11.758439064025879, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.021379513081589568, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004275902616317913, | |
| "grad_norm": 0.03745068982243538, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7662, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004275902616317913, | |
| "eval_loss": 11.763663291931152, | |
| "eval_runtime": 0.4241, | |
| "eval_samples_per_second": 117.908, | |
| "eval_steps_per_second": 30.656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008551805232635826, | |
| "grad_norm": 0.031333476305007935, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7643, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001282770784895374, | |
| "grad_norm": 0.03287268057465553, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.7653, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017103610465271652, | |
| "grad_norm": 0.03197765350341797, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.7642, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021379513081589566, | |
| "grad_norm": 0.03344624489545822, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.7638, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002565541569790748, | |
| "grad_norm": 0.03495028242468834, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.7636, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029931318314225393, | |
| "grad_norm": 0.03678389638662338, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.7632, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034207220930543305, | |
| "grad_norm": 0.037863459438085556, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.763, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003848312354686122, | |
| "grad_norm": 0.039279576390981674, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.7635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004275902616317913, | |
| "grad_norm": 0.0446021743118763, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.7636, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004703492877949704, | |
| "grad_norm": 0.039255332201719284, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.7627, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005131083139581496, | |
| "grad_norm": 0.04781685024499893, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.7616, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0055586734012132875, | |
| "grad_norm": 0.05885741114616394, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.7616, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005986263662845079, | |
| "grad_norm": 0.03861386701464653, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.7633, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00641385392447687, | |
| "grad_norm": 0.039729539304971695, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.7631, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006841444186108661, | |
| "grad_norm": 0.04080519452691078, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.7622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007269034447740453, | |
| "grad_norm": 0.04761909320950508, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.7628, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007696624709372244, | |
| "grad_norm": 0.042627450078725815, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.7624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008124214971004035, | |
| "grad_norm": 0.04835887625813484, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.7618, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008551805232635826, | |
| "grad_norm": 0.045272503048181534, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.7618, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008979395494267618, | |
| "grad_norm": 0.055312931537628174, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.761, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009406985755899409, | |
| "grad_norm": 0.05657023563981056, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.7605, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009834576017531202, | |
| "grad_norm": 0.05651591718196869, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.7603, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010262166279162993, | |
| "grad_norm": 0.05788685753941536, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.7604, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010689756540794784, | |
| "grad_norm": 0.06326596438884735, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.7596, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010689756540794784, | |
| "eval_loss": 11.760405540466309, | |
| "eval_runtime": 0.3942, | |
| "eval_samples_per_second": 126.842, | |
| "eval_steps_per_second": 32.979, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011117346802426575, | |
| "grad_norm": 0.0947161465883255, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.7612, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011544937064058366, | |
| "grad_norm": 0.0553748682141304, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.7607, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011972527325690157, | |
| "grad_norm": 0.05844997987151146, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012400117587321948, | |
| "grad_norm": 0.05783386155962944, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.7611, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01282770784895374, | |
| "grad_norm": 0.061772510409355164, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.7603, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01325529811058553, | |
| "grad_norm": 0.06448950618505478, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.7604, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013682888372217322, | |
| "grad_norm": 0.06722883880138397, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.7601, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014110478633849115, | |
| "grad_norm": 0.06685524433851242, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.7607, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014538068895480906, | |
| "grad_norm": 0.06618436425924301, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.7594, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014965659157112697, | |
| "grad_norm": 0.07597427815198898, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.7591, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015393249418744488, | |
| "grad_norm": 0.08120574802160263, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.7585, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01582083968037628, | |
| "grad_norm": 0.07383999228477478, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.7593, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01624842994200807, | |
| "grad_norm": 0.09645941108465195, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.7583, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01667602020363986, | |
| "grad_norm": 0.06341534852981567, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.7606, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.017103610465271653, | |
| "grad_norm": 0.06619752943515778, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.7593, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017531200726903444, | |
| "grad_norm": 0.07469940930604935, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.7589, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.017958790988535235, | |
| "grad_norm": 0.08176931738853455, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.7585, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.018386381250167026, | |
| "grad_norm": 0.07405959814786911, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.7593, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.018813971511798817, | |
| "grad_norm": 0.07433359324932098, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.7595, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01924156177343061, | |
| "grad_norm": 0.07951745390892029, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.7585, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019669152035062403, | |
| "grad_norm": 0.07772774249315262, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.7587, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.020096742296694194, | |
| "grad_norm": 0.08244699239730835, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.7572, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.020524332558325985, | |
| "grad_norm": 0.08685096353292465, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.7573, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.020951922819957777, | |
| "grad_norm": 0.08589866757392883, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.7589, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.021379513081589568, | |
| "grad_norm": 0.09261184185743332, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021379513081589568, | |
| "eval_loss": 11.758439064025879, | |
| "eval_runtime": 0.4257, | |
| "eval_samples_per_second": 117.455, | |
| "eval_steps_per_second": 30.538, | |
| "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": 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": 166344429404160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |