| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "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": 17.016149520874023, | |
| "learning_rate": 5e-05, | |
| "loss": 14.1219, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004275902616317913, | |
| "eval_loss": 0.6975424289703369, | |
| "eval_runtime": 4.7188, | |
| "eval_samples_per_second": 10.596, | |
| "eval_steps_per_second": 2.755, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008551805232635826, | |
| "grad_norm": 24.373233795166016, | |
| "learning_rate": 0.0001, | |
| "loss": 19.0381, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001282770784895374, | |
| "grad_norm": 18.29240608215332, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 18.5439, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017103610465271652, | |
| "grad_norm": 55.57586669921875, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 20.8671, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021379513081589566, | |
| "grad_norm": 40.574012756347656, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 20.9025, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002565541569790748, | |
| "grad_norm": 19.65155601501465, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 19.7865, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029931318314225393, | |
| "grad_norm": 17.976009368896484, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 20.1064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034207220930543305, | |
| "grad_norm": 17.989582061767578, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 20.7254, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003848312354686122, | |
| "grad_norm": 16.528972625732422, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 21.4587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004275902616317913, | |
| "grad_norm": 16.301668167114258, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 20.2535, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004703492877949704, | |
| "grad_norm": 16.937824249267578, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 20.0616, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005131083139581496, | |
| "grad_norm": 20.719322204589844, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 21.4276, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0055586734012132875, | |
| "grad_norm": 14.288154602050781, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 15.3058, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005986263662845079, | |
| "grad_norm": 22.180660247802734, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 16.3832, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00641385392447687, | |
| "grad_norm": 15.857145309448242, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 17.4158, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006841444186108661, | |
| "grad_norm": 13.35568618774414, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 17.8514, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007269034447740453, | |
| "grad_norm": 13.346510887145996, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 16.1613, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007696624709372244, | |
| "grad_norm": 13.989509582519531, | |
| "learning_rate": 7.75e-05, | |
| "loss": 18.1431, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008124214971004035, | |
| "grad_norm": 13.145577430725098, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 18.4521, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008551805232635826, | |
| "grad_norm": 13.035820960998535, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 18.0997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008979395494267618, | |
| "grad_norm": 13.4092378616333, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 18.836, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009406985755899409, | |
| "grad_norm": 14.309627532958984, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 19.516, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009834576017531202, | |
| "grad_norm": 13.839709281921387, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 19.228, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010262166279162993, | |
| "grad_norm": 15.516990661621094, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 19.8197, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010689756540794784, | |
| "grad_norm": 19.321626663208008, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 21.2602, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010689756540794784, | |
| "eval_loss": 0.5550210475921631, | |
| "eval_runtime": 4.7886, | |
| "eval_samples_per_second": 10.441, | |
| "eval_steps_per_second": 2.715, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011117346802426575, | |
| "grad_norm": 12.312941551208496, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.3935, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011544937064058366, | |
| "grad_norm": 14.37541675567627, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 15.2392, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011972527325690157, | |
| "grad_norm": 12.340313911437988, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 15.1875, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012400117587321948, | |
| "grad_norm": 11.889932632446289, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 15.776, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01282770784895374, | |
| "grad_norm": 13.100401878356934, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 16.6528, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01325529811058553, | |
| "grad_norm": 13.858903884887695, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 18.0721, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013682888372217322, | |
| "grad_norm": 13.05334758758545, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 17.9538, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014110478633849115, | |
| "grad_norm": 13.130781173706055, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 17.6755, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014538068895480906, | |
| "grad_norm": 12.964271545410156, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 18.443, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014965659157112697, | |
| "grad_norm": 13.65394401550293, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 18.8783, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015393249418744488, | |
| "grad_norm": 14.562626838684082, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 19.9088, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01582083968037628, | |
| "grad_norm": 15.111961364746094, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 20.2572, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01624842994200807, | |
| "grad_norm": 12.405916213989258, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 14.7318, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01667602020363986, | |
| "grad_norm": 11.5278959274292, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 13.9384, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.017103610465271653, | |
| "grad_norm": 12.947035789489746, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 15.3045, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017531200726903444, | |
| "grad_norm": 13.242534637451172, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 16.33, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.017958790988535235, | |
| "grad_norm": 12.534408569335938, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 16.4756, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.018386381250167026, | |
| "grad_norm": 12.54093074798584, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 17.4493, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.018813971511798817, | |
| "grad_norm": 12.03007698059082, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 16.682, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01924156177343061, | |
| "grad_norm": 13.081326484680176, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 17.7897, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019669152035062403, | |
| "grad_norm": 13.734363555908203, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 18.6434, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.020096742296694194, | |
| "grad_norm": 13.227235794067383, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 18.1203, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.020524332558325985, | |
| "grad_norm": 14.222868919372559, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 18.8453, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.020951922819957777, | |
| "grad_norm": 17.175867080688477, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 20.3476, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.021379513081589568, | |
| "grad_norm": 19.736366271972656, | |
| "learning_rate": 1e-05, | |
| "loss": 20.5668, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021379513081589568, | |
| "eval_loss": 0.5390623807907104, | |
| "eval_runtime": 4.8096, | |
| "eval_samples_per_second": 10.396, | |
| "eval_steps_per_second": 2.703, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.755268578358067e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |