| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2057272042200453, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024114544084400905, | |
| "grad_norm": 12.853450775146484, | |
| "learning_rate": 5e-05, | |
| "loss": 18.202, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024114544084400905, | |
| "eval_loss": 17.88939666748047, | |
| "eval_runtime": 1.1457, | |
| "eval_samples_per_second": 43.643, | |
| "eval_steps_per_second": 11.347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04822908816880181, | |
| "grad_norm": 12.898941993713379, | |
| "learning_rate": 0.0001, | |
| "loss": 18.0174, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07234363225320271, | |
| "grad_norm": 13.988131523132324, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 17.5915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09645817633760362, | |
| "grad_norm": 21.47568130493164, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 15.9516, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12057272042200452, | |
| "grad_norm": 31.15035629272461, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 14.0236, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14468726450640543, | |
| "grad_norm": 32.609195709228516, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 12.3079, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16880180859080632, | |
| "grad_norm": 33.13249588012695, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.6888, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19291635267520724, | |
| "grad_norm": 33.3653450012207, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 9.2295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21703089675960813, | |
| "grad_norm": 31.56165313720703, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 8.028, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.24114544084400905, | |
| "grad_norm": 26.991592407226562, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26525998492840996, | |
| "grad_norm": 31.015859603881836, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.9948, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.28937452901281085, | |
| "grad_norm": 42.92523193359375, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.8584, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.31348907309721175, | |
| "grad_norm": 54.43761444091797, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.4654, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.33760361718161264, | |
| "grad_norm": 37.214935302734375, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.132, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3617181612660136, | |
| "grad_norm": 20.878231048583984, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.3045, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3858327053504145, | |
| "grad_norm": 6.039570331573486, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.9199, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.40994724943481536, | |
| "grad_norm": 2.416555166244507, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.7876, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.43406179351921625, | |
| "grad_norm": 1.814249873161316, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.7597, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4581763376036172, | |
| "grad_norm": 2.3626012802124023, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7374, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4822908816880181, | |
| "grad_norm": 1.6917897462844849, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7166, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.506405425772419, | |
| "grad_norm": 0.8339031338691711, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.6961, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5305199698568199, | |
| "grad_norm": 1.4751001596450806, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.7014, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5546345139412208, | |
| "grad_norm": 2.256863832473755, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.7286, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5787490580256217, | |
| "grad_norm": 2.8666281700134277, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.7385, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6028636021100227, | |
| "grad_norm": 1.928024411201477, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.7182, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6028636021100227, | |
| "eval_loss": 0.7318603992462158, | |
| "eval_runtime": 1.1476, | |
| "eval_samples_per_second": 43.57, | |
| "eval_steps_per_second": 11.328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6269781461944235, | |
| "grad_norm": 1.8943963050842285, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7098, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6510926902788244, | |
| "grad_norm": 1.3358711004257202, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6979, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6752072343632253, | |
| "grad_norm": 1.7418076992034912, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.718, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6993217784476262, | |
| "grad_norm": 2.2980732917785645, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7217, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7234363225320272, | |
| "grad_norm": 2.3880324363708496, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.7251, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.747550866616428, | |
| "grad_norm": 2.4463062286376953, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7254, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.771665410700829, | |
| "grad_norm": 1.9282697439193726, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.7128, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7957799547852299, | |
| "grad_norm": 1.4290863275527954, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.6968, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8198944988696307, | |
| "grad_norm": 1.8006930351257324, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.7076, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8440090429540317, | |
| "grad_norm": 1.0373167991638184, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.7026, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8681235870384325, | |
| "grad_norm": 0.7661415338516235, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.6926, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8922381311228335, | |
| "grad_norm": 1.2040423154830933, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.701, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9163526752072344, | |
| "grad_norm": 0.8971741199493408, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.7018, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9404672192916352, | |
| "grad_norm": 0.7175334692001343, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.7001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9645817633760362, | |
| "grad_norm": 0.8451390862464905, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.6945, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9886963074604371, | |
| "grad_norm": 1.954053282737732, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.7059, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.012810851544838, | |
| "grad_norm": 2.4371275901794434, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.076, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0369253956292388, | |
| "grad_norm": 1.6779913902282715, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.6984, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0610399397136399, | |
| "grad_norm": 1.369674563407898, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.6834, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0851544837980407, | |
| "grad_norm": 1.0458629131317139, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6891, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1092690278824415, | |
| "grad_norm": 0.7835463285446167, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.6877, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1333835719668426, | |
| "grad_norm": 1.0629692077636719, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.6778, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1574981160512434, | |
| "grad_norm": 0.4367343485355377, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.6783, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1816126601356443, | |
| "grad_norm": 0.9655264616012573, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.676, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.2057272042200453, | |
| "grad_norm": 0.7904195785522461, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6994, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2057272042200453, | |
| "eval_loss": 0.7077999711036682, | |
| "eval_runtime": 1.1629, | |
| "eval_samples_per_second": 42.995, | |
| "eval_steps_per_second": 11.179, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |