dada22231's picture
Training in progress, step 50, checkpoint
e9522aa verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8681497558328811,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017362995116657624,
"grad_norm": 0.7182026505470276,
"learning_rate": 5e-05,
"loss": 1.0881,
"step": 1
},
{
"epoch": 0.017362995116657624,
"eval_loss": 1.3584372997283936,
"eval_runtime": 1.8757,
"eval_samples_per_second": 13.328,
"eval_steps_per_second": 3.732,
"step": 1
},
{
"epoch": 0.03472599023331525,
"grad_norm": 0.7809290289878845,
"learning_rate": 0.0001,
"loss": 1.1949,
"step": 2
},
{
"epoch": 0.05208898534997287,
"grad_norm": 0.7038278579711914,
"learning_rate": 9.990365154573717e-05,
"loss": 1.2373,
"step": 3
},
{
"epoch": 0.0694519804666305,
"grad_norm": 0.5672025680541992,
"learning_rate": 9.961501876182148e-05,
"loss": 1.2077,
"step": 4
},
{
"epoch": 0.08681497558328811,
"grad_norm": 1.2600429058074951,
"learning_rate": 9.913533761814537e-05,
"loss": 1.2304,
"step": 5
},
{
"epoch": 0.10417797069994574,
"grad_norm": 0.874370813369751,
"learning_rate": 9.846666218300807e-05,
"loss": 1.2001,
"step": 6
},
{
"epoch": 0.12154096581660337,
"grad_norm": 0.3352430462837219,
"learning_rate": 9.761185582727977e-05,
"loss": 1.1001,
"step": 7
},
{
"epoch": 0.138903960933261,
"grad_norm": 0.90861976146698,
"learning_rate": 9.657457896300791e-05,
"loss": 1.1131,
"step": 8
},
{
"epoch": 0.1562669560499186,
"grad_norm": 0.3815368413925171,
"learning_rate": 9.535927336897098e-05,
"loss": 1.0594,
"step": 9
},
{
"epoch": 0.17362995116657623,
"grad_norm": 0.4673871397972107,
"learning_rate": 9.397114317029975e-05,
"loss": 1.1235,
"step": 10
},
{
"epoch": 0.19099294628323385,
"grad_norm": 0.3776948153972626,
"learning_rate": 9.241613255361455e-05,
"loss": 1.1361,
"step": 11
},
{
"epoch": 0.20835594139989147,
"grad_norm": 0.3672788143157959,
"learning_rate": 9.070090031310558e-05,
"loss": 1.0379,
"step": 12
},
{
"epoch": 0.22571893651654912,
"grad_norm": 0.5735769867897034,
"learning_rate": 8.883279133655399e-05,
"loss": 1.0946,
"step": 13
},
{
"epoch": 0.24308193163320674,
"grad_norm": 0.5544564723968506,
"learning_rate": 8.681980515339464e-05,
"loss": 1.0344,
"step": 14
},
{
"epoch": 0.26044492674986436,
"grad_norm": 0.4513843357563019,
"learning_rate": 8.467056167950311e-05,
"loss": 1.0465,
"step": 15
},
{
"epoch": 0.277807921866522,
"grad_norm": 0.47421953082084656,
"learning_rate": 8.239426430539243e-05,
"loss": 1.027,
"step": 16
},
{
"epoch": 0.2951709169831796,
"grad_norm": 0.3568557798862457,
"learning_rate": 8.000066048588211e-05,
"loss": 1.062,
"step": 17
},
{
"epoch": 0.3125339120998372,
"grad_norm": 0.46328404545783997,
"learning_rate": 7.75e-05,
"loss": 1.0561,
"step": 18
},
{
"epoch": 0.32989690721649484,
"grad_norm": 0.45868080854415894,
"learning_rate": 7.490299105985507e-05,
"loss": 1.0949,
"step": 19
},
{
"epoch": 0.34725990233315246,
"grad_norm": 0.4798765480518341,
"learning_rate": 7.222075445642904e-05,
"loss": 1.0376,
"step": 20
},
{
"epoch": 0.3646228974498101,
"grad_norm": 0.3499842584133148,
"learning_rate": 6.946477593864228e-05,
"loss": 1.041,
"step": 21
},
{
"epoch": 0.3819858925664677,
"grad_norm": 0.3488876223564148,
"learning_rate": 6.664685702961344e-05,
"loss": 1.0498,
"step": 22
},
{
"epoch": 0.3993488876831253,
"grad_norm": 0.3430456817150116,
"learning_rate": 6.377906449072578e-05,
"loss": 1.0897,
"step": 23
},
{
"epoch": 0.41671188279978294,
"grad_norm": 0.43366703391075134,
"learning_rate": 6.087367864990233e-05,
"loss": 1.07,
"step": 24
},
{
"epoch": 0.43407487791644056,
"grad_norm": 0.4223703444004059,
"learning_rate": 5.794314081535644e-05,
"loss": 1.1504,
"step": 25
},
{
"epoch": 0.43407487791644056,
"eval_loss": 0.9815278053283691,
"eval_runtime": 3.9827,
"eval_samples_per_second": 6.277,
"eval_steps_per_second": 1.758,
"step": 25
},
{
"epoch": 0.45143787303309824,
"grad_norm": 0.3909236192703247,
"learning_rate": 5.500000000000001e-05,
"loss": 0.9775,
"step": 26
},
{
"epoch": 0.46880086814975586,
"grad_norm": 0.4122433066368103,
"learning_rate": 5.205685918464356e-05,
"loss": 0.9869,
"step": 27
},
{
"epoch": 0.4861638632664135,
"grad_norm": 0.4743092954158783,
"learning_rate": 4.912632135009769e-05,
"loss": 1.0769,
"step": 28
},
{
"epoch": 0.5035268583830711,
"grad_norm": 0.5240751504898071,
"learning_rate": 4.6220935509274235e-05,
"loss": 1.0527,
"step": 29
},
{
"epoch": 0.5208898534997287,
"grad_norm": 0.5160244107246399,
"learning_rate": 4.3353142970386564e-05,
"loss": 1.0738,
"step": 30
},
{
"epoch": 0.5382528486163863,
"grad_norm": 0.4228280782699585,
"learning_rate": 4.053522406135775e-05,
"loss": 1.0908,
"step": 31
},
{
"epoch": 0.555615843733044,
"grad_norm": 0.3233334422111511,
"learning_rate": 3.777924554357096e-05,
"loss": 1.0445,
"step": 32
},
{
"epoch": 0.5729788388497016,
"grad_norm": 0.2721971571445465,
"learning_rate": 3.509700894014496e-05,
"loss": 1.0104,
"step": 33
},
{
"epoch": 0.5903418339663592,
"grad_norm": 0.27864304184913635,
"learning_rate": 3.250000000000001e-05,
"loss": 1.0216,
"step": 34
},
{
"epoch": 0.6077048290830168,
"grad_norm": 0.3138728141784668,
"learning_rate": 2.9999339514117912e-05,
"loss": 1.0543,
"step": 35
},
{
"epoch": 0.6250678241996744,
"grad_norm": 0.43779677152633667,
"learning_rate": 2.760573569460757e-05,
"loss": 1.0291,
"step": 36
},
{
"epoch": 0.6424308193163321,
"grad_norm": 0.5752337574958801,
"learning_rate": 2.53294383204969e-05,
"loss": 1.0821,
"step": 37
},
{
"epoch": 0.6597938144329897,
"grad_norm": 0.20029059052467346,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.9379,
"step": 38
},
{
"epoch": 0.6771568095496473,
"grad_norm": 0.1933901011943817,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.9276,
"step": 39
},
{
"epoch": 0.6945198046663049,
"grad_norm": 0.2140360325574875,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.986,
"step": 40
},
{
"epoch": 0.7118827997829625,
"grad_norm": 0.24084554612636566,
"learning_rate": 1.758386744638546e-05,
"loss": 1.0175,
"step": 41
},
{
"epoch": 0.7292457948996202,
"grad_norm": 0.2267829179763794,
"learning_rate": 1.602885682970026e-05,
"loss": 1.0397,
"step": 42
},
{
"epoch": 0.7466087900162778,
"grad_norm": 0.2309180051088333,
"learning_rate": 1.464072663102903e-05,
"loss": 1.0084,
"step": 43
},
{
"epoch": 0.7639717851329354,
"grad_norm": 0.2305024117231369,
"learning_rate": 1.3425421036992098e-05,
"loss": 1.02,
"step": 44
},
{
"epoch": 0.781334780249593,
"grad_norm": 0.24496528506278992,
"learning_rate": 1.2388144172720251e-05,
"loss": 1.0425,
"step": 45
},
{
"epoch": 0.7986977753662506,
"grad_norm": 0.25039851665496826,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.9937,
"step": 46
},
{
"epoch": 0.8160607704829083,
"grad_norm": 0.29076555371284485,
"learning_rate": 1.0864662381854632e-05,
"loss": 1.0502,
"step": 47
},
{
"epoch": 0.8334237655995659,
"grad_norm": 0.31782031059265137,
"learning_rate": 1.0384981238178534e-05,
"loss": 1.0334,
"step": 48
},
{
"epoch": 0.8507867607162235,
"grad_norm": 0.3960300385951996,
"learning_rate": 1.0096348454262845e-05,
"loss": 1.0323,
"step": 49
},
{
"epoch": 0.8681497558328811,
"grad_norm": 0.536109447479248,
"learning_rate": 1e-05,
"loss": 1.1306,
"step": 50
},
{
"epoch": 0.8681497558328811,
"eval_loss": 0.9419312477111816,
"eval_runtime": 3.981,
"eval_samples_per_second": 6.28,
"eval_steps_per_second": 1.758,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.968083617316864e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}