dada22231's picture
Training in progress, step 50, checkpoint
16e5c7c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.44543429844098,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008908685968819599,
"grad_norm": 0.18692760169506073,
"learning_rate": 5e-05,
"loss": 1.741,
"step": 1
},
{
"epoch": 0.008908685968819599,
"eval_loss": 3.07926607131958,
"eval_runtime": 1.3149,
"eval_samples_per_second": 38.025,
"eval_steps_per_second": 9.886,
"step": 1
},
{
"epoch": 0.017817371937639197,
"grad_norm": 0.30333977937698364,
"learning_rate": 0.0001,
"loss": 1.9502,
"step": 2
},
{
"epoch": 0.026726057906458798,
"grad_norm": 0.3452962636947632,
"learning_rate": 9.990365154573717e-05,
"loss": 2.0,
"step": 3
},
{
"epoch": 0.035634743875278395,
"grad_norm": 0.5005683302879333,
"learning_rate": 9.961501876182148e-05,
"loss": 2.1854,
"step": 4
},
{
"epoch": 0.044543429844097995,
"grad_norm": 0.9022629261016846,
"learning_rate": 9.913533761814537e-05,
"loss": 2.1835,
"step": 5
},
{
"epoch": 0.053452115812917596,
"grad_norm": 0.8575097322463989,
"learning_rate": 9.846666218300807e-05,
"loss": 2.1896,
"step": 6
},
{
"epoch": 0.062360801781737196,
"grad_norm": 0.833286702632904,
"learning_rate": 9.761185582727977e-05,
"loss": 2.2395,
"step": 7
},
{
"epoch": 0.07126948775055679,
"grad_norm": 1.007340669631958,
"learning_rate": 9.657457896300791e-05,
"loss": 2.0513,
"step": 8
},
{
"epoch": 0.0801781737193764,
"grad_norm": 1.394514560699463,
"learning_rate": 9.535927336897098e-05,
"loss": 2.0675,
"step": 9
},
{
"epoch": 0.08908685968819599,
"grad_norm": 1.8569551706314087,
"learning_rate": 9.397114317029975e-05,
"loss": 2.0956,
"step": 10
},
{
"epoch": 0.09799554565701558,
"grad_norm": 3.6165878772735596,
"learning_rate": 9.241613255361455e-05,
"loss": 2.1212,
"step": 11
},
{
"epoch": 0.10690423162583519,
"grad_norm": 5.517111301422119,
"learning_rate": 9.070090031310558e-05,
"loss": 2.4758,
"step": 12
},
{
"epoch": 0.11581291759465479,
"grad_norm": 2.0073649883270264,
"learning_rate": 8.883279133655399e-05,
"loss": 1.8598,
"step": 13
},
{
"epoch": 0.12472160356347439,
"grad_norm": 2.560000419616699,
"learning_rate": 8.681980515339464e-05,
"loss": 1.7981,
"step": 14
},
{
"epoch": 0.133630289532294,
"grad_norm": 2.6340982913970947,
"learning_rate": 8.467056167950311e-05,
"loss": 1.9514,
"step": 15
},
{
"epoch": 0.14253897550111358,
"grad_norm": 2.3387725353240967,
"learning_rate": 8.239426430539243e-05,
"loss": 1.954,
"step": 16
},
{
"epoch": 0.1514476614699332,
"grad_norm": 0.6694347858428955,
"learning_rate": 8.000066048588211e-05,
"loss": 2.0982,
"step": 17
},
{
"epoch": 0.1603563474387528,
"grad_norm": 0.8026701211929321,
"learning_rate": 7.75e-05,
"loss": 1.9768,
"step": 18
},
{
"epoch": 0.16926503340757237,
"grad_norm": 1.3480937480926514,
"learning_rate": 7.490299105985507e-05,
"loss": 2.0367,
"step": 19
},
{
"epoch": 0.17817371937639198,
"grad_norm": 1.5750824213027954,
"learning_rate": 7.222075445642904e-05,
"loss": 1.9608,
"step": 20
},
{
"epoch": 0.1870824053452116,
"grad_norm": 1.8090828657150269,
"learning_rate": 6.946477593864228e-05,
"loss": 1.8402,
"step": 21
},
{
"epoch": 0.19599109131403117,
"grad_norm": 1.8316267728805542,
"learning_rate": 6.664685702961344e-05,
"loss": 1.7045,
"step": 22
},
{
"epoch": 0.20489977728285078,
"grad_norm": 3.0264618396759033,
"learning_rate": 6.377906449072578e-05,
"loss": 1.8959,
"step": 23
},
{
"epoch": 0.21380846325167038,
"grad_norm": 2.6325416564941406,
"learning_rate": 6.087367864990233e-05,
"loss": 1.4814,
"step": 24
},
{
"epoch": 0.22271714922049,
"grad_norm": 11.370490074157715,
"learning_rate": 5.794314081535644e-05,
"loss": 2.6302,
"step": 25
},
{
"epoch": 0.22271714922049,
"eval_loss": 1.8585379123687744,
"eval_runtime": 1.3456,
"eval_samples_per_second": 37.159,
"eval_steps_per_second": 9.661,
"step": 25
},
{
"epoch": 0.23162583518930957,
"grad_norm": 0.4977087080478668,
"learning_rate": 5.500000000000001e-05,
"loss": 1.6454,
"step": 26
},
{
"epoch": 0.24053452115812918,
"grad_norm": 0.9038933515548706,
"learning_rate": 5.205685918464356e-05,
"loss": 1.6915,
"step": 27
},
{
"epoch": 0.24944320712694878,
"grad_norm": 0.9914548993110657,
"learning_rate": 4.912632135009769e-05,
"loss": 2.0145,
"step": 28
},
{
"epoch": 0.2583518930957684,
"grad_norm": 1.172132134437561,
"learning_rate": 4.6220935509274235e-05,
"loss": 1.8721,
"step": 29
},
{
"epoch": 0.267260579064588,
"grad_norm": 0.8836953639984131,
"learning_rate": 4.3353142970386564e-05,
"loss": 2.0052,
"step": 30
},
{
"epoch": 0.27616926503340755,
"grad_norm": 0.703058660030365,
"learning_rate": 4.053522406135775e-05,
"loss": 2.0188,
"step": 31
},
{
"epoch": 0.28507795100222716,
"grad_norm": 0.5177896618843079,
"learning_rate": 3.777924554357096e-05,
"loss": 1.974,
"step": 32
},
{
"epoch": 0.29398663697104677,
"grad_norm": 0.5310644507408142,
"learning_rate": 3.509700894014496e-05,
"loss": 1.7945,
"step": 33
},
{
"epoch": 0.3028953229398664,
"grad_norm": 0.8083738088607788,
"learning_rate": 3.250000000000001e-05,
"loss": 1.835,
"step": 34
},
{
"epoch": 0.311804008908686,
"grad_norm": 1.105912208557129,
"learning_rate": 2.9999339514117912e-05,
"loss": 1.7656,
"step": 35
},
{
"epoch": 0.3207126948775056,
"grad_norm": 1.593446135520935,
"learning_rate": 2.760573569460757e-05,
"loss": 1.6878,
"step": 36
},
{
"epoch": 0.32962138084632514,
"grad_norm": 3.458589792251587,
"learning_rate": 2.53294383204969e-05,
"loss": 1.6475,
"step": 37
},
{
"epoch": 0.33853006681514475,
"grad_norm": 0.33230629563331604,
"learning_rate": 2.3180194846605367e-05,
"loss": 1.6323,
"step": 38
},
{
"epoch": 0.34743875278396436,
"grad_norm": 0.2732144296169281,
"learning_rate": 2.1167208663446025e-05,
"loss": 1.515,
"step": 39
},
{
"epoch": 0.35634743875278396,
"grad_norm": 0.32098567485809326,
"learning_rate": 1.9299099686894423e-05,
"loss": 1.7213,
"step": 40
},
{
"epoch": 0.36525612472160357,
"grad_norm": 0.31850364804267883,
"learning_rate": 1.758386744638546e-05,
"loss": 1.8198,
"step": 41
},
{
"epoch": 0.3741648106904232,
"grad_norm": 0.27133655548095703,
"learning_rate": 1.602885682970026e-05,
"loss": 1.946,
"step": 42
},
{
"epoch": 0.3830734966592428,
"grad_norm": 0.29527726769447327,
"learning_rate": 1.464072663102903e-05,
"loss": 1.8802,
"step": 43
},
{
"epoch": 0.39198218262806234,
"grad_norm": 0.326080322265625,
"learning_rate": 1.3425421036992098e-05,
"loss": 1.9288,
"step": 44
},
{
"epoch": 0.40089086859688194,
"grad_norm": 0.32311415672302246,
"learning_rate": 1.2388144172720251e-05,
"loss": 1.8807,
"step": 45
},
{
"epoch": 0.40979955456570155,
"grad_norm": 0.37641483545303345,
"learning_rate": 1.1533337816991932e-05,
"loss": 1.8189,
"step": 46
},
{
"epoch": 0.41870824053452116,
"grad_norm": 0.5488148927688599,
"learning_rate": 1.0864662381854632e-05,
"loss": 1.7643,
"step": 47
},
{
"epoch": 0.42761692650334077,
"grad_norm": 0.8097848296165466,
"learning_rate": 1.0384981238178534e-05,
"loss": 1.8119,
"step": 48
},
{
"epoch": 0.4365256124721604,
"grad_norm": 1.8706375360488892,
"learning_rate": 1.0096348454262845e-05,
"loss": 1.607,
"step": 49
},
{
"epoch": 0.44543429844098,
"grad_norm": 4.828557968139648,
"learning_rate": 1e-05,
"loss": 2.0986,
"step": 50
},
{
"epoch": 0.44543429844098,
"eval_loss": 1.7255163192749023,
"eval_runtime": 1.3424,
"eval_samples_per_second": 37.246,
"eval_steps_per_second": 9.684,
"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": 1.0620196435787776e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}