dada22231's picture
Training in progress, step 50, checkpoint
89159ab verified
raw
history blame
10 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.025040299231575816,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005008059846315163,
"grad_norm": 14.94532585144043,
"learning_rate": 5e-05,
"loss": 55.3033,
"step": 1
},
{
"epoch": 0.0005008059846315163,
"eval_loss": 1.6915992498397827,
"eval_runtime": 3.963,
"eval_samples_per_second": 12.617,
"eval_steps_per_second": 3.28,
"step": 1
},
{
"epoch": 0.0010016119692630326,
"grad_norm": 21.021150588989258,
"learning_rate": 0.0001,
"loss": 59.4736,
"step": 2
},
{
"epoch": 0.001502417953894549,
"grad_norm": 15.826090812683105,
"learning_rate": 9.990365154573717e-05,
"loss": 48.3357,
"step": 3
},
{
"epoch": 0.002003223938526065,
"grad_norm": 14.021793365478516,
"learning_rate": 9.961501876182148e-05,
"loss": 47.4736,
"step": 4
},
{
"epoch": 0.0025040299231575817,
"grad_norm": 14.354966163635254,
"learning_rate": 9.913533761814537e-05,
"loss": 46.1515,
"step": 5
},
{
"epoch": 0.003004835907789098,
"grad_norm": 12.20103645324707,
"learning_rate": 9.846666218300807e-05,
"loss": 44.2306,
"step": 6
},
{
"epoch": 0.0035056418924206143,
"grad_norm": 11.178145408630371,
"learning_rate": 9.761185582727977e-05,
"loss": 43.0892,
"step": 7
},
{
"epoch": 0.00400644787705213,
"grad_norm": 10.050987243652344,
"learning_rate": 9.657457896300791e-05,
"loss": 39.7662,
"step": 8
},
{
"epoch": 0.004507253861683647,
"grad_norm": 9.848730087280273,
"learning_rate": 9.535927336897098e-05,
"loss": 43.9977,
"step": 9
},
{
"epoch": 0.005008059846315163,
"grad_norm": 11.008878707885742,
"learning_rate": 9.397114317029975e-05,
"loss": 41.5182,
"step": 10
},
{
"epoch": 0.0055088658309466795,
"grad_norm": 10.566274642944336,
"learning_rate": 9.241613255361455e-05,
"loss": 35.1738,
"step": 11
},
{
"epoch": 0.006009671815578196,
"grad_norm": 10.088213920593262,
"learning_rate": 9.070090031310558e-05,
"loss": 31.3863,
"step": 12
},
{
"epoch": 0.0065104778002097125,
"grad_norm": 19.065397262573242,
"learning_rate": 8.883279133655399e-05,
"loss": 44.4877,
"step": 13
},
{
"epoch": 0.0070112837848412286,
"grad_norm": 15.400626182556152,
"learning_rate": 8.681980515339464e-05,
"loss": 45.3939,
"step": 14
},
{
"epoch": 0.0075120897694727455,
"grad_norm": 13.578170776367188,
"learning_rate": 8.467056167950311e-05,
"loss": 38.4454,
"step": 15
},
{
"epoch": 0.00801289575410426,
"grad_norm": 10.751890182495117,
"learning_rate": 8.239426430539243e-05,
"loss": 34.8616,
"step": 16
},
{
"epoch": 0.008513701738735778,
"grad_norm": 9.421052932739258,
"learning_rate": 8.000066048588211e-05,
"loss": 36.6543,
"step": 17
},
{
"epoch": 0.009014507723367295,
"grad_norm": 9.424656867980957,
"learning_rate": 7.75e-05,
"loss": 36.1756,
"step": 18
},
{
"epoch": 0.00951531370799881,
"grad_norm": 9.777093887329102,
"learning_rate": 7.490299105985507e-05,
"loss": 36.6961,
"step": 19
},
{
"epoch": 0.010016119692630327,
"grad_norm": 8.841789245605469,
"learning_rate": 7.222075445642904e-05,
"loss": 35.7028,
"step": 20
},
{
"epoch": 0.010516925677261844,
"grad_norm": 7.8035712242126465,
"learning_rate": 6.946477593864228e-05,
"loss": 36.5471,
"step": 21
},
{
"epoch": 0.011017731661893359,
"grad_norm": 7.310739040374756,
"learning_rate": 6.664685702961344e-05,
"loss": 35.0386,
"step": 22
},
{
"epoch": 0.011518537646524876,
"grad_norm": 8.161108016967773,
"learning_rate": 6.377906449072578e-05,
"loss": 35.7743,
"step": 23
},
{
"epoch": 0.012019343631156393,
"grad_norm": 7.978611946105957,
"learning_rate": 6.087367864990233e-05,
"loss": 34.2856,
"step": 24
},
{
"epoch": 0.012520149615787908,
"grad_norm": 14.87539291381836,
"learning_rate": 5.794314081535644e-05,
"loss": 37.7461,
"step": 25
},
{
"epoch": 0.012520149615787908,
"eval_loss": 1.110192894935608,
"eval_runtime": 4.0093,
"eval_samples_per_second": 12.471,
"eval_steps_per_second": 3.242,
"step": 25
},
{
"epoch": 0.013020955600419425,
"grad_norm": 12.907711029052734,
"learning_rate": 5.500000000000001e-05,
"loss": 40.5466,
"step": 26
},
{
"epoch": 0.013521761585050942,
"grad_norm": 14.298810958862305,
"learning_rate": 5.205685918464356e-05,
"loss": 39.6971,
"step": 27
},
{
"epoch": 0.014022567569682457,
"grad_norm": 8.840272903442383,
"learning_rate": 4.912632135009769e-05,
"loss": 33.8011,
"step": 28
},
{
"epoch": 0.014523373554313974,
"grad_norm": 8.240339279174805,
"learning_rate": 4.6220935509274235e-05,
"loss": 34.7336,
"step": 29
},
{
"epoch": 0.015024179538945491,
"grad_norm": 7.267547607421875,
"learning_rate": 4.3353142970386564e-05,
"loss": 39.301,
"step": 30
},
{
"epoch": 0.015524985523577006,
"grad_norm": 6.603776931762695,
"learning_rate": 4.053522406135775e-05,
"loss": 34.2265,
"step": 31
},
{
"epoch": 0.01602579150820852,
"grad_norm": 8.114143371582031,
"learning_rate": 3.777924554357096e-05,
"loss": 35.1166,
"step": 32
},
{
"epoch": 0.01652659749284004,
"grad_norm": 9.130178451538086,
"learning_rate": 3.509700894014496e-05,
"loss": 34.9486,
"step": 33
},
{
"epoch": 0.017027403477471555,
"grad_norm": 10.9686861038208,
"learning_rate": 3.250000000000001e-05,
"loss": 37.1661,
"step": 34
},
{
"epoch": 0.01752820946210307,
"grad_norm": 11.460497856140137,
"learning_rate": 2.9999339514117912e-05,
"loss": 35.1148,
"step": 35
},
{
"epoch": 0.01802901544673459,
"grad_norm": 9.752028465270996,
"learning_rate": 2.760573569460757e-05,
"loss": 31.4821,
"step": 36
},
{
"epoch": 0.018529821431366104,
"grad_norm": 12.186714172363281,
"learning_rate": 2.53294383204969e-05,
"loss": 31.2477,
"step": 37
},
{
"epoch": 0.01903062741599762,
"grad_norm": 13.641959190368652,
"learning_rate": 2.3180194846605367e-05,
"loss": 43.8177,
"step": 38
},
{
"epoch": 0.01953143340062914,
"grad_norm": 18.16305160522461,
"learning_rate": 2.1167208663446025e-05,
"loss": 42.221,
"step": 39
},
{
"epoch": 0.020032239385260654,
"grad_norm": 8.292379379272461,
"learning_rate": 1.9299099686894423e-05,
"loss": 33.8687,
"step": 40
},
{
"epoch": 0.02053304536989217,
"grad_norm": 7.936122894287109,
"learning_rate": 1.758386744638546e-05,
"loss": 30.5119,
"step": 41
},
{
"epoch": 0.021033851354523687,
"grad_norm": 9.7647705078125,
"learning_rate": 1.602885682970026e-05,
"loss": 34.835,
"step": 42
},
{
"epoch": 0.021534657339155203,
"grad_norm": 11.5134859085083,
"learning_rate": 1.464072663102903e-05,
"loss": 33.8628,
"step": 43
},
{
"epoch": 0.022035463323786718,
"grad_norm": 11.015727043151855,
"learning_rate": 1.3425421036992098e-05,
"loss": 34.5979,
"step": 44
},
{
"epoch": 0.022536269308418237,
"grad_norm": 8.781559944152832,
"learning_rate": 1.2388144172720251e-05,
"loss": 35.5065,
"step": 45
},
{
"epoch": 0.023037075293049752,
"grad_norm": 7.820028781890869,
"learning_rate": 1.1533337816991932e-05,
"loss": 33.935,
"step": 46
},
{
"epoch": 0.023537881277681267,
"grad_norm": 6.9192352294921875,
"learning_rate": 1.0864662381854632e-05,
"loss": 32.8078,
"step": 47
},
{
"epoch": 0.024038687262312786,
"grad_norm": 7.588488578796387,
"learning_rate": 1.0384981238178534e-05,
"loss": 32.1488,
"step": 48
},
{
"epoch": 0.0245394932469443,
"grad_norm": 7.037163734436035,
"learning_rate": 1.0096348454262845e-05,
"loss": 29.7435,
"step": 49
},
{
"epoch": 0.025040299231575816,
"grad_norm": 12.27120304107666,
"learning_rate": 1e-05,
"loss": 32.5584,
"step": 50
},
{
"epoch": 0.025040299231575816,
"eval_loss": 1.0642402172088623,
"eval_runtime": 3.8404,
"eval_samples_per_second": 13.02,
"eval_steps_per_second": 3.385,
"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": 5.904224712120074e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}