dada22231's picture
Training in progress, step 50, checkpoint
f7c8e14 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6717044500419815,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01343408900083963,
"grad_norm": 0.8214039206504822,
"learning_rate": 5e-05,
"loss": 1.1132,
"step": 1
},
{
"epoch": 0.01343408900083963,
"eval_loss": 1.183107852935791,
"eval_runtime": 0.7389,
"eval_samples_per_second": 67.666,
"eval_steps_per_second": 17.593,
"step": 1
},
{
"epoch": 0.02686817800167926,
"grad_norm": 0.985977828502655,
"learning_rate": 0.0001,
"loss": 1.1582,
"step": 2
},
{
"epoch": 0.04030226700251889,
"grad_norm": 0.8014296889305115,
"learning_rate": 9.990365154573717e-05,
"loss": 1.1182,
"step": 3
},
{
"epoch": 0.05373635600335852,
"grad_norm": 0.7511947751045227,
"learning_rate": 9.961501876182148e-05,
"loss": 1.0511,
"step": 4
},
{
"epoch": 0.06717044500419815,
"grad_norm": 0.7431446313858032,
"learning_rate": 9.913533761814537e-05,
"loss": 1.0338,
"step": 5
},
{
"epoch": 0.08060453400503778,
"grad_norm": 0.7233390212059021,
"learning_rate": 9.846666218300807e-05,
"loss": 1.0094,
"step": 6
},
{
"epoch": 0.09403862300587741,
"grad_norm": 0.6397824883460999,
"learning_rate": 9.761185582727977e-05,
"loss": 0.994,
"step": 7
},
{
"epoch": 0.10747271200671704,
"grad_norm": 0.502813458442688,
"learning_rate": 9.657457896300791e-05,
"loss": 0.9737,
"step": 8
},
{
"epoch": 0.12090680100755667,
"grad_norm": 0.4122387766838074,
"learning_rate": 9.535927336897098e-05,
"loss": 0.9339,
"step": 9
},
{
"epoch": 0.1343408900083963,
"grad_norm": 0.3604699671268463,
"learning_rate": 9.397114317029975e-05,
"loss": 0.9606,
"step": 10
},
{
"epoch": 0.14777497900923595,
"grad_norm": 0.3673606514930725,
"learning_rate": 9.241613255361455e-05,
"loss": 0.92,
"step": 11
},
{
"epoch": 0.16120906801007556,
"grad_norm": 0.3747656047344208,
"learning_rate": 9.070090031310558e-05,
"loss": 0.9341,
"step": 12
},
{
"epoch": 0.1746431570109152,
"grad_norm": 0.32330557703971863,
"learning_rate": 8.883279133655399e-05,
"loss": 0.9357,
"step": 13
},
{
"epoch": 0.18807724601175482,
"grad_norm": 0.3396777808666229,
"learning_rate": 8.681980515339464e-05,
"loss": 0.9556,
"step": 14
},
{
"epoch": 0.20151133501259447,
"grad_norm": 0.2774878144264221,
"learning_rate": 8.467056167950311e-05,
"loss": 0.9447,
"step": 15
},
{
"epoch": 0.21494542401343408,
"grad_norm": 0.24314501881599426,
"learning_rate": 8.239426430539243e-05,
"loss": 0.9251,
"step": 16
},
{
"epoch": 0.22837951301427373,
"grad_norm": 0.26309147477149963,
"learning_rate": 8.000066048588211e-05,
"loss": 0.954,
"step": 17
},
{
"epoch": 0.24181360201511334,
"grad_norm": 0.26773422956466675,
"learning_rate": 7.75e-05,
"loss": 0.9512,
"step": 18
},
{
"epoch": 0.25524769101595296,
"grad_norm": 0.2681795358657837,
"learning_rate": 7.490299105985507e-05,
"loss": 0.9019,
"step": 19
},
{
"epoch": 0.2686817800167926,
"grad_norm": 0.27614450454711914,
"learning_rate": 7.222075445642904e-05,
"loss": 0.9271,
"step": 20
},
{
"epoch": 0.28211586901763225,
"grad_norm": 0.2500954270362854,
"learning_rate": 6.946477593864228e-05,
"loss": 0.9204,
"step": 21
},
{
"epoch": 0.2955499580184719,
"grad_norm": 0.2638442814350128,
"learning_rate": 6.664685702961344e-05,
"loss": 0.9472,
"step": 22
},
{
"epoch": 0.3089840470193115,
"grad_norm": 0.23764583468437195,
"learning_rate": 6.377906449072578e-05,
"loss": 0.9245,
"step": 23
},
{
"epoch": 0.3224181360201511,
"grad_norm": 0.24344375729560852,
"learning_rate": 6.087367864990233e-05,
"loss": 0.9207,
"step": 24
},
{
"epoch": 0.33585222502099077,
"grad_norm": 0.27440446615219116,
"learning_rate": 5.794314081535644e-05,
"loss": 0.9518,
"step": 25
},
{
"epoch": 0.33585222502099077,
"eval_loss": 0.9221521019935608,
"eval_runtime": 0.7412,
"eval_samples_per_second": 67.461,
"eval_steps_per_second": 17.54,
"step": 25
},
{
"epoch": 0.3492863140218304,
"grad_norm": 0.27871379256248474,
"learning_rate": 5.500000000000001e-05,
"loss": 0.9502,
"step": 26
},
{
"epoch": 0.36272040302267,
"grad_norm": 0.2754870057106018,
"learning_rate": 5.205685918464356e-05,
"loss": 0.9393,
"step": 27
},
{
"epoch": 0.37615449202350965,
"grad_norm": 0.24578134715557098,
"learning_rate": 4.912632135009769e-05,
"loss": 0.9144,
"step": 28
},
{
"epoch": 0.3895885810243493,
"grad_norm": 0.24544677138328552,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.9256,
"step": 29
},
{
"epoch": 0.40302267002518893,
"grad_norm": 0.2284000962972641,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.8907,
"step": 30
},
{
"epoch": 0.4164567590260285,
"grad_norm": 0.22578762471675873,
"learning_rate": 4.053522406135775e-05,
"loss": 0.9039,
"step": 31
},
{
"epoch": 0.42989084802686817,
"grad_norm": 0.21225938200950623,
"learning_rate": 3.777924554357096e-05,
"loss": 0.9315,
"step": 32
},
{
"epoch": 0.4433249370277078,
"grad_norm": 0.22618161141872406,
"learning_rate": 3.509700894014496e-05,
"loss": 0.8937,
"step": 33
},
{
"epoch": 0.45675902602854745,
"grad_norm": 0.24397031962871552,
"learning_rate": 3.250000000000001e-05,
"loss": 0.8986,
"step": 34
},
{
"epoch": 0.47019311502938704,
"grad_norm": 0.2503018081188202,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.9226,
"step": 35
},
{
"epoch": 0.4836272040302267,
"grad_norm": 0.23289993405342102,
"learning_rate": 2.760573569460757e-05,
"loss": 0.8954,
"step": 36
},
{
"epoch": 0.49706129303106633,
"grad_norm": 0.2558768689632416,
"learning_rate": 2.53294383204969e-05,
"loss": 0.8833,
"step": 37
},
{
"epoch": 0.5104953820319059,
"grad_norm": 0.22449778020381927,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.9091,
"step": 38
},
{
"epoch": 0.5239294710327456,
"grad_norm": 0.20541346073150635,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.9165,
"step": 39
},
{
"epoch": 0.5373635600335852,
"grad_norm": 0.20522888004779816,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.9178,
"step": 40
},
{
"epoch": 0.5507976490344249,
"grad_norm": 0.20278018712997437,
"learning_rate": 1.758386744638546e-05,
"loss": 0.9317,
"step": 41
},
{
"epoch": 0.5642317380352645,
"grad_norm": 0.20812608301639557,
"learning_rate": 1.602885682970026e-05,
"loss": 0.8763,
"step": 42
},
{
"epoch": 0.5776658270361041,
"grad_norm": 0.20340973138809204,
"learning_rate": 1.464072663102903e-05,
"loss": 0.8815,
"step": 43
},
{
"epoch": 0.5910999160369438,
"grad_norm": 0.20302090048789978,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.9081,
"step": 44
},
{
"epoch": 0.6045340050377834,
"grad_norm": 0.20221669971942902,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.8941,
"step": 45
},
{
"epoch": 0.617968094038623,
"grad_norm": 0.21326152980327606,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.8953,
"step": 46
},
{
"epoch": 0.6314021830394626,
"grad_norm": 0.20957252383232117,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.8796,
"step": 47
},
{
"epoch": 0.6448362720403022,
"grad_norm": 0.21854941546916962,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.9229,
"step": 48
},
{
"epoch": 0.6582703610411419,
"grad_norm": 0.2276400476694107,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.8743,
"step": 49
},
{
"epoch": 0.6717044500419815,
"grad_norm": 0.27538827061653137,
"learning_rate": 1e-05,
"loss": 0.938,
"step": 50
},
{
"epoch": 0.6717044500419815,
"eval_loss": 0.9089437127113342,
"eval_runtime": 0.7452,
"eval_samples_per_second": 67.098,
"eval_steps_per_second": 17.445,
"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": 2.95300912644096e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}