364 lines
8.6 KiB
JSON
364 lines
8.6 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.6493055555555556,
|
|
"eval_steps": 500,
|
|
"global_step": 950,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.034722222222222224,
|
|
"grad_norm": 2.548311471939087,
|
|
"learning_rate": 1.6379310344827587e-06,
|
|
"loss": 2.4451,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.06944444444444445,
|
|
"grad_norm": 1.93834388256073,
|
|
"learning_rate": 3.362068965517242e-06,
|
|
"loss": 2.269,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.10416666666666667,
|
|
"grad_norm": 1.7273279428482056,
|
|
"learning_rate": 5.086206896551724e-06,
|
|
"loss": 2.1237,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.1388888888888889,
|
|
"grad_norm": 1.6319563388824463,
|
|
"learning_rate": 6.810344827586207e-06,
|
|
"loss": 1.969,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.1736111111111111,
|
|
"grad_norm": 2.0262465476989746,
|
|
"learning_rate": 8.53448275862069e-06,
|
|
"loss": 1.8517,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.20833333333333334,
|
|
"grad_norm": 2.1673457622528076,
|
|
"learning_rate": 9.999793100349294e-06,
|
|
"loss": 1.851,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.24305555555555555,
|
|
"grad_norm": 2.474327802658081,
|
|
"learning_rate": 9.987843743451796e-06,
|
|
"loss": 1.7448,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 2.0316762924194336,
|
|
"learning_rate": 9.957553516178782e-06,
|
|
"loss": 1.6721,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.3125,
|
|
"grad_norm": 2.3124542236328125,
|
|
"learning_rate": 9.909033799150947e-06,
|
|
"loss": 1.7265,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.3472222222222222,
|
|
"grad_norm": 2.2682251930236816,
|
|
"learning_rate": 9.842463004902127e-06,
|
|
"loss": 1.6325,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.3819444444444444,
|
|
"grad_norm": 2.4642767906188965,
|
|
"learning_rate": 9.758085921836076e-06,
|
|
"loss": 1.6193,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.4166666666666667,
|
|
"grad_norm": 2.4372549057006836,
|
|
"learning_rate": 9.656212814111567e-06,
|
|
"loss": 1.6297,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.4513888888888889,
|
|
"grad_norm": 2.7898528575897217,
|
|
"learning_rate": 9.53721828076571e-06,
|
|
"loss": 1.598,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.4861111111111111,
|
|
"grad_norm": 2.742067813873291,
|
|
"learning_rate": 9.401539878270545e-06,
|
|
"loss": 1.596,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.5208333333333334,
|
|
"grad_norm": 2.9180655479431152,
|
|
"learning_rate": 9.249676511588e-06,
|
|
"loss": 1.5923,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.5555555555555556,
|
|
"grad_norm": 2.760483503341675,
|
|
"learning_rate": 9.082186599639429e-06,
|
|
"loss": 1.5733,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 0.5902777777777778,
|
|
"grad_norm": 2.5661356449127197,
|
|
"learning_rate": 8.899686021935554e-06,
|
|
"loss": 1.5574,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 0.625,
|
|
"grad_norm": 2.650604248046875,
|
|
"learning_rate": 8.702845853917242e-06,
|
|
"loss": 1.5331,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 0.6597222222222222,
|
|
"grad_norm": 2.5134191513061523,
|
|
"learning_rate": 8.492389899334572e-06,
|
|
"loss": 1.5116,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 0.6944444444444444,
|
|
"grad_norm": 2.971090316772461,
|
|
"learning_rate": 8.269092028737885e-06,
|
|
"loss": 1.4993,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.7291666666666666,
|
|
"grad_norm": 3.0398788452148438,
|
|
"learning_rate": 8.033773333867498e-06,
|
|
"loss": 1.4751,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 0.7638888888888888,
|
|
"grad_norm": 2.7814712524414062,
|
|
"learning_rate": 7.78729910840572e-06,
|
|
"loss": 1.4688,
|
|
"step": 440
|
|
},
|
|
{
|
|
"epoch": 0.7986111111111112,
|
|
"grad_norm": 2.9422523975372314,
|
|
"learning_rate": 7.530575666193283e-06,
|
|
"loss": 1.4645,
|
|
"step": 460
|
|
},
|
|
{
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 3.5797832012176514,
|
|
"learning_rate": 7.26454700860997e-06,
|
|
"loss": 1.4473,
|
|
"step": 480
|
|
},
|
|
{
|
|
"epoch": 0.8680555555555556,
|
|
"grad_norm": 3.557054281234741,
|
|
"learning_rate": 6.990191353373876e-06,
|
|
"loss": 1.4428,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.9027777777777778,
|
|
"grad_norm": 3.7312850952148438,
|
|
"learning_rate": 6.708517537523264e-06,
|
|
"loss": 1.4014,
|
|
"step": 520
|
|
},
|
|
{
|
|
"epoch": 0.9375,
|
|
"grad_norm": 3.2819321155548096,
|
|
"learning_rate": 6.420561307807713e-06,
|
|
"loss": 1.4214,
|
|
"step": 540
|
|
},
|
|
{
|
|
"epoch": 0.9722222222222222,
|
|
"grad_norm": 2.9412100315093994,
|
|
"learning_rate": 6.12738151212918e-06,
|
|
"loss": 1.4367,
|
|
"step": 560
|
|
},
|
|
{
|
|
"epoch": 1.0069444444444444,
|
|
"grad_norm": 4.002957820892334,
|
|
"learning_rate": 5.830056206037482e-06,
|
|
"loss": 1.4019,
|
|
"step": 580
|
|
},
|
|
{
|
|
"epoch": 1.0416666666666667,
|
|
"grad_norm": 3.2070395946502686,
|
|
"learning_rate": 5.529678688597081e-06,
|
|
"loss": 1.3294,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 1.0763888888888888,
|
|
"grad_norm": 3.3583526611328125,
|
|
"learning_rate": 5.2273534822017105e-06,
|
|
"loss": 1.3302,
|
|
"step": 620
|
|
},
|
|
{
|
|
"epoch": 1.1111111111111112,
|
|
"grad_norm": 4.011720657348633,
|
|
"learning_rate": 4.924192271119554e-06,
|
|
"loss": 1.2973,
|
|
"step": 640
|
|
},
|
|
{
|
|
"epoch": 1.1458333333333333,
|
|
"grad_norm": 3.383192539215088,
|
|
"learning_rate": 4.621309813703385e-06,
|
|
"loss": 1.3066,
|
|
"step": 660
|
|
},
|
|
{
|
|
"epoch": 1.1805555555555556,
|
|
"grad_norm": 4.335385322570801,
|
|
"learning_rate": 4.319819843296952e-06,
|
|
"loss": 1.3068,
|
|
"step": 680
|
|
},
|
|
{
|
|
"epoch": 1.2152777777777777,
|
|
"grad_norm": 3.696607828140259,
|
|
"learning_rate": 4.020830972910433e-06,
|
|
"loss": 1.3135,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"grad_norm": 3.395407199859619,
|
|
"learning_rate": 3.7254426187239567e-06,
|
|
"loss": 1.2704,
|
|
"step": 720
|
|
},
|
|
{
|
|
"epoch": 1.2847222222222223,
|
|
"grad_norm": 3.829279661178589,
|
|
"learning_rate": 3.4347409574088896e-06,
|
|
"loss": 1.2869,
|
|
"step": 740
|
|
},
|
|
{
|
|
"epoch": 1.3194444444444444,
|
|
"grad_norm": 4.77693510055542,
|
|
"learning_rate": 3.149794932132331e-06,
|
|
"loss": 1.2903,
|
|
"step": 760
|
|
},
|
|
{
|
|
"epoch": 1.3541666666666667,
|
|
"grad_norm": 4.946527004241943,
|
|
"learning_rate": 2.871652321931161e-06,
|
|
"loss": 1.2661,
|
|
"step": 780
|
|
},
|
|
{
|
|
"epoch": 1.3888888888888888,
|
|
"grad_norm": 3.0826640129089355,
|
|
"learning_rate": 2.601335888909005e-06,
|
|
"loss": 1.2786,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 1.4236111111111112,
|
|
"grad_norm": 4.134871959686279,
|
|
"learning_rate": 2.339839617423318e-06,
|
|
"loss": 1.2386,
|
|
"step": 820
|
|
},
|
|
{
|
|
"epoch": 1.4583333333333333,
|
|
"grad_norm": 3.8811264038085938,
|
|
"learning_rate": 2.0881250590915316e-06,
|
|
"loss": 1.2478,
|
|
"step": 840
|
|
},
|
|
{
|
|
"epoch": 1.4930555555555556,
|
|
"grad_norm": 4.137213230133057,
|
|
"learning_rate": 1.8471177970560712e-06,
|
|
"loss": 1.2635,
|
|
"step": 860
|
|
},
|
|
{
|
|
"epoch": 1.5277777777777777,
|
|
"grad_norm": 3.4709768295288086,
|
|
"learning_rate": 1.6177040425095664e-06,
|
|
"loss": 1.2247,
|
|
"step": 880
|
|
},
|
|
{
|
|
"epoch": 1.5625,
|
|
"grad_norm": 3.841049909591675,
|
|
"learning_rate": 1.40072737599522e-06,
|
|
"loss": 1.2721,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 1.5972222222222223,
|
|
"grad_norm": 3.412503480911255,
|
|
"learning_rate": 1.196985645464921e-06,
|
|
"loss": 1.2439,
|
|
"step": 920
|
|
},
|
|
{
|
|
"epoch": 1.6319444444444444,
|
|
"grad_norm": 4.341178894042969,
|
|
"learning_rate": 1.0072280325013185e-06,
|
|
"loss": 1.2459,
|
|
"step": 940
|
|
}
|
|
],
|
|
"logging_steps": 20,
|
|
"max_steps": 1152,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 2,
|
|
"save_steps": 50,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.860300923853865e+17,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|