385 lines
9.1 KiB
JSON
385 lines
9.1 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.7361111111111112,
|
|
"eval_steps": 500,
|
|
"global_step": 1000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.034722222222222224,
|
|
"grad_norm": 2.528588056564331,
|
|
"learning_rate": 1.6379310344827587e-06,
|
|
"loss": 2.4452,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.06944444444444445,
|
|
"grad_norm": 1.9198594093322754,
|
|
"learning_rate": 3.362068965517242e-06,
|
|
"loss": 2.2698,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.10416666666666667,
|
|
"grad_norm": 1.7612886428833008,
|
|
"learning_rate": 5.086206896551724e-06,
|
|
"loss": 2.1235,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.1388888888888889,
|
|
"grad_norm": 1.667220115661621,
|
|
"learning_rate": 6.810344827586207e-06,
|
|
"loss": 1.9688,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.1736111111111111,
|
|
"grad_norm": 2.0434842109680176,
|
|
"learning_rate": 8.53448275862069e-06,
|
|
"loss": 1.852,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.20833333333333334,
|
|
"grad_norm": 2.1740384101867676,
|
|
"learning_rate": 9.999793100349294e-06,
|
|
"loss": 1.8515,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.24305555555555555,
|
|
"grad_norm": 2.4882936477661133,
|
|
"learning_rate": 9.987843743451796e-06,
|
|
"loss": 1.7452,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 2.0491299629211426,
|
|
"learning_rate": 9.957553516178782e-06,
|
|
"loss": 1.672,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.3125,
|
|
"grad_norm": 2.3231043815612793,
|
|
"learning_rate": 9.909033799150947e-06,
|
|
"loss": 1.7257,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.3472222222222222,
|
|
"grad_norm": 2.2714061737060547,
|
|
"learning_rate": 9.842463004902127e-06,
|
|
"loss": 1.6321,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.3819444444444444,
|
|
"grad_norm": 2.4732699394226074,
|
|
"learning_rate": 9.758085921836076e-06,
|
|
"loss": 1.6189,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.4166666666666667,
|
|
"grad_norm": 2.4421303272247314,
|
|
"learning_rate": 9.656212814111567e-06,
|
|
"loss": 1.6285,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.4513888888888889,
|
|
"grad_norm": 2.8063509464263916,
|
|
"learning_rate": 9.53721828076571e-06,
|
|
"loss": 1.5975,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.4861111111111111,
|
|
"grad_norm": 2.7459986209869385,
|
|
"learning_rate": 9.401539878270545e-06,
|
|
"loss": 1.5955,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.5208333333333334,
|
|
"grad_norm": 2.9211506843566895,
|
|
"learning_rate": 9.249676511588e-06,
|
|
"loss": 1.5918,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.5555555555555556,
|
|
"grad_norm": 2.7910404205322266,
|
|
"learning_rate": 9.082186599639429e-06,
|
|
"loss": 1.5728,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 0.5902777777777778,
|
|
"grad_norm": 2.565889596939087,
|
|
"learning_rate": 8.899686021935554e-06,
|
|
"loss": 1.5565,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 0.625,
|
|
"grad_norm": 2.653115749359131,
|
|
"learning_rate": 8.702845853917242e-06,
|
|
"loss": 1.5323,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 0.6597222222222222,
|
|
"grad_norm": 2.514103412628174,
|
|
"learning_rate": 8.492389899334572e-06,
|
|
"loss": 1.5109,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 0.6944444444444444,
|
|
"grad_norm": 2.9695253372192383,
|
|
"learning_rate": 8.269092028737885e-06,
|
|
"loss": 1.4991,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.7291666666666666,
|
|
"grad_norm": 2.9976706504821777,
|
|
"learning_rate": 8.033773333867498e-06,
|
|
"loss": 1.4744,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 0.7638888888888888,
|
|
"grad_norm": 2.794107675552368,
|
|
"learning_rate": 7.78729910840572e-06,
|
|
"loss": 1.4678,
|
|
"step": 440
|
|
},
|
|
{
|
|
"epoch": 0.7986111111111112,
|
|
"grad_norm": 2.9695143699645996,
|
|
"learning_rate": 7.530575666193283e-06,
|
|
"loss": 1.4634,
|
|
"step": 460
|
|
},
|
|
{
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 3.623947858810425,
|
|
"learning_rate": 7.26454700860997e-06,
|
|
"loss": 1.4467,
|
|
"step": 480
|
|
},
|
|
{
|
|
"epoch": 0.8680555555555556,
|
|
"grad_norm": 3.5737252235412598,
|
|
"learning_rate": 6.990191353373876e-06,
|
|
"loss": 1.4423,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.9027777777777778,
|
|
"grad_norm": 3.735530376434326,
|
|
"learning_rate": 6.708517537523264e-06,
|
|
"loss": 1.4011,
|
|
"step": 520
|
|
},
|
|
{
|
|
"epoch": 0.9375,
|
|
"grad_norm": 3.286858081817627,
|
|
"learning_rate": 6.420561307807713e-06,
|
|
"loss": 1.4212,
|
|
"step": 540
|
|
},
|
|
{
|
|
"epoch": 0.9722222222222222,
|
|
"grad_norm": 2.975515842437744,
|
|
"learning_rate": 6.12738151212918e-06,
|
|
"loss": 1.4365,
|
|
"step": 560
|
|
},
|
|
{
|
|
"epoch": 1.0069444444444444,
|
|
"grad_norm": 3.989678144454956,
|
|
"learning_rate": 5.830056206037482e-06,
|
|
"loss": 1.4018,
|
|
"step": 580
|
|
},
|
|
{
|
|
"epoch": 1.0416666666666667,
|
|
"grad_norm": 3.2178144454956055,
|
|
"learning_rate": 5.529678688597081e-06,
|
|
"loss": 1.3287,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 1.0763888888888888,
|
|
"grad_norm": 3.363408088684082,
|
|
"learning_rate": 5.2273534822017105e-06,
|
|
"loss": 1.3294,
|
|
"step": 620
|
|
},
|
|
{
|
|
"epoch": 1.1111111111111112,
|
|
"grad_norm": 4.074166297912598,
|
|
"learning_rate": 4.924192271119554e-06,
|
|
"loss": 1.2959,
|
|
"step": 640
|
|
},
|
|
{
|
|
"epoch": 1.1458333333333333,
|
|
"grad_norm": 3.1612188816070557,
|
|
"learning_rate": 4.621309813703385e-06,
|
|
"loss": 1.3059,
|
|
"step": 660
|
|
},
|
|
{
|
|
"epoch": 1.1805555555555556,
|
|
"grad_norm": 4.3585896492004395,
|
|
"learning_rate": 4.319819843296952e-06,
|
|
"loss": 1.3052,
|
|
"step": 680
|
|
},
|
|
{
|
|
"epoch": 1.2152777777777777,
|
|
"grad_norm": 3.699857234954834,
|
|
"learning_rate": 4.020830972910433e-06,
|
|
"loss": 1.3131,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"grad_norm": 3.4211180210113525,
|
|
"learning_rate": 3.7254426187239567e-06,
|
|
"loss": 1.2698,
|
|
"step": 720
|
|
},
|
|
{
|
|
"epoch": 1.2847222222222223,
|
|
"grad_norm": 3.812756299972534,
|
|
"learning_rate": 3.4347409574088896e-06,
|
|
"loss": 1.286,
|
|
"step": 740
|
|
},
|
|
{
|
|
"epoch": 1.3194444444444444,
|
|
"grad_norm": 4.69367790222168,
|
|
"learning_rate": 3.149794932132331e-06,
|
|
"loss": 1.2883,
|
|
"step": 760
|
|
},
|
|
{
|
|
"epoch": 1.3541666666666667,
|
|
"grad_norm": 4.980796813964844,
|
|
"learning_rate": 2.871652321931161e-06,
|
|
"loss": 1.2646,
|
|
"step": 780
|
|
},
|
|
{
|
|
"epoch": 1.3888888888888888,
|
|
"grad_norm": 3.0813663005828857,
|
|
"learning_rate": 2.601335888909005e-06,
|
|
"loss": 1.2779,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 1.4236111111111112,
|
|
"grad_norm": 4.145002841949463,
|
|
"learning_rate": 2.339839617423318e-06,
|
|
"loss": 1.237,
|
|
"step": 820
|
|
},
|
|
{
|
|
"epoch": 1.4583333333333333,
|
|
"grad_norm": 3.879746437072754,
|
|
"learning_rate": 2.0881250590915316e-06,
|
|
"loss": 1.2466,
|
|
"step": 840
|
|
},
|
|
{
|
|
"epoch": 1.4930555555555556,
|
|
"grad_norm": 4.132529258728027,
|
|
"learning_rate": 1.8471177970560712e-06,
|
|
"loss": 1.2622,
|
|
"step": 860
|
|
},
|
|
{
|
|
"epoch": 1.5277777777777777,
|
|
"grad_norm": 3.4623332023620605,
|
|
"learning_rate": 1.6177040425095664e-06,
|
|
"loss": 1.2239,
|
|
"step": 880
|
|
},
|
|
{
|
|
"epoch": 1.5625,
|
|
"grad_norm": 3.851890802383423,
|
|
"learning_rate": 1.40072737599522e-06,
|
|
"loss": 1.2711,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 1.5972222222222223,
|
|
"grad_norm": 3.429495096206665,
|
|
"learning_rate": 1.196985645464921e-06,
|
|
"loss": 1.2424,
|
|
"step": 920
|
|
},
|
|
{
|
|
"epoch": 1.6319444444444444,
|
|
"grad_norm": 4.348053932189941,
|
|
"learning_rate": 1.0072280325013185e-06,
|
|
"loss": 1.2449,
|
|
"step": 940
|
|
},
|
|
{
|
|
"epoch": 1.6666666666666665,
|
|
"grad_norm": 4.481091022491455,
|
|
"learning_rate": 8.321522974916968e-07,
|
|
"loss": 1.2653,
|
|
"step": 960
|
|
},
|
|
{
|
|
"epoch": 1.7013888888888888,
|
|
"grad_norm": 4.414041996002197,
|
|
"learning_rate": 6.724022138834341e-07,
|
|
"loss": 1.2279,
|
|
"step": 980
|
|
},
|
|
{
|
|
"epoch": 1.7361111111111112,
|
|
"grad_norm": 3.4355506896972656,
|
|
"learning_rate": 5.285652009556075e-07,
|
|
"loss": 1.2171,
|
|
"step": 1000
|
|
}
|
|
],
|
|
"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": 1.9555180478889984e+17,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|