259 lines
6.1 KiB
JSON
259 lines
6.1 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1284722222222223,
|
|
"eval_steps": 500,
|
|
"global_step": 650,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.034722222222222224,
|
|
"grad_norm": 2.985321283340454,
|
|
"learning_rate": 1.6379310344827587e-06,
|
|
"loss": 2.6523,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.06944444444444445,
|
|
"grad_norm": 2.353632926940918,
|
|
"learning_rate": 3.362068965517242e-06,
|
|
"loss": 2.4359,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.10416666666666667,
|
|
"grad_norm": 1.865394115447998,
|
|
"learning_rate": 5.086206896551724e-06,
|
|
"loss": 2.2545,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.1388888888888889,
|
|
"grad_norm": 1.8125933408737183,
|
|
"learning_rate": 6.810344827586207e-06,
|
|
"loss": 2.0557,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.1736111111111111,
|
|
"grad_norm": 2.3572490215301514,
|
|
"learning_rate": 8.53448275862069e-06,
|
|
"loss": 1.9334,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.20833333333333334,
|
|
"grad_norm": 2.395277261734009,
|
|
"learning_rate": 9.999793100349294e-06,
|
|
"loss": 1.9212,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.24305555555555555,
|
|
"grad_norm": 2.714841604232788,
|
|
"learning_rate": 9.987843743451796e-06,
|
|
"loss": 1.7889,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 2.236692190170288,
|
|
"learning_rate": 9.957553516178782e-06,
|
|
"loss": 1.716,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.3125,
|
|
"grad_norm": 2.3020412921905518,
|
|
"learning_rate": 9.909033799150947e-06,
|
|
"loss": 1.7569,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.3472222222222222,
|
|
"grad_norm": 2.5109288692474365,
|
|
"learning_rate": 9.842463004902127e-06,
|
|
"loss": 1.6664,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.3819444444444444,
|
|
"grad_norm": 2.5140888690948486,
|
|
"learning_rate": 9.758085921836076e-06,
|
|
"loss": 1.6544,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.4166666666666667,
|
|
"grad_norm": 2.666377544403076,
|
|
"learning_rate": 9.656212814111567e-06,
|
|
"loss": 1.6608,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.4513888888888889,
|
|
"grad_norm": 2.715240955352783,
|
|
"learning_rate": 9.53721828076571e-06,
|
|
"loss": 1.6353,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.4861111111111111,
|
|
"grad_norm": 2.7697439193725586,
|
|
"learning_rate": 9.401539878270545e-06,
|
|
"loss": 1.6352,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.5208333333333334,
|
|
"grad_norm": 2.9743459224700928,
|
|
"learning_rate": 9.249676511588e-06,
|
|
"loss": 1.6275,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.5555555555555556,
|
|
"grad_norm": 2.955244541168213,
|
|
"learning_rate": 9.082186599639429e-06,
|
|
"loss": 1.6052,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 0.5902777777777778,
|
|
"grad_norm": 2.6228716373443604,
|
|
"learning_rate": 8.899686021935554e-06,
|
|
"loss": 1.5924,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 0.625,
|
|
"grad_norm": 2.7822635173797607,
|
|
"learning_rate": 8.702845853917242e-06,
|
|
"loss": 1.5711,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 0.6597222222222222,
|
|
"grad_norm": 2.450777769088745,
|
|
"learning_rate": 8.492389899334572e-06,
|
|
"loss": 1.5601,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 0.6944444444444444,
|
|
"grad_norm": 2.999849557876587,
|
|
"learning_rate": 8.269092028737885e-06,
|
|
"loss": 1.5497,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.7291666666666666,
|
|
"grad_norm": 3.2980637550354004,
|
|
"learning_rate": 8.033773333867498e-06,
|
|
"loss": 1.5243,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 0.7638888888888888,
|
|
"grad_norm": 2.758843421936035,
|
|
"learning_rate": 7.78729910840572e-06,
|
|
"loss": 1.5171,
|
|
"step": 440
|
|
},
|
|
{
|
|
"epoch": 0.7986111111111112,
|
|
"grad_norm": 3.114650249481201,
|
|
"learning_rate": 7.530575666193283e-06,
|
|
"loss": 1.5212,
|
|
"step": 460
|
|
},
|
|
{
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 3.235766649246216,
|
|
"learning_rate": 7.26454700860997e-06,
|
|
"loss": 1.5019,
|
|
"step": 480
|
|
},
|
|
{
|
|
"epoch": 0.8680555555555556,
|
|
"grad_norm": 3.39516544342041,
|
|
"learning_rate": 6.990191353373876e-06,
|
|
"loss": 1.4963,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.9027777777777778,
|
|
"grad_norm": 3.507965087890625,
|
|
"learning_rate": 6.708517537523264e-06,
|
|
"loss": 1.4762,
|
|
"step": 520
|
|
},
|
|
{
|
|
"epoch": 0.9375,
|
|
"grad_norm": 3.2428181171417236,
|
|
"learning_rate": 6.420561307807713e-06,
|
|
"loss": 1.4822,
|
|
"step": 540
|
|
},
|
|
{
|
|
"epoch": 0.9722222222222222,
|
|
"grad_norm": 2.9236435890197754,
|
|
"learning_rate": 6.12738151212918e-06,
|
|
"loss": 1.5021,
|
|
"step": 560
|
|
},
|
|
{
|
|
"epoch": 1.0069444444444444,
|
|
"grad_norm": 3.689115047454834,
|
|
"learning_rate": 5.830056206037482e-06,
|
|
"loss": 1.4606,
|
|
"step": 580
|
|
},
|
|
{
|
|
"epoch": 1.0416666666666667,
|
|
"grad_norm": 2.897470474243164,
|
|
"learning_rate": 5.529678688597081e-06,
|
|
"loss": 1.3981,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 1.0763888888888888,
|
|
"grad_norm": 3.1479601860046387,
|
|
"learning_rate": 5.2273534822017105e-06,
|
|
"loss": 1.4024,
|
|
"step": 620
|
|
},
|
|
{
|
|
"epoch": 1.1111111111111112,
|
|
"grad_norm": 3.726175546646118,
|
|
"learning_rate": 4.924192271119554e-06,
|
|
"loss": 1.3784,
|
|
"step": 640
|
|
}
|
|
],
|
|
"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": 1.321789950959616e+17,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|