ee-searchqa-sr / trainer_state.json
Chasechenxc's picture
Re-upload searchqa_sr checkpoint
2dcc71d verified
Raw
History Blame Contribute Delete
7.17 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 360,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08376963350785341,
"grad_norm": 3.169169896438987,
"learning_rate": 8.181818181818183e-06,
"loss": 1.8489,
"step": 10
},
{
"epoch": 0.16753926701570682,
"grad_norm": 1.3802763747416895,
"learning_rate": 9.987040710851148e-06,
"loss": 1.1097,
"step": 20
},
{
"epoch": 0.2513089005235602,
"grad_norm": 1.8235147456527805,
"learning_rate": 9.934508710457944e-06,
"loss": 0.9165,
"step": 30
},
{
"epoch": 0.33507853403141363,
"grad_norm": 1.1094799264769253,
"learning_rate": 9.842019097444414e-06,
"loss": 0.8707,
"step": 40
},
{
"epoch": 0.418848167539267,
"grad_norm": 1.071204885131367,
"learning_rate": 9.710320814480448e-06,
"loss": 0.8491,
"step": 50
},
{
"epoch": 0.5026178010471204,
"grad_norm": 1.0480012388850464,
"learning_rate": 9.540480299844345e-06,
"loss": 0.8325,
"step": 60
},
{
"epoch": 0.5863874345549738,
"grad_norm": 1.0445713310540294,
"learning_rate": 9.333872851846285e-06,
"loss": 0.8025,
"step": 70
},
{
"epoch": 0.6701570680628273,
"grad_norm": 1.0143705207544078,
"learning_rate": 9.092171492230883e-06,
"loss": 0.8215,
"step": 80
},
{
"epoch": 0.7539267015706806,
"grad_norm": 1.1383403777344858,
"learning_rate": 8.817333418738382e-06,
"loss": 0.7901,
"step": 90
},
{
"epoch": 0.837696335078534,
"grad_norm": 1.06314552298384,
"learning_rate": 8.511584156526059e-06,
"loss": 0.798,
"step": 100
},
{
"epoch": 0.9214659685863874,
"grad_norm": 1.0187818573520582,
"learning_rate": 8.17739953678508e-06,
"loss": 0.7784,
"step": 110
},
{
"epoch": 1.0,
"grad_norm": 0.9987724518107024,
"learning_rate": 7.817485648482514e-06,
"loss": 0.7701,
"step": 120
},
{
"epoch": 1.0837696335078535,
"grad_norm": 1.2075010096518963,
"learning_rate": 7.4347569255710254e-06,
"loss": 0.6348,
"step": 130
},
{
"epoch": 1.1675392670157068,
"grad_norm": 1.1252494325347693,
"learning_rate": 7.03231254710695e-06,
"loss": 0.6368,
"step": 140
},
{
"epoch": 1.2513089005235603,
"grad_norm": 1.0071602621155262,
"learning_rate": 6.613411341378872e-06,
"loss": 0.6424,
"step": 150
},
{
"epoch": 1.3350785340314135,
"grad_norm": 1.0423961874539487,
"learning_rate": 6.181445397262671e-06,
"loss": 0.629,
"step": 160
},
{
"epoch": 1.418848167539267,
"grad_norm": 1.0610480085254952,
"learning_rate": 5.739912596487396e-06,
"loss": 0.6295,
"step": 170
},
{
"epoch": 1.5026178010471205,
"grad_norm": 0.9844726794912988,
"learning_rate": 5.292388289234349e-06,
"loss": 0.6321,
"step": 180
},
{
"epoch": 1.5863874345549738,
"grad_norm": 1.0658948538036357,
"learning_rate": 4.842496342428616e-06,
"loss": 0.6225,
"step": 190
},
{
"epoch": 1.6701570680628273,
"grad_norm": 1.0102500512090389,
"learning_rate": 4.393879795162088e-06,
"loss": 0.6309,
"step": 200
},
{
"epoch": 1.7539267015706805,
"grad_norm": 1.0308580477438927,
"learning_rate": 3.950171358868177e-06,
"loss": 0.6113,
"step": 210
},
{
"epoch": 1.837696335078534,
"grad_norm": 1.135723953503225,
"learning_rate": 3.5149640011256438e-06,
"loss": 0.6361,
"step": 220
},
{
"epoch": 1.9214659685863875,
"grad_norm": 1.0564348370808865,
"learning_rate": 3.091781851291753e-06,
"loss": 0.6244,
"step": 230
},
{
"epoch": 2.0,
"grad_norm": 1.0156710112462206,
"learning_rate": 2.684051663558884e-06,
"loss": 0.6135,
"step": 240
},
{
"epoch": 2.0837696335078535,
"grad_norm": 1.1070950299043167,
"learning_rate": 2.2950750685150045e-06,
"loss": 0.5203,
"step": 250
},
{
"epoch": 2.167539267015707,
"grad_norm": 1.1867040422823472,
"learning_rate": 1.9280018379033884e-06,
"loss": 0.5044,
"step": 260
},
{
"epoch": 2.25130890052356,
"grad_norm": 1.1491308045780408,
"learning_rate": 1.5858043790725096e-06,
"loss": 0.4921,
"step": 270
},
{
"epoch": 2.3350785340314135,
"grad_norm": 1.1572535320627513,
"learning_rate": 1.2712536656495167e-06,
"loss": 0.511,
"step": 280
},
{
"epoch": 2.418848167539267,
"grad_norm": 1.1012580832378704,
"learning_rate": 9.868967993407603e-07,
"loss": 0.5013,
"step": 290
},
{
"epoch": 2.5026178010471205,
"grad_norm": 1.0370411119291143,
"learning_rate": 7.35036384554621e-07,
"loss": 0.4961,
"step": 300
},
{
"epoch": 2.5863874345549736,
"grad_norm": 1.0686281277697005,
"learning_rate": 5.177118828624395e-07,
"loss": 0.5056,
"step": 310
},
{
"epoch": 2.670157068062827,
"grad_norm": 1.1392900772951553,
"learning_rate": 3.36683098281404e-07,
"loss": 0.4914,
"step": 320
},
{
"epoch": 2.7539267015706805,
"grad_norm": 1.0467255500464812,
"learning_rate": 1.9341592710876656e-07,
"loss": 0.4991,
"step": 330
},
{
"epoch": 2.837696335078534,
"grad_norm": 1.14569883298037,
"learning_rate": 8.907048769932813e-08,
"loss": 0.5084,
"step": 340
},
{
"epoch": 2.9214659685863875,
"grad_norm": 1.0648873056672876,
"learning_rate": 2.4491726306357656e-08,
"loss": 0.5052,
"step": 350
},
{
"epoch": 3.0,
"grad_norm": 1.978921784285558,
"learning_rate": 2.0257505595810966e-10,
"loss": 0.4979,
"step": 360
},
{
"epoch": 3.0,
"step": 360,
"total_flos": 139401716826112.0,
"train_loss": 0.6878950622346666,
"train_runtime": 5355.5704,
"train_samples_per_second": 8.559,
"train_steps_per_second": 0.067
}
],
"logging_steps": 10,
"max_steps": 360,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 139401716826112.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}