Files
OpenThoughts3-random-groups…/checkpoint-50/trainer_state.json

384 lines
8.4 KiB
JSON
Raw Normal View History

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"grad_norm": 2.0897409915924072,
"learning_rate": 0.00015996052482925854,
"loss": 1.2438,
"step": 1
},
{
"epoch": 0.04,
"grad_norm": 28.813220977783203,
"learning_rate": 0.00015984213827426174,
"loss": 3.7464,
"step": 2
},
{
"epoch": 0.06,
"grad_norm": 16.25991439819336,
"learning_rate": 0.0001596449571682464,
"loss": 2.9219,
"step": 3
},
{
"epoch": 0.08,
"grad_norm": 5.324892520904541,
"learning_rate": 0.00015936917610515826,
"loss": 2.1242,
"step": 4
},
{
"epoch": 0.1,
"grad_norm": 2.8375790119171143,
"learning_rate": 0.00015901506724761103,
"loss": 1.7799,
"step": 5
},
{
"epoch": 0.12,
"grad_norm": 4.01439905166626,
"learning_rate": 0.00015858298005829512,
"loss": 1.6514,
"step": 6
},
{
"epoch": 0.14,
"grad_norm": 2.095858335494995,
"learning_rate": 0.0001580733409550998,
"loss": 1.5758,
"step": 7
},
{
"epoch": 0.16,
"grad_norm": 1.694789171218872,
"learning_rate": 0.0001574866528902905,
"loss": 1.4651,
"step": 8
},
{
"epoch": 0.18,
"grad_norm": 1.4686285257339478,
"learning_rate": 0.00015682349485415545,
"loss": 1.3782,
"step": 9
},
{
"epoch": 0.2,
"grad_norm": 0.9562129378318787,
"learning_rate": 0.0001560845213036123,
"loss": 1.353,
"step": 10
},
{
"epoch": 0.22,
"grad_norm": 1.4398468732833862,
"learning_rate": 0.00015527046151633805,
"loss": 1.3325,
"step": 11
},
{
"epoch": 0.24,
"grad_norm": 0.827878475189209,
"learning_rate": 0.00015438211887106013,
"loss": 1.2997,
"step": 12
},
{
"epoch": 0.26,
"grad_norm": 1.015064001083374,
"learning_rate": 0.0001534203700547185,
"loss": 1.2664,
"step": 13
},
{
"epoch": 0.28,
"grad_norm": 0.680793821811676,
"learning_rate": 0.00015238616419728157,
"loss": 1.239,
"step": 14
},
{
"epoch": 0.3,
"grad_norm": 0.9654543995857239,
"learning_rate": 0.00015128052193506944,
"loss": 1.2528,
"step": 15
},
{
"epoch": 0.32,
"grad_norm": 0.7509903907775879,
"learning_rate": 0.0001501045344035091,
"loss": 1.2447,
"step": 16
},
{
"epoch": 0.34,
"grad_norm": 0.6938178539276123,
"learning_rate": 0.0001488593621603155,
"loss": 1.2231,
"step": 17
},
{
"epoch": 0.36,
"grad_norm": 0.6297674179077148,
"learning_rate": 0.00014754623404016122,
"loss": 1.2305,
"step": 18
},
{
"epoch": 0.38,
"grad_norm": 0.535707950592041,
"learning_rate": 0.00014616644594196495,
"loss": 1.2339,
"step": 19
},
{
"epoch": 0.4,
"grad_norm": 0.5825291275978088,
"learning_rate": 0.00014472135954999581,
"loss": 1.1903,
"step": 20
},
{
"epoch": 0.42,
"grad_norm": 0.36997389793395996,
"learning_rate": 0.00014321240099005524,
"loss": 1.1979,
"step": 21
},
{
"epoch": 0.44,
"grad_norm": 0.4852772355079651,
"learning_rate": 0.00014164105942206316,
"loss": 1.1951,
"step": 22
},
{
"epoch": 0.46,
"grad_norm": 0.43263790011405945,
"learning_rate": 0.00014000888557043678,
"loss": 1.1632,
"step": 23
},
{
"epoch": 0.48,
"grad_norm": 0.39633846282958984,
"learning_rate": 0.00013831749019371293,
"loss": 1.1631,
"step": 24
},
{
"epoch": 0.5,
"grad_norm": 0.41002726554870605,
"learning_rate": 0.00013656854249492382,
"loss": 1.1886,
"step": 25
},
{
"epoch": 0.52,
"grad_norm": 0.39650410413742065,
"learning_rate": 0.00013476376847429511,
"loss": 1.202,
"step": 26
},
{
"epoch": 0.54,
"grad_norm": 0.3824397921562195,
"learning_rate": 0.00013290494922589216,
"loss": 1.1832,
"step": 27
},
{
"epoch": 0.56,
"grad_norm": 0.3212684094905853,
"learning_rate": 0.0001309939191798952,
"loss": 1.1466,
"step": 28
},
{
"epoch": 0.58,
"grad_norm": 0.32189854979515076,
"learning_rate": 0.00012903256429223813,
"loss": 1.1975,
"step": 29
},
{
"epoch": 0.6,
"grad_norm": 0.3070578873157501,
"learning_rate": 0.00012702282018339786,
"loss": 1.154,
"step": 30
},
{
"epoch": 0.62,
"grad_norm": 0.25685596466064453,
"learning_rate": 0.00012496667022817044,
"loss": 1.1357,
"step": 31
},
{
"epoch": 0.64,
"grad_norm": 0.2539421021938324,
"learning_rate": 0.00012286614359831974,
"loss": 1.158,
"step": 32
},
{
"epoch": 0.66,
"grad_norm": 0.2875991761684418,
"learning_rate": 0.00012072331326002972,
"loss": 1.1849,
"step": 33
},
{
"epoch": 0.68,
"grad_norm": 0.2683248221874237,
"learning_rate": 0.00011854029392813723,
"loss": 1.1935,
"step": 34
},
{
"epoch": 0.7,
"grad_norm": 0.2622566819190979,
"learning_rate": 0.00011631923997916375,
"loss": 1.1624,
"step": 35
},
{
"epoch": 0.72,
"grad_norm": 0.2862881124019623,
"learning_rate": 0.00011406234332520582,
"loss": 1.1854,
"step": 36
},
{
"epoch": 0.74,
"grad_norm": 0.24599239230155945,
"learning_rate": 0.00011177183125078245,
"loss": 1.1597,
"step": 37
},
{
"epoch": 0.76,
"grad_norm": 0.23713542520999908,
"learning_rate": 0.00010944996421477426,
"loss": 1.125,
"step": 38
},
{
"epoch": 0.78,
"grad_norm": 0.26411688327789307,
"learning_rate": 0.00010709903361962333,
"loss": 1.1144,
"step": 39
},
{
"epoch": 0.8,
"grad_norm": 0.24425670504570007,
"learning_rate": 0.0001047213595499958,
"loss": 1.1443,
"step": 40
},
{
"epoch": 0.82,
"grad_norm": 0.26452597975730896,
"learning_rate": 0.00010231928848313836,
"loss": 1.1376,
"step": 41
},
{
"epoch": 0.84,
"grad_norm": 0.21576781570911407,
"learning_rate": 9.989519097318841e-05,
"loss": 1.1616,
"step": 42
},
{
"epoch": 0.86,
"grad_norm": 0.2854762375354767,
"learning_rate": 9.745145931172342e-05,
"loss": 1.1511,
"step": 43
},
{
"epoch": 0.88,
"grad_norm": 0.2194770872592926,
"learning_rate": 9.4990505166858e-05,
"loss": 1.1385,
"step": 44
},
{
"epoch": 0.9,
"grad_norm": 0.22979624569416046,
"learning_rate": 9.251475720321848e-05,
"loss": 1.1429,
"step": 45
},
{
"epoch": 0.92,
"grad_norm": 0.22235210239887238,
"learning_rate": 9.002665868514435e-05,
"loss": 1.119,
"step": 46
},
{
"epoch": 0.94,
"grad_norm": 0.22438690066337585,
"learning_rate": 8.752866506548117e-05,
"loss": 1.1642,
"step": 47
},
{
"epoch": 0.96,
"grad_norm": 0.18937288224697113,
"learning_rate": 8.502324156234508e-05,
"loss": 1.1281,
"step": 48
},
{
"epoch": 0.98,
"grad_norm": 0.22655418515205383,
"learning_rate": 8.251286072625027e-05,
"loss": 1.1399,
"step": 49
},
{
"epoch": 1.0,
"grad_norm": 0.21689347922801971,
"learning_rate": 8e-05,
"loss": 1.0937,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"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": 1.131732051523797e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}