85ac608c11
Model: cjiao/OpenThoughts3-greedy-groups-top-openthinker3-1.5B-checkpoint-375-length-filtered Source: Original Platform
384 lines
8.4 KiB
JSON
384 lines
8.4 KiB
JSON
{
|
|
"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": 2.5414493083953857,
|
|
"learning_rate": 0.00015996052482925854,
|
|
"loss": 1.3158,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"grad_norm": 22.558874130249023,
|
|
"learning_rate": 0.00015984213827426174,
|
|
"loss": 3.9659,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"grad_norm": 13.792680740356445,
|
|
"learning_rate": 0.0001596449571682464,
|
|
"loss": 2.6879,
|
|
"step": 3
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"grad_norm": 4.81754207611084,
|
|
"learning_rate": 0.00015936917610515826,
|
|
"loss": 2.0717,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"grad_norm": 6.582490921020508,
|
|
"learning_rate": 0.00015901506724761103,
|
|
"loss": 1.9221,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"grad_norm": 3.573866844177246,
|
|
"learning_rate": 0.00015858298005829512,
|
|
"loss": 1.7919,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"grad_norm": 2.014141082763672,
|
|
"learning_rate": 0.0001580733409550998,
|
|
"loss": 1.6514,
|
|
"step": 7
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"grad_norm": 2.1408352851867676,
|
|
"learning_rate": 0.0001574866528902905,
|
|
"loss": 1.561,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"grad_norm": 1.8259636163711548,
|
|
"learning_rate": 0.00015682349485415545,
|
|
"loss": 1.4794,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"grad_norm": 1.1060450077056885,
|
|
"learning_rate": 0.0001560845213036123,
|
|
"loss": 1.4122,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"grad_norm": 1.6639591455459595,
|
|
"learning_rate": 0.00015527046151633805,
|
|
"loss": 1.4144,
|
|
"step": 11
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"grad_norm": 1.007230281829834,
|
|
"learning_rate": 0.00015438211887106013,
|
|
"loss": 1.3658,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"grad_norm": 0.9042938947677612,
|
|
"learning_rate": 0.0001534203700547185,
|
|
"loss": 1.3555,
|
|
"step": 13
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"grad_norm": 1.5797706842422485,
|
|
"learning_rate": 0.00015238616419728157,
|
|
"loss": 1.3031,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"grad_norm": 0.8265913128852844,
|
|
"learning_rate": 0.00015128052193506944,
|
|
"loss": 1.2992,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"grad_norm": 0.7161855697631836,
|
|
"learning_rate": 0.0001501045344035091,
|
|
"loss": 1.3053,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"grad_norm": 0.655879557132721,
|
|
"learning_rate": 0.0001488593621603155,
|
|
"loss": 1.2677,
|
|
"step": 17
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"grad_norm": 0.7548253536224365,
|
|
"learning_rate": 0.00014754623404016122,
|
|
"loss": 1.243,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"grad_norm": 0.7004591822624207,
|
|
"learning_rate": 0.00014616644594196495,
|
|
"loss": 1.2565,
|
|
"step": 19
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"grad_norm": 0.5514001250267029,
|
|
"learning_rate": 0.00014472135954999581,
|
|
"loss": 1.2198,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"grad_norm": 0.45575690269470215,
|
|
"learning_rate": 0.00014321240099005524,
|
|
"loss": 1.2149,
|
|
"step": 21
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"grad_norm": 0.45689329504966736,
|
|
"learning_rate": 0.00014164105942206316,
|
|
"loss": 1.2114,
|
|
"step": 22
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"grad_norm": 0.47528719902038574,
|
|
"learning_rate": 0.00014000888557043678,
|
|
"loss": 1.2158,
|
|
"step": 23
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"grad_norm": 0.4457974135875702,
|
|
"learning_rate": 0.00013831749019371293,
|
|
"loss": 1.2238,
|
|
"step": 24
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"grad_norm": 0.35548001527786255,
|
|
"learning_rate": 0.00013656854249492382,
|
|
"loss": 1.2145,
|
|
"step": 25
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"grad_norm": 0.5427165627479553,
|
|
"learning_rate": 0.00013476376847429511,
|
|
"loss": 1.2081,
|
|
"step": 26
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"grad_norm": 0.44462138414382935,
|
|
"learning_rate": 0.00013290494922589216,
|
|
"loss": 1.1975,
|
|
"step": 27
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"grad_norm": 0.43967288732528687,
|
|
"learning_rate": 0.0001309939191798952,
|
|
"loss": 1.1867,
|
|
"step": 28
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"grad_norm": 0.3888394236564636,
|
|
"learning_rate": 0.00012903256429223813,
|
|
"loss": 1.1566,
|
|
"step": 29
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"grad_norm": 0.3624572455883026,
|
|
"learning_rate": 0.00012702282018339786,
|
|
"loss": 1.1663,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"grad_norm": 0.37822291254997253,
|
|
"learning_rate": 0.00012496667022817044,
|
|
"loss": 1.1654,
|
|
"step": 31
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"grad_norm": 0.312124103307724,
|
|
"learning_rate": 0.00012286614359831974,
|
|
"loss": 1.1489,
|
|
"step": 32
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"grad_norm": 0.3584006428718567,
|
|
"learning_rate": 0.00012072331326002972,
|
|
"loss": 1.18,
|
|
"step": 33
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"grad_norm": 0.2872241735458374,
|
|
"learning_rate": 0.00011854029392813723,
|
|
"loss": 1.139,
|
|
"step": 34
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"grad_norm": 0.2621050179004669,
|
|
"learning_rate": 0.00011631923997916375,
|
|
"loss": 1.1694,
|
|
"step": 35
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"grad_norm": 0.2508472502231598,
|
|
"learning_rate": 0.00011406234332520582,
|
|
"loss": 1.1404,
|
|
"step": 36
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"grad_norm": 0.2924502491950989,
|
|
"learning_rate": 0.00011177183125078245,
|
|
"loss": 1.1311,
|
|
"step": 37
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"grad_norm": 0.3054457902908325,
|
|
"learning_rate": 0.00010944996421477426,
|
|
"loss": 1.1536,
|
|
"step": 38
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"grad_norm": 0.255205363035202,
|
|
"learning_rate": 0.00010709903361962333,
|
|
"loss": 1.137,
|
|
"step": 39
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"grad_norm": 0.2247438281774521,
|
|
"learning_rate": 0.0001047213595499958,
|
|
"loss": 1.1247,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"grad_norm": 0.22704657912254333,
|
|
"learning_rate": 0.00010231928848313836,
|
|
"loss": 1.1189,
|
|
"step": 41
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"grad_norm": 0.22271329164505005,
|
|
"learning_rate": 9.989519097318841e-05,
|
|
"loss": 1.1254,
|
|
"step": 42
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"grad_norm": 0.21321555972099304,
|
|
"learning_rate": 9.745145931172342e-05,
|
|
"loss": 1.0805,
|
|
"step": 43
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"grad_norm": 0.2108481377363205,
|
|
"learning_rate": 9.4990505166858e-05,
|
|
"loss": 1.1303,
|
|
"step": 44
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"grad_norm": 0.2166047990322113,
|
|
"learning_rate": 9.251475720321848e-05,
|
|
"loss": 1.1149,
|
|
"step": 45
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"grad_norm": 0.20189222693443298,
|
|
"learning_rate": 9.002665868514435e-05,
|
|
"loss": 1.1049,
|
|
"step": 46
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"grad_norm": 0.23353922367095947,
|
|
"learning_rate": 8.752866506548117e-05,
|
|
"loss": 1.0833,
|
|
"step": 47
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"grad_norm": 0.20002281665802002,
|
|
"learning_rate": 8.502324156234508e-05,
|
|
"loss": 1.0629,
|
|
"step": 48
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"grad_norm": 0.22263740003108978,
|
|
"learning_rate": 8.251286072625027e-05,
|
|
"loss": 1.1009,
|
|
"step": 49
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.2224554568529129,
|
|
"learning_rate": 8e-05,
|
|
"loss": 1.07,
|
|
"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": 1.335556313035309e+18,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|