aleegis10's picture
Training in progress, step 50, checkpoint
fe6d01c verified
Raw History Blame
9.9 kB
{
"best_metric": 0.745703935623169,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.1558846453624318,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003117692907248636,
"grad_norm": 11.655372619628906,
"learning_rate": 1e-05,
"loss": 9.4725,
"step": 1
},
{
"epoch": 0.003117692907248636,
"eval_loss": 2.0170581340789795,
"eval_runtime": 19.8075,
"eval_samples_per_second": 27.262,
"eval_steps_per_second": 6.816,
"step": 1
},
{
"epoch": 0.006235385814497272,
"grad_norm": 13.125012397766113,
"learning_rate": 2e-05,
"loss": 11.8029,
"step": 2
},
{
"epoch": 0.009353078721745909,
"grad_norm": 12.141226768493652,
"learning_rate": 3e-05,
"loss": 11.4664,
"step": 3
},
{
"epoch": 0.012470771628994544,
"grad_norm": 14.667614936828613,
"learning_rate": 4e-05,
"loss": 12.0023,
"step": 4
},
{
"epoch": 0.01558846453624318,
"grad_norm": 12.08423137664795,
"learning_rate": 5e-05,
"loss": 10.5206,
"step": 5
},
{
"epoch": 0.018706157443491817,
"grad_norm": 11.249734878540039,
"learning_rate": 6e-05,
"loss": 9.5772,
"step": 6
},
{
"epoch": 0.021823850350740453,
"grad_norm": 22.513164520263672,
"learning_rate": 7e-05,
"loss": 9.5923,
"step": 7
},
{
"epoch": 0.02494154325798909,
"grad_norm": 18.979618072509766,
"learning_rate": 8e-05,
"loss": 9.3301,
"step": 8
},
{
"epoch": 0.028059236165237724,
"grad_norm": 29.20528221130371,
"learning_rate": 9e-05,
"loss": 10.607,
"step": 9
},
{
"epoch": 0.03117692907248636,
"grad_norm": 25.135574340820312,
"learning_rate": 0.0001,
"loss": 11.5226,
"step": 10
},
{
"epoch": 0.034294621979735,
"grad_norm": 15.285947799682617,
"learning_rate": 9.999316524962345e-05,
"loss": 8.4817,
"step": 11
},
{
"epoch": 0.037412314886983634,
"grad_norm": 15.414291381835938,
"learning_rate": 9.997266286704631e-05,
"loss": 7.4645,
"step": 12
},
{
"epoch": 0.04053000779423227,
"grad_norm": 13.062957763671875,
"learning_rate": 9.993849845741524e-05,
"loss": 5.7704,
"step": 13
},
{
"epoch": 0.043647700701480906,
"grad_norm": 13.44833755493164,
"learning_rate": 9.989068136093873e-05,
"loss": 6.9123,
"step": 14
},
{
"epoch": 0.04676539360872954,
"grad_norm": 12.443500518798828,
"learning_rate": 9.98292246503335e-05,
"loss": 5.7389,
"step": 15
},
{
"epoch": 0.04988308651597818,
"grad_norm": 12.959155082702637,
"learning_rate": 9.975414512725057e-05,
"loss": 5.9033,
"step": 16
},
{
"epoch": 0.05300077942322681,
"grad_norm": 9.476544380187988,
"learning_rate": 9.966546331768191e-05,
"loss": 5.9961,
"step": 17
},
{
"epoch": 0.05611847233047545,
"grad_norm": 11.186797142028809,
"learning_rate": 9.956320346634876e-05,
"loss": 5.6498,
"step": 18
},
{
"epoch": 0.059236165237724084,
"grad_norm": 11.144340515136719,
"learning_rate": 9.944739353007344e-05,
"loss": 5.4165,
"step": 19
},
{
"epoch": 0.06235385814497272,
"grad_norm": 12.207180976867676,
"learning_rate": 9.931806517013612e-05,
"loss": 6.3502,
"step": 20
},
{
"epoch": 0.06547155105222136,
"grad_norm": 12.063061714172363,
"learning_rate": 9.917525374361912e-05,
"loss": 5.482,
"step": 21
},
{
"epoch": 0.06858924395947,
"grad_norm": 13.639694213867188,
"learning_rate": 9.901899829374047e-05,
"loss": 5.8621,
"step": 22
},
{
"epoch": 0.07170693686671863,
"grad_norm": 10.871453285217285,
"learning_rate": 9.884934153917997e-05,
"loss": 5.3057,
"step": 23
},
{
"epoch": 0.07482462977396727,
"grad_norm": 11.467005729675293,
"learning_rate": 9.86663298624003e-05,
"loss": 4.4601,
"step": 24
},
{
"epoch": 0.0779423226812159,
"grad_norm": 11.330914497375488,
"learning_rate": 9.847001329696653e-05,
"loss": 4.9252,
"step": 25
},
{
"epoch": 0.08106001558846454,
"grad_norm": 11.97061538696289,
"learning_rate": 9.826044551386744e-05,
"loss": 4.8823,
"step": 26
},
{
"epoch": 0.08417770849571317,
"grad_norm": 13.585055351257324,
"learning_rate": 9.803768380684242e-05,
"loss": 5.3709,
"step": 27
},
{
"epoch": 0.08729540140296181,
"grad_norm": 13.680033683776855,
"learning_rate": 9.780178907671789e-05,
"loss": 5.6623,
"step": 28
},
{
"epoch": 0.09041309431021044,
"grad_norm": 14.604742050170898,
"learning_rate": 9.755282581475769e-05,
"loss": 5.3659,
"step": 29
},
{
"epoch": 0.09353078721745908,
"grad_norm": 13.014104843139648,
"learning_rate": 9.729086208503174e-05,
"loss": 5.0338,
"step": 30
},
{
"epoch": 0.09664848012470771,
"grad_norm": 13.416587829589844,
"learning_rate": 9.701596950580806e-05,
"loss": 4.5345,
"step": 31
},
{
"epoch": 0.09976617303195635,
"grad_norm": 13.330890655517578,
"learning_rate": 9.672822322997305e-05,
"loss": 4.7284,
"step": 32
},
{
"epoch": 0.10288386593920498,
"grad_norm": 14.181489944458008,
"learning_rate": 9.642770192448536e-05,
"loss": 5.1683,
"step": 33
},
{
"epoch": 0.10600155884645363,
"grad_norm": 14.32101058959961,
"learning_rate": 9.611448774886924e-05,
"loss": 4.4735,
"step": 34
},
{
"epoch": 0.10911925175370225,
"grad_norm": 11.41262435913086,
"learning_rate": 9.578866633275288e-05,
"loss": 4.555,
"step": 35
},
{
"epoch": 0.1122369446609509,
"grad_norm": 11.651115417480469,
"learning_rate": 9.545032675245813e-05,
"loss": 4.3732,
"step": 36
},
{
"epoch": 0.11535463756819954,
"grad_norm": 10.54432487487793,
"learning_rate": 9.509956150664796e-05,
"loss": 4.2542,
"step": 37
},
{
"epoch": 0.11847233047544817,
"grad_norm": 13.021109580993652,
"learning_rate": 9.473646649103818e-05,
"loss": 4.5108,
"step": 38
},
{
"epoch": 0.12159002338269681,
"grad_norm": 13.503449440002441,
"learning_rate": 9.43611409721806e-05,
"loss": 4.2284,
"step": 39
},
{
"epoch": 0.12470771628994544,
"grad_norm": 13.191174507141113,
"learning_rate": 9.397368756032445e-05,
"loss": 4.2834,
"step": 40
},
{
"epoch": 0.12782540919719407,
"grad_norm": 12.584697723388672,
"learning_rate": 9.357421218136386e-05,
"loss": 3.8461,
"step": 41
},
{
"epoch": 0.1309431021044427,
"grad_norm": 14.472663879394531,
"learning_rate": 9.316282404787871e-05,
"loss": 3.8354,
"step": 42
},
{
"epoch": 0.13406079501169135,
"grad_norm": 12.175851821899414,
"learning_rate": 9.273963562927695e-05,
"loss": 3.9488,
"step": 43
},
{
"epoch": 0.13717848791894,
"grad_norm": 28.482507705688477,
"learning_rate": 9.230476262104677e-05,
"loss": 3.8271,
"step": 44
},
{
"epoch": 0.1402961808261886,
"grad_norm": 18.594249725341797,
"learning_rate": 9.185832391312644e-05,
"loss": 4.1931,
"step": 45
},
{
"epoch": 0.14341387373343725,
"grad_norm": 15.749979019165039,
"learning_rate": 9.140044155740101e-05,
"loss": 3.1982,
"step": 46
},
{
"epoch": 0.1465315666406859,
"grad_norm": 20.301923751831055,
"learning_rate": 9.093124073433463e-05,
"loss": 4.3817,
"step": 47
},
{
"epoch": 0.14964925954793454,
"grad_norm": 13.996861457824707,
"learning_rate": 9.045084971874738e-05,
"loss": 4.1606,
"step": 48
},
{
"epoch": 0.15276695245518315,
"grad_norm": 19.21599006652832,
"learning_rate": 8.995939984474624e-05,
"loss": 4.6406,
"step": 49
},
{
"epoch": 0.1558846453624318,
"grad_norm": 19.336666107177734,
"learning_rate": 8.945702546981969e-05,
"loss": 4.3495,
"step": 50
},
{
"epoch": 0.1558846453624318,
"eval_loss": 0.745703935623169,
"eval_runtime": 20.391,
"eval_samples_per_second": 26.482,
"eval_steps_per_second": 6.621,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.92427982176256e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}