aleegis10's picture
Training in progress, step 50, checkpoint
3afa187 verified
raw
history blame
10 kB
{
"best_metric": 1.5395351648330688,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.004213897433736463,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 8.427794867472926e-05,
"grad_norm": 2.148855686187744,
"learning_rate": 1e-05,
"loss": 2.1105,
"step": 1
},
{
"epoch": 8.427794867472926e-05,
"eval_loss": 2.0573813915252686,
"eval_runtime": 1544.4321,
"eval_samples_per_second": 12.94,
"eval_steps_per_second": 3.235,
"step": 1
},
{
"epoch": 0.00016855589734945852,
"grad_norm": 1.8630555868148804,
"learning_rate": 2e-05,
"loss": 1.9751,
"step": 2
},
{
"epoch": 0.00025283384602418777,
"grad_norm": 1.6783190965652466,
"learning_rate": 3e-05,
"loss": 1.7007,
"step": 3
},
{
"epoch": 0.00033711179469891704,
"grad_norm": 1.4482625722885132,
"learning_rate": 4e-05,
"loss": 1.5429,
"step": 4
},
{
"epoch": 0.00042138974337364626,
"grad_norm": 1.7178997993469238,
"learning_rate": 5e-05,
"loss": 1.6393,
"step": 5
},
{
"epoch": 0.0005056676920483755,
"grad_norm": 1.1909184455871582,
"learning_rate": 6e-05,
"loss": 1.6192,
"step": 6
},
{
"epoch": 0.0005899456407231048,
"grad_norm": 1.0116609334945679,
"learning_rate": 7e-05,
"loss": 1.86,
"step": 7
},
{
"epoch": 0.0006742235893978341,
"grad_norm": 0.9478005170822144,
"learning_rate": 8e-05,
"loss": 1.7564,
"step": 8
},
{
"epoch": 0.0007585015380725634,
"grad_norm": 0.9280062913894653,
"learning_rate": 9e-05,
"loss": 1.8039,
"step": 9
},
{
"epoch": 0.0008427794867472925,
"grad_norm": 0.9564406275749207,
"learning_rate": 0.0001,
"loss": 1.6172,
"step": 10
},
{
"epoch": 0.0009270574354220218,
"grad_norm": 0.9788842797279358,
"learning_rate": 9.999316524962345e-05,
"loss": 1.7433,
"step": 11
},
{
"epoch": 0.001011335384096751,
"grad_norm": 1.0648996829986572,
"learning_rate": 9.997266286704631e-05,
"loss": 1.6529,
"step": 12
},
{
"epoch": 0.0010956133327714803,
"grad_norm": 0.8593961000442505,
"learning_rate": 9.993849845741524e-05,
"loss": 1.476,
"step": 13
},
{
"epoch": 0.0011798912814462096,
"grad_norm": 0.7885779738426208,
"learning_rate": 9.989068136093873e-05,
"loss": 2.0156,
"step": 14
},
{
"epoch": 0.001264169230120939,
"grad_norm": 0.791583240032196,
"learning_rate": 9.98292246503335e-05,
"loss": 1.7382,
"step": 15
},
{
"epoch": 0.0013484471787956682,
"grad_norm": 0.7276984453201294,
"learning_rate": 9.975414512725057e-05,
"loss": 1.7673,
"step": 16
},
{
"epoch": 0.0014327251274703974,
"grad_norm": 0.705528736114502,
"learning_rate": 9.966546331768191e-05,
"loss": 1.5786,
"step": 17
},
{
"epoch": 0.0015170030761451267,
"grad_norm": 0.619422435760498,
"learning_rate": 9.956320346634876e-05,
"loss": 1.3861,
"step": 18
},
{
"epoch": 0.0016012810248198558,
"grad_norm": 0.7505267858505249,
"learning_rate": 9.944739353007344e-05,
"loss": 1.7197,
"step": 19
},
{
"epoch": 0.001685558973494585,
"grad_norm": 0.6622971296310425,
"learning_rate": 9.931806517013612e-05,
"loss": 1.5297,
"step": 20
},
{
"epoch": 0.0017698369221693143,
"grad_norm": 0.6275780200958252,
"learning_rate": 9.917525374361912e-05,
"loss": 1.5839,
"step": 21
},
{
"epoch": 0.0018541148708440436,
"grad_norm": 0.679114580154419,
"learning_rate": 9.901899829374047e-05,
"loss": 1.7993,
"step": 22
},
{
"epoch": 0.0019383928195187729,
"grad_norm": 0.8077395558357239,
"learning_rate": 9.884934153917997e-05,
"loss": 1.5271,
"step": 23
},
{
"epoch": 0.002022670768193502,
"grad_norm": 0.7224380373954773,
"learning_rate": 9.86663298624003e-05,
"loss": 1.5168,
"step": 24
},
{
"epoch": 0.0021069487168682314,
"grad_norm": 0.6832942962646484,
"learning_rate": 9.847001329696653e-05,
"loss": 1.407,
"step": 25
},
{
"epoch": 0.0021912266655429607,
"grad_norm": 0.5775948166847229,
"learning_rate": 9.826044551386744e-05,
"loss": 1.3875,
"step": 26
},
{
"epoch": 0.00227550461421769,
"grad_norm": 0.6365522146224976,
"learning_rate": 9.803768380684242e-05,
"loss": 1.614,
"step": 27
},
{
"epoch": 0.0023597825628924192,
"grad_norm": 0.7473817467689514,
"learning_rate": 9.780178907671789e-05,
"loss": 1.7015,
"step": 28
},
{
"epoch": 0.0024440605115671485,
"grad_norm": 0.6332816481590271,
"learning_rate": 9.755282581475769e-05,
"loss": 1.6255,
"step": 29
},
{
"epoch": 0.002528338460241878,
"grad_norm": 0.6358436942100525,
"learning_rate": 9.729086208503174e-05,
"loss": 1.7346,
"step": 30
},
{
"epoch": 0.002612616408916607,
"grad_norm": 0.6233913898468018,
"learning_rate": 9.701596950580806e-05,
"loss": 1.6548,
"step": 31
},
{
"epoch": 0.0026968943575913363,
"grad_norm": 0.587378203868866,
"learning_rate": 9.672822322997305e-05,
"loss": 1.6502,
"step": 32
},
{
"epoch": 0.0027811723062660656,
"grad_norm": 0.7984997630119324,
"learning_rate": 9.642770192448536e-05,
"loss": 1.6918,
"step": 33
},
{
"epoch": 0.002865450254940795,
"grad_norm": 0.651034414768219,
"learning_rate": 9.611448774886924e-05,
"loss": 1.6203,
"step": 34
},
{
"epoch": 0.002949728203615524,
"grad_norm": 0.7940975427627563,
"learning_rate": 9.578866633275288e-05,
"loss": 1.5908,
"step": 35
},
{
"epoch": 0.0030340061522902534,
"grad_norm": 0.756313681602478,
"learning_rate": 9.545032675245813e-05,
"loss": 1.8236,
"step": 36
},
{
"epoch": 0.0031182841009649827,
"grad_norm": 0.6613308191299438,
"learning_rate": 9.509956150664796e-05,
"loss": 1.5652,
"step": 37
},
{
"epoch": 0.0032025620496397116,
"grad_norm": 0.7427698373794556,
"learning_rate": 9.473646649103818e-05,
"loss": 1.5391,
"step": 38
},
{
"epoch": 0.003286839998314441,
"grad_norm": 0.8335131406784058,
"learning_rate": 9.43611409721806e-05,
"loss": 1.8327,
"step": 39
},
{
"epoch": 0.00337111794698917,
"grad_norm": 0.8421139717102051,
"learning_rate": 9.397368756032445e-05,
"loss": 1.7076,
"step": 40
},
{
"epoch": 0.0034553958956638994,
"grad_norm": 0.6234191060066223,
"learning_rate": 9.357421218136386e-05,
"loss": 1.8075,
"step": 41
},
{
"epoch": 0.0035396738443386287,
"grad_norm": 0.7577528953552246,
"learning_rate": 9.316282404787871e-05,
"loss": 1.6297,
"step": 42
},
{
"epoch": 0.003623951793013358,
"grad_norm": 0.8572260141372681,
"learning_rate": 9.273963562927695e-05,
"loss": 1.5807,
"step": 43
},
{
"epoch": 0.003708229741688087,
"grad_norm": 0.7775949835777283,
"learning_rate": 9.230476262104677e-05,
"loss": 1.6965,
"step": 44
},
{
"epoch": 0.0037925076903628165,
"grad_norm": 0.6420420408248901,
"learning_rate": 9.185832391312644e-05,
"loss": 1.524,
"step": 45
},
{
"epoch": 0.0038767856390375457,
"grad_norm": 0.7884761691093445,
"learning_rate": 9.140044155740101e-05,
"loss": 1.6729,
"step": 46
},
{
"epoch": 0.0039610635877122755,
"grad_norm": 0.787156343460083,
"learning_rate": 9.093124073433463e-05,
"loss": 1.7154,
"step": 47
},
{
"epoch": 0.004045341536387004,
"grad_norm": 0.7888066172599792,
"learning_rate": 9.045084971874738e-05,
"loss": 1.9746,
"step": 48
},
{
"epoch": 0.004129619485061734,
"grad_norm": 0.9960417747497559,
"learning_rate": 8.995939984474624e-05,
"loss": 1.7341,
"step": 49
},
{
"epoch": 0.004213897433736463,
"grad_norm": 0.8822570443153381,
"learning_rate": 8.945702546981969e-05,
"loss": 1.7701,
"step": 50
},
{
"epoch": 0.004213897433736463,
"eval_loss": 1.5395351648330688,
"eval_runtime": 1551.3419,
"eval_samples_per_second": 12.882,
"eval_steps_per_second": 3.221,
"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": 7.731132091072512e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}