aleegis11's picture
Training in progress, step 50, checkpoint
0b31437 verified
raw
history blame
10 kB
{
"best_metric": 5.211904048919678,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.003207338390236862,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 6.414676780473723e-05,
"grad_norm": 1.642872929573059,
"learning_rate": 1e-05,
"loss": 4.7768,
"step": 1
},
{
"epoch": 6.414676780473723e-05,
"eval_loss": 5.596181392669678,
"eval_runtime": 175.703,
"eval_samples_per_second": 149.434,
"eval_steps_per_second": 37.359,
"step": 1
},
{
"epoch": 0.00012829353560947447,
"grad_norm": 1.7171331644058228,
"learning_rate": 2e-05,
"loss": 4.9218,
"step": 2
},
{
"epoch": 0.00019244030341421172,
"grad_norm": 1.7027052640914917,
"learning_rate": 3e-05,
"loss": 4.8481,
"step": 3
},
{
"epoch": 0.00025658707121894894,
"grad_norm": 1.678208351135254,
"learning_rate": 4e-05,
"loss": 4.7427,
"step": 4
},
{
"epoch": 0.0003207338390236862,
"grad_norm": 1.685784101486206,
"learning_rate": 5e-05,
"loss": 4.9766,
"step": 5
},
{
"epoch": 0.00038488060682842344,
"grad_norm": 1.6038089990615845,
"learning_rate": 6e-05,
"loss": 4.8053,
"step": 6
},
{
"epoch": 0.00044902737463316066,
"grad_norm": 1.4707045555114746,
"learning_rate": 7e-05,
"loss": 4.9695,
"step": 7
},
{
"epoch": 0.0005131741424378979,
"grad_norm": 1.2065513134002686,
"learning_rate": 8e-05,
"loss": 4.8506,
"step": 8
},
{
"epoch": 0.0005773209102426352,
"grad_norm": 1.217518925666809,
"learning_rate": 9e-05,
"loss": 4.8318,
"step": 9
},
{
"epoch": 0.0006414676780473724,
"grad_norm": 1.1238003969192505,
"learning_rate": 0.0001,
"loss": 4.7909,
"step": 10
},
{
"epoch": 0.0007056144458521096,
"grad_norm": 1.2250131368637085,
"learning_rate": 9.999316524962345e-05,
"loss": 4.8419,
"step": 11
},
{
"epoch": 0.0007697612136568469,
"grad_norm": 1.0958911180496216,
"learning_rate": 9.997266286704631e-05,
"loss": 4.6394,
"step": 12
},
{
"epoch": 0.0008339079814615841,
"grad_norm": 1.075415849685669,
"learning_rate": 9.993849845741524e-05,
"loss": 4.7929,
"step": 13
},
{
"epoch": 0.0008980547492663213,
"grad_norm": 0.9673530459403992,
"learning_rate": 9.989068136093873e-05,
"loss": 4.8091,
"step": 14
},
{
"epoch": 0.0009622015170710586,
"grad_norm": 1.070448398590088,
"learning_rate": 9.98292246503335e-05,
"loss": 4.7363,
"step": 15
},
{
"epoch": 0.0010263482848757958,
"grad_norm": 1.0438446998596191,
"learning_rate": 9.975414512725057e-05,
"loss": 4.6623,
"step": 16
},
{
"epoch": 0.001090495052680533,
"grad_norm": 1.0157839059829712,
"learning_rate": 9.966546331768191e-05,
"loss": 4.6976,
"step": 17
},
{
"epoch": 0.0011546418204852703,
"grad_norm": 1.041697382926941,
"learning_rate": 9.956320346634876e-05,
"loss": 4.6569,
"step": 18
},
{
"epoch": 0.0012187885882900076,
"grad_norm": 1.0324170589447021,
"learning_rate": 9.944739353007344e-05,
"loss": 4.6052,
"step": 19
},
{
"epoch": 0.0012829353560947449,
"grad_norm": 1.0508081912994385,
"learning_rate": 9.931806517013612e-05,
"loss": 4.8329,
"step": 20
},
{
"epoch": 0.001347082123899482,
"grad_norm": 1.0439448356628418,
"learning_rate": 9.917525374361912e-05,
"loss": 4.6623,
"step": 21
},
{
"epoch": 0.0014112288917042192,
"grad_norm": 0.9907127618789673,
"learning_rate": 9.901899829374047e-05,
"loss": 4.6505,
"step": 22
},
{
"epoch": 0.0014753756595089565,
"grad_norm": 1.0066382884979248,
"learning_rate": 9.884934153917997e-05,
"loss": 4.5596,
"step": 23
},
{
"epoch": 0.0015395224273136937,
"grad_norm": 1.057041883468628,
"learning_rate": 9.86663298624003e-05,
"loss": 4.5897,
"step": 24
},
{
"epoch": 0.001603669195118431,
"grad_norm": 1.0306063890457153,
"learning_rate": 9.847001329696653e-05,
"loss": 4.7666,
"step": 25
},
{
"epoch": 0.0016678159629231683,
"grad_norm": 1.0321996212005615,
"learning_rate": 9.826044551386744e-05,
"loss": 4.6842,
"step": 26
},
{
"epoch": 0.0017319627307279054,
"grad_norm": 1.0303255319595337,
"learning_rate": 9.803768380684242e-05,
"loss": 4.7573,
"step": 27
},
{
"epoch": 0.0017961094985326426,
"grad_norm": 1.052943468093872,
"learning_rate": 9.780178907671789e-05,
"loss": 4.5831,
"step": 28
},
{
"epoch": 0.00186025626633738,
"grad_norm": 1.0942226648330688,
"learning_rate": 9.755282581475769e-05,
"loss": 4.569,
"step": 29
},
{
"epoch": 0.0019244030341421172,
"grad_norm": 1.1259537935256958,
"learning_rate": 9.729086208503174e-05,
"loss": 4.6559,
"step": 30
},
{
"epoch": 0.0019885498019468545,
"grad_norm": 1.1287720203399658,
"learning_rate": 9.701596950580806e-05,
"loss": 4.5996,
"step": 31
},
{
"epoch": 0.0020526965697515915,
"grad_norm": 1.3546675443649292,
"learning_rate": 9.672822322997305e-05,
"loss": 4.5527,
"step": 32
},
{
"epoch": 0.002116843337556329,
"grad_norm": 1.4525164365768433,
"learning_rate": 9.642770192448536e-05,
"loss": 4.7025,
"step": 33
},
{
"epoch": 0.002180990105361066,
"grad_norm": 1.6699098348617554,
"learning_rate": 9.611448774886924e-05,
"loss": 4.6607,
"step": 34
},
{
"epoch": 0.0022451368731658036,
"grad_norm": 1.2364184856414795,
"learning_rate": 9.578866633275288e-05,
"loss": 4.743,
"step": 35
},
{
"epoch": 0.0023092836409705406,
"grad_norm": 1.2899703979492188,
"learning_rate": 9.545032675245813e-05,
"loss": 4.5895,
"step": 36
},
{
"epoch": 0.0023734304087752777,
"grad_norm": 1.2018170356750488,
"learning_rate": 9.509956150664796e-05,
"loss": 4.6149,
"step": 37
},
{
"epoch": 0.002437577176580015,
"grad_norm": 1.5725171566009521,
"learning_rate": 9.473646649103818e-05,
"loss": 4.7538,
"step": 38
},
{
"epoch": 0.0025017239443847522,
"grad_norm": 1.5618175268173218,
"learning_rate": 9.43611409721806e-05,
"loss": 4.729,
"step": 39
},
{
"epoch": 0.0025658707121894897,
"grad_norm": 1.3766765594482422,
"learning_rate": 9.397368756032445e-05,
"loss": 4.6127,
"step": 40
},
{
"epoch": 0.0026300174799942268,
"grad_norm": 2.1418488025665283,
"learning_rate": 9.357421218136386e-05,
"loss": 4.7404,
"step": 41
},
{
"epoch": 0.002694164247798964,
"grad_norm": 4.414487361907959,
"learning_rate": 9.316282404787871e-05,
"loss": 4.5486,
"step": 42
},
{
"epoch": 0.0027583110156037013,
"grad_norm": 1.9374182224273682,
"learning_rate": 9.273963562927695e-05,
"loss": 4.5715,
"step": 43
},
{
"epoch": 0.0028224577834084384,
"grad_norm": 1.7547005414962769,
"learning_rate": 9.230476262104677e-05,
"loss": 4.9717,
"step": 44
},
{
"epoch": 0.002886604551213176,
"grad_norm": 2.0398449897766113,
"learning_rate": 9.185832391312644e-05,
"loss": 5.0536,
"step": 45
},
{
"epoch": 0.002950751319017913,
"grad_norm": 2.199415683746338,
"learning_rate": 9.140044155740101e-05,
"loss": 5.0214,
"step": 46
},
{
"epoch": 0.0030148980868226504,
"grad_norm": 2.3262555599212646,
"learning_rate": 9.093124073433463e-05,
"loss": 5.1181,
"step": 47
},
{
"epoch": 0.0030790448546273875,
"grad_norm": 2.498055934906006,
"learning_rate": 9.045084971874738e-05,
"loss": 5.01,
"step": 48
},
{
"epoch": 0.0031431916224321245,
"grad_norm": 2.4217894077301025,
"learning_rate": 8.995939984474624e-05,
"loss": 5.1427,
"step": 49
},
{
"epoch": 0.003207338390236862,
"grad_norm": 3.816474199295044,
"learning_rate": 8.945702546981969e-05,
"loss": 5.765,
"step": 50
},
{
"epoch": 0.003207338390236862,
"eval_loss": 5.211904048919678,
"eval_runtime": 176.0481,
"eval_samples_per_second": 149.141,
"eval_steps_per_second": 37.285,
"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": 1488394911744000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}