bbytxt's picture
Training in progress, step 50, checkpoint
cd8de28 verified
raw
history blame
9.94 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.0946073793755913,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001892147587511826,
"grad_norm": 2.4111679522320628e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.001892147587511826,
"eval_loss": 11.5,
"eval_runtime": 4.1112,
"eval_samples_per_second": 216.48,
"eval_steps_per_second": 54.242,
"step": 1
},
{
"epoch": 0.003784295175023652,
"grad_norm": 5.082612915430218e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.005676442762535478,
"grad_norm": 3.6502256989479065e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.007568590350047304,
"grad_norm": 4.035709207528271e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.00946073793755913,
"grad_norm": 2.7358584702597e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.011352885525070956,
"grad_norm": 6.69207438477315e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.013245033112582781,
"grad_norm": 5.749729461967945e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.015137180700094607,
"grad_norm": 5.156379484105855e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.017029328287606435,
"grad_norm": 4.9736248911358416e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.01892147587511826,
"grad_norm": 4.439418626134284e-05,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.020813623462630087,
"grad_norm": 3.578408359317109e-05,
"learning_rate": 9.999316524962345e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.02270577105014191,
"grad_norm": 4.5976918045198545e-05,
"learning_rate": 9.997266286704631e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.02459791863765374,
"grad_norm": 4.328038630774245e-05,
"learning_rate": 9.993849845741524e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.026490066225165563,
"grad_norm": 6.62132297293283e-05,
"learning_rate": 9.989068136093873e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.02838221381267739,
"grad_norm": 4.295597682357766e-05,
"learning_rate": 9.98292246503335e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.030274361400189215,
"grad_norm": 5.483837958308868e-05,
"learning_rate": 9.975414512725057e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.03216650898770104,
"grad_norm": 5.1548016926972196e-05,
"learning_rate": 9.966546331768191e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.03405865657521287,
"grad_norm": 5.622395110549405e-05,
"learning_rate": 9.956320346634876e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.03595080416272469,
"grad_norm": 5.4803811508463696e-05,
"learning_rate": 9.944739353007344e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.03784295175023652,
"grad_norm": 5.92364594922401e-05,
"learning_rate": 9.931806517013612e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.039735099337748346,
"grad_norm": 3.621938230935484e-05,
"learning_rate": 9.917525374361912e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.041627246925260174,
"grad_norm": 6.96440038154833e-05,
"learning_rate": 9.901899829374047e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.043519394512771994,
"grad_norm": 5.8083074691239744e-05,
"learning_rate": 9.884934153917997e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.04541154210028382,
"grad_norm": 6.714474875479937e-05,
"learning_rate": 9.86663298624003e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.04730368968779565,
"grad_norm": 5.7245619245804846e-05,
"learning_rate": 9.847001329696653e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.04919583727530748,
"grad_norm": 8.519292896380648e-05,
"learning_rate": 9.826044551386744e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.0510879848628193,
"grad_norm": 6.0471407778095454e-05,
"learning_rate": 9.803768380684242e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.052980132450331126,
"grad_norm": 8.57353734318167e-05,
"learning_rate": 9.780178907671789e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.05487228003784295,
"grad_norm": 6.721801037201658e-05,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.05676442762535478,
"grad_norm": 4.0291612094733864e-05,
"learning_rate": 9.729086208503174e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.0586565752128666,
"grad_norm": 8.024101407499984e-05,
"learning_rate": 9.701596950580806e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.06054872280037843,
"grad_norm": 0.00010948763519991189,
"learning_rate": 9.672822322997305e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.06244087038789026,
"grad_norm": 9.849704656517133e-05,
"learning_rate": 9.642770192448536e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.06433301797540208,
"grad_norm": 0.0001186469744425267,
"learning_rate": 9.611448774886924e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.06622516556291391,
"grad_norm": 8.63405002746731e-05,
"learning_rate": 9.578866633275288e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.06811731315042574,
"grad_norm": 0.0001031709325616248,
"learning_rate": 9.545032675245813e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.07000946073793755,
"grad_norm": 8.092836651485413e-05,
"learning_rate": 9.509956150664796e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.07190160832544938,
"grad_norm": 0.00012377151870168746,
"learning_rate": 9.473646649103818e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.07379375591296121,
"grad_norm": 8.76743724802509e-05,
"learning_rate": 9.43611409721806e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.07568590350047304,
"grad_norm": 0.00011488812742754817,
"learning_rate": 9.397368756032445e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.07757805108798486,
"grad_norm": 0.00017331365961581469,
"learning_rate": 9.357421218136386e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.07947019867549669,
"grad_norm": 0.0001301294832956046,
"learning_rate": 9.316282404787871e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.08136234626300852,
"grad_norm": 0.000131969281937927,
"learning_rate": 9.273963562927695e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.08325449385052035,
"grad_norm": 0.00013541184307541698,
"learning_rate": 9.230476262104677e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.08514664143803216,
"grad_norm": 0.00013825498172082007,
"learning_rate": 9.185832391312644e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.08703878902554399,
"grad_norm": 0.00011591362999752164,
"learning_rate": 9.140044155740101e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.08893093661305582,
"grad_norm": 0.0001691806101007387,
"learning_rate": 9.093124073433463e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.09082308420056764,
"grad_norm": 0.0002150857326341793,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.09271523178807947,
"grad_norm": 0.0001261103170691058,
"learning_rate": 8.995939984474624e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.0946073793755913,
"grad_norm": 0.00012130875984439626,
"learning_rate": 8.945702546981969e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.0946073793755913,
"eval_loss": 11.5,
"eval_runtime": 4.0175,
"eval_samples_per_second": 221.531,
"eval_steps_per_second": 55.507,
"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": 8039615692800.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}