arcwarden46's picture
Training in progress, step 50, checkpoint
929349a verified
raw
history blame
9.99 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.029394473838918283,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005878894767783657,
"grad_norm": 1.2049655197188258e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.0005878894767783657,
"eval_loss": 11.5,
"eval_runtime": 14.6823,
"eval_samples_per_second": 195.133,
"eval_steps_per_second": 48.834,
"step": 1
},
{
"epoch": 0.0011757789535567313,
"grad_norm": 1.823827733460348e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.001763668430335097,
"grad_norm": 2.4213779397541657e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.0023515579071134627,
"grad_norm": 1.0648317584127653e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.0029394473838918285,
"grad_norm": 1.3218937056080904e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.003527336860670194,
"grad_norm": 1.2285052434890531e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.00411522633744856,
"grad_norm": 1.5408370018121786e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.004703115814226925,
"grad_norm": 1.0934895726677496e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.005291005291005291,
"grad_norm": 1.4163848391035572e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.005878894767783657,
"grad_norm": 1.3702650903724134e-05,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.006466784244562022,
"grad_norm": 1.6521877114428207e-05,
"learning_rate": 9.999316524962345e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.007054673721340388,
"grad_norm": 2.2343438104144298e-05,
"learning_rate": 9.997266286704631e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.007642563198118754,
"grad_norm": 2.0393068552948534e-05,
"learning_rate": 9.993849845741524e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.00823045267489712,
"grad_norm": 2.3643553504371084e-05,
"learning_rate": 9.989068136093873e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.008818342151675485,
"grad_norm": 2.0201492588967085e-05,
"learning_rate": 9.98292246503335e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.00940623162845385,
"grad_norm": 2.733259134402033e-05,
"learning_rate": 9.975414512725057e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.009994121105232217,
"grad_norm": 2.66439383267425e-05,
"learning_rate": 9.966546331768191e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.010582010582010581,
"grad_norm": 2.4708726414246485e-05,
"learning_rate": 9.956320346634876e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.011169900058788948,
"grad_norm": 3.3240445191040635e-05,
"learning_rate": 9.944739353007344e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.011757789535567314,
"grad_norm": 3.116807056358084e-05,
"learning_rate": 9.931806517013612e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.012345679012345678,
"grad_norm": 2.70261152763851e-05,
"learning_rate": 9.917525374361912e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.012933568489124045,
"grad_norm": 3.885727346641943e-05,
"learning_rate": 9.901899829374047e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.01352145796590241,
"grad_norm": 2.9568360332632437e-05,
"learning_rate": 9.884934153917997e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.014109347442680775,
"grad_norm": 2.813040373439435e-05,
"learning_rate": 9.86663298624003e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.014697236919459141,
"grad_norm": 4.1485443944111466e-05,
"learning_rate": 9.847001329696653e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.015285126396237508,
"grad_norm": 3.4513588616391644e-05,
"learning_rate": 9.826044551386744e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.015873015873015872,
"grad_norm": 3.281708632130176e-05,
"learning_rate": 9.803768380684242e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.01646090534979424,
"grad_norm": 4.911908399662934e-05,
"learning_rate": 9.780178907671789e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.017048794826572605,
"grad_norm": 5.5504242482129484e-05,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.01763668430335097,
"grad_norm": 6.484489858848974e-05,
"learning_rate": 9.729086208503174e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.018224573780129337,
"grad_norm": 5.0496259063947946e-05,
"learning_rate": 9.701596950580806e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.0188124632569077,
"grad_norm": 4.737185008707456e-05,
"learning_rate": 9.672822322997305e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.019400352733686066,
"grad_norm": 5.226164648775011e-05,
"learning_rate": 9.642770192448536e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.019988242210464434,
"grad_norm": 3.672628372441977e-05,
"learning_rate": 9.611448774886924e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.0205761316872428,
"grad_norm": 6.169499101815745e-05,
"learning_rate": 9.578866633275288e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.021164021164021163,
"grad_norm": 5.515438533620909e-05,
"learning_rate": 9.545032675245813e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.02175191064079953,
"grad_norm": 5.111669088364579e-05,
"learning_rate": 9.509956150664796e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.022339800117577895,
"grad_norm": 7.183753768913448e-05,
"learning_rate": 9.473646649103818e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.02292768959435626,
"grad_norm": 8.155861723935232e-05,
"learning_rate": 9.43611409721806e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.023515579071134628,
"grad_norm": 6.214533641468734e-05,
"learning_rate": 9.397368756032445e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.024103468547912992,
"grad_norm": 5.506568413693458e-05,
"learning_rate": 9.357421218136386e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.024691358024691357,
"grad_norm": 6.899887375766411e-05,
"learning_rate": 9.316282404787871e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.025279247501469725,
"grad_norm": 7.455835293512791e-05,
"learning_rate": 9.273963562927695e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.02586713697824809,
"grad_norm": 6.946162466192618e-05,
"learning_rate": 9.230476262104677e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.026455026455026454,
"grad_norm": 6.329041934804991e-05,
"learning_rate": 9.185832391312644e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.02704291593180482,
"grad_norm": 7.549597648903728e-05,
"learning_rate": 9.140044155740101e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.027630805408583186,
"grad_norm": 7.37153459340334e-05,
"learning_rate": 9.093124073433463e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.02821869488536155,
"grad_norm": 0.00010305437172064558,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.02880658436213992,
"grad_norm": 9.27174769458361e-05,
"learning_rate": 8.995939984474624e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.029394473838918283,
"grad_norm": 0.00013789732474833727,
"learning_rate": 8.945702546981969e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.029394473838918283,
"eval_loss": 11.5,
"eval_runtime": 14.6384,
"eval_samples_per_second": 195.718,
"eval_steps_per_second": 48.981,
"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": 9285756125184.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}