DeepDream2045's picture
Training in progress, step 50, checkpoint
1227668 verified
{
"best_metric": 10.3651704788208,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.024497045043941575,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0004899409008788315,
"grad_norm": 0.07435133308172226,
"learning_rate": 5e-05,
"loss": 10.3777,
"step": 1
},
{
"epoch": 0.0004899409008788315,
"eval_loss": 10.376495361328125,
"eval_runtime": 33.0382,
"eval_samples_per_second": 416.216,
"eval_steps_per_second": 52.031,
"step": 1
},
{
"epoch": 0.000979881801757663,
"grad_norm": 0.07061050087213516,
"learning_rate": 0.0001,
"loss": 10.3782,
"step": 2
},
{
"epoch": 0.0014698227026364945,
"grad_norm": 0.06603322178125381,
"learning_rate": 9.989294616193017e-05,
"loss": 10.3768,
"step": 3
},
{
"epoch": 0.001959763603515326,
"grad_norm": 0.07089418172836304,
"learning_rate": 9.957224306869053e-05,
"loss": 10.3754,
"step": 4
},
{
"epoch": 0.0024497045043941575,
"grad_norm": 0.06795217096805573,
"learning_rate": 9.903926402016153e-05,
"loss": 10.3757,
"step": 5
},
{
"epoch": 0.002939645405272989,
"grad_norm": 0.07028926908969879,
"learning_rate": 9.829629131445342e-05,
"loss": 10.3734,
"step": 6
},
{
"epoch": 0.0034295863061518206,
"grad_norm": 0.07632067054510117,
"learning_rate": 9.73465064747553e-05,
"loss": 10.3748,
"step": 7
},
{
"epoch": 0.003919527207030652,
"grad_norm": 0.07464627921581268,
"learning_rate": 9.619397662556435e-05,
"loss": 10.3739,
"step": 8
},
{
"epoch": 0.004409468107909483,
"grad_norm": 0.07415231317281723,
"learning_rate": 9.484363707663442e-05,
"loss": 10.3727,
"step": 9
},
{
"epoch": 0.004899409008788315,
"grad_norm": 0.08245952427387238,
"learning_rate": 9.330127018922194e-05,
"loss": 10.3724,
"step": 10
},
{
"epoch": 0.005389349909667146,
"grad_norm": 0.08654414117336273,
"learning_rate": 9.157348061512727e-05,
"loss": 10.3711,
"step": 11
},
{
"epoch": 0.005879290810545978,
"grad_norm": 0.08921003341674805,
"learning_rate": 8.966766701456177e-05,
"loss": 10.3739,
"step": 12
},
{
"epoch": 0.006369231711424809,
"grad_norm": 0.08911455422639847,
"learning_rate": 8.759199037394887e-05,
"loss": 10.3745,
"step": 13
},
{
"epoch": 0.006859172612303641,
"grad_norm": 0.08878596127033234,
"learning_rate": 8.535533905932738e-05,
"loss": 10.3732,
"step": 14
},
{
"epoch": 0.007349113513182472,
"grad_norm": 0.08633674681186676,
"learning_rate": 8.296729075500344e-05,
"loss": 10.374,
"step": 15
},
{
"epoch": 0.007839054414061304,
"grad_norm": 0.08906910568475723,
"learning_rate": 8.043807145043604e-05,
"loss": 10.3722,
"step": 16
},
{
"epoch": 0.008328995314940135,
"grad_norm": 0.0873604342341423,
"learning_rate": 7.777851165098012e-05,
"loss": 10.3702,
"step": 17
},
{
"epoch": 0.008818936215818966,
"grad_norm": 0.08805176615715027,
"learning_rate": 7.500000000000001e-05,
"loss": 10.3705,
"step": 18
},
{
"epoch": 0.009308877116697799,
"grad_norm": 0.10004222393035889,
"learning_rate": 7.211443451095007e-05,
"loss": 10.369,
"step": 19
},
{
"epoch": 0.00979881801757663,
"grad_norm": 0.09142635762691498,
"learning_rate": 6.91341716182545e-05,
"loss": 10.3695,
"step": 20
},
{
"epoch": 0.010288758918455461,
"grad_norm": 0.11121775954961777,
"learning_rate": 6.607197326515808e-05,
"loss": 10.3687,
"step": 21
},
{
"epoch": 0.010778699819334292,
"grad_norm": 0.11228284984827042,
"learning_rate": 6.294095225512603e-05,
"loss": 10.3694,
"step": 22
},
{
"epoch": 0.011268640720213125,
"grad_norm": 0.10820707678794861,
"learning_rate": 5.9754516100806423e-05,
"loss": 10.3684,
"step": 23
},
{
"epoch": 0.011758581621091956,
"grad_norm": 0.12054973840713501,
"learning_rate": 5.6526309611002594e-05,
"loss": 10.3698,
"step": 24
},
{
"epoch": 0.012248522521970787,
"grad_norm": 0.14238008856773376,
"learning_rate": 5.327015646150716e-05,
"loss": 10.3704,
"step": 25
},
{
"epoch": 0.012248522521970787,
"eval_loss": 10.368396759033203,
"eval_runtime": 31.2676,
"eval_samples_per_second": 439.785,
"eval_steps_per_second": 54.977,
"step": 25
},
{
"epoch": 0.012738463422849618,
"grad_norm": 0.12131338566541672,
"learning_rate": 5e-05,
"loss": 10.3703,
"step": 26
},
{
"epoch": 0.01322840432372845,
"grad_norm": 0.10950379073619843,
"learning_rate": 4.6729843538492847e-05,
"loss": 10.3681,
"step": 27
},
{
"epoch": 0.013718345224607282,
"grad_norm": 0.1175779178738594,
"learning_rate": 4.347369038899744e-05,
"loss": 10.3684,
"step": 28
},
{
"epoch": 0.014208286125486113,
"grad_norm": 0.11989858746528625,
"learning_rate": 4.0245483899193595e-05,
"loss": 10.3675,
"step": 29
},
{
"epoch": 0.014698227026364944,
"grad_norm": 0.11529122292995453,
"learning_rate": 3.705904774487396e-05,
"loss": 10.3677,
"step": 30
},
{
"epoch": 0.015188167927243775,
"grad_norm": 0.1135224774479866,
"learning_rate": 3.392802673484193e-05,
"loss": 10.3665,
"step": 31
},
{
"epoch": 0.01567810882812261,
"grad_norm": 0.1238592267036438,
"learning_rate": 3.086582838174551e-05,
"loss": 10.365,
"step": 32
},
{
"epoch": 0.01616804972900144,
"grad_norm": 0.13364364206790924,
"learning_rate": 2.7885565489049946e-05,
"loss": 10.3664,
"step": 33
},
{
"epoch": 0.01665799062988027,
"grad_norm": 0.13014760613441467,
"learning_rate": 2.500000000000001e-05,
"loss": 10.3635,
"step": 34
},
{
"epoch": 0.0171479315307591,
"grad_norm": 0.13167224824428558,
"learning_rate": 2.2221488349019903e-05,
"loss": 10.3663,
"step": 35
},
{
"epoch": 0.017637872431637933,
"grad_norm": 0.14532671868801117,
"learning_rate": 1.9561928549563968e-05,
"loss": 10.3636,
"step": 36
},
{
"epoch": 0.018127813332516764,
"grad_norm": 0.14160360395908356,
"learning_rate": 1.703270924499656e-05,
"loss": 10.3645,
"step": 37
},
{
"epoch": 0.018617754233395598,
"grad_norm": 0.1375637799501419,
"learning_rate": 1.4644660940672627e-05,
"loss": 10.3681,
"step": 38
},
{
"epoch": 0.01910769513427443,
"grad_norm": 0.12385618686676025,
"learning_rate": 1.2408009626051137e-05,
"loss": 10.3669,
"step": 39
},
{
"epoch": 0.01959763603515326,
"grad_norm": 0.13332408666610718,
"learning_rate": 1.0332332985438248e-05,
"loss": 10.3649,
"step": 40
},
{
"epoch": 0.02008757693603209,
"grad_norm": 0.13181282579898834,
"learning_rate": 8.426519384872733e-06,
"loss": 10.3666,
"step": 41
},
{
"epoch": 0.020577517836910923,
"grad_norm": 0.13302215933799744,
"learning_rate": 6.698729810778065e-06,
"loss": 10.3654,
"step": 42
},
{
"epoch": 0.021067458737789754,
"grad_norm": 0.1286499947309494,
"learning_rate": 5.156362923365588e-06,
"loss": 10.3634,
"step": 43
},
{
"epoch": 0.021557399638668585,
"grad_norm": 0.14264312386512756,
"learning_rate": 3.8060233744356633e-06,
"loss": 10.3635,
"step": 44
},
{
"epoch": 0.022047340539547416,
"grad_norm": 0.14282181859016418,
"learning_rate": 2.653493525244721e-06,
"loss": 10.3655,
"step": 45
},
{
"epoch": 0.02253728144042625,
"grad_norm": 0.1369328647851944,
"learning_rate": 1.70370868554659e-06,
"loss": 10.3652,
"step": 46
},
{
"epoch": 0.02302722234130508,
"grad_norm": 0.1347339153289795,
"learning_rate": 9.607359798384785e-07,
"loss": 10.3637,
"step": 47
},
{
"epoch": 0.023517163242183912,
"grad_norm": 0.13543902337551117,
"learning_rate": 4.277569313094809e-07,
"loss": 10.3645,
"step": 48
},
{
"epoch": 0.024007104143062744,
"grad_norm": 0.15400274097919464,
"learning_rate": 1.0705383806982606e-07,
"loss": 10.3637,
"step": 49
},
{
"epoch": 0.024497045043941575,
"grad_norm": 0.16417399048805237,
"learning_rate": 0.0,
"loss": 10.3647,
"step": 50
},
{
"epoch": 0.024497045043941575,
"eval_loss": 10.3651704788208,
"eval_runtime": 30.4468,
"eval_samples_per_second": 451.64,
"eval_steps_per_second": 56.459,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 42768059596800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}