jssky's picture
Training in progress, step 50, checkpoint
49206e0 verified
raw
history blame
10.2 kB
{
"best_metric": 0.4515899121761322,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.3329171868497711,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006658343736995423,
"grad_norm": 0.6766905784606934,
"learning_rate": 5e-05,
"loss": 0.5045,
"step": 1
},
{
"epoch": 0.006658343736995423,
"eval_loss": 0.7748587727546692,
"eval_runtime": 68.2989,
"eval_samples_per_second": 14.817,
"eval_steps_per_second": 1.859,
"step": 1
},
{
"epoch": 0.013316687473990845,
"grad_norm": 0.9477994441986084,
"learning_rate": 0.0001,
"loss": 0.601,
"step": 2
},
{
"epoch": 0.019975031210986267,
"grad_norm": 1.1717606782913208,
"learning_rate": 9.989294616193017e-05,
"loss": 0.6239,
"step": 3
},
{
"epoch": 0.02663337494798169,
"grad_norm": 1.6087969541549683,
"learning_rate": 9.957224306869053e-05,
"loss": 0.6256,
"step": 4
},
{
"epoch": 0.033291718684977115,
"grad_norm": 2.2669594287872314,
"learning_rate": 9.903926402016153e-05,
"loss": 0.6503,
"step": 5
},
{
"epoch": 0.039950062421972535,
"grad_norm": 2.2688164710998535,
"learning_rate": 9.829629131445342e-05,
"loss": 0.6151,
"step": 6
},
{
"epoch": 0.046608406158967955,
"grad_norm": 2.020754098892212,
"learning_rate": 9.73465064747553e-05,
"loss": 0.5776,
"step": 7
},
{
"epoch": 0.05326674989596338,
"grad_norm": 2.412825345993042,
"learning_rate": 9.619397662556435e-05,
"loss": 0.5873,
"step": 8
},
{
"epoch": 0.0599250936329588,
"grad_norm": 3.532561779022217,
"learning_rate": 9.484363707663442e-05,
"loss": 0.6026,
"step": 9
},
{
"epoch": 0.06658343736995423,
"grad_norm": 3.2861530780792236,
"learning_rate": 9.330127018922194e-05,
"loss": 0.6352,
"step": 10
},
{
"epoch": 0.07324178110694965,
"grad_norm": 3.0673956871032715,
"learning_rate": 9.157348061512727e-05,
"loss": 0.6631,
"step": 11
},
{
"epoch": 0.07990012484394507,
"grad_norm": 4.215164661407471,
"learning_rate": 8.966766701456177e-05,
"loss": 0.7748,
"step": 12
},
{
"epoch": 0.08655846858094049,
"grad_norm": 3.3592727184295654,
"learning_rate": 8.759199037394887e-05,
"loss": 0.6992,
"step": 13
},
{
"epoch": 0.09321681231793591,
"grad_norm": 1.4204148054122925,
"learning_rate": 8.535533905932738e-05,
"loss": 0.4338,
"step": 14
},
{
"epoch": 0.09987515605493133,
"grad_norm": 2.203651189804077,
"learning_rate": 8.296729075500344e-05,
"loss": 0.4438,
"step": 15
},
{
"epoch": 0.10653349979192676,
"grad_norm": 1.6005713939666748,
"learning_rate": 8.043807145043604e-05,
"loss": 0.4472,
"step": 16
},
{
"epoch": 0.11319184352892218,
"grad_norm": 1.6566606760025024,
"learning_rate": 7.777851165098012e-05,
"loss": 0.4457,
"step": 17
},
{
"epoch": 0.1198501872659176,
"grad_norm": 1.827477216720581,
"learning_rate": 7.500000000000001e-05,
"loss": 0.445,
"step": 18
},
{
"epoch": 0.12650853100291304,
"grad_norm": 1.4291009902954102,
"learning_rate": 7.211443451095007e-05,
"loss": 0.4475,
"step": 19
},
{
"epoch": 0.13316687473990846,
"grad_norm": 1.28583824634552,
"learning_rate": 6.91341716182545e-05,
"loss": 0.4522,
"step": 20
},
{
"epoch": 0.13982521847690388,
"grad_norm": 1.3042387962341309,
"learning_rate": 6.607197326515808e-05,
"loss": 0.4603,
"step": 21
},
{
"epoch": 0.1464835622138993,
"grad_norm": 1.6690038442611694,
"learning_rate": 6.294095225512603e-05,
"loss": 0.4664,
"step": 22
},
{
"epoch": 0.15314190595089472,
"grad_norm": 2.043731212615967,
"learning_rate": 5.9754516100806423e-05,
"loss": 0.5016,
"step": 23
},
{
"epoch": 0.15980024968789014,
"grad_norm": 3.2721598148345947,
"learning_rate": 5.6526309611002594e-05,
"loss": 0.6257,
"step": 24
},
{
"epoch": 0.16645859342488556,
"grad_norm": 6.480600833892822,
"learning_rate": 5.327015646150716e-05,
"loss": 0.8083,
"step": 25
},
{
"epoch": 0.16645859342488556,
"eval_loss": 0.4790324866771698,
"eval_runtime": 68.3057,
"eval_samples_per_second": 14.816,
"eval_steps_per_second": 1.859,
"step": 25
},
{
"epoch": 0.17311693716188098,
"grad_norm": 1.0460373163223267,
"learning_rate": 5e-05,
"loss": 0.3871,
"step": 26
},
{
"epoch": 0.1797752808988764,
"grad_norm": 1.1974306106567383,
"learning_rate": 4.6729843538492847e-05,
"loss": 0.3586,
"step": 27
},
{
"epoch": 0.18643362463587182,
"grad_norm": 1.1274254322052002,
"learning_rate": 4.347369038899744e-05,
"loss": 0.3886,
"step": 28
},
{
"epoch": 0.19309196837286724,
"grad_norm": 1.193386435508728,
"learning_rate": 4.0245483899193595e-05,
"loss": 0.4036,
"step": 29
},
{
"epoch": 0.19975031210986266,
"grad_norm": 1.0893070697784424,
"learning_rate": 3.705904774487396e-05,
"loss": 0.4003,
"step": 30
},
{
"epoch": 0.2064086558468581,
"grad_norm": 1.2256414890289307,
"learning_rate": 3.392802673484193e-05,
"loss": 0.3774,
"step": 31
},
{
"epoch": 0.21306699958385353,
"grad_norm": 1.1129382848739624,
"learning_rate": 3.086582838174551e-05,
"loss": 0.4126,
"step": 32
},
{
"epoch": 0.21972534332084895,
"grad_norm": 1.1873247623443604,
"learning_rate": 2.7885565489049946e-05,
"loss": 0.4491,
"step": 33
},
{
"epoch": 0.22638368705784437,
"grad_norm": 1.3507243394851685,
"learning_rate": 2.500000000000001e-05,
"loss": 0.4582,
"step": 34
},
{
"epoch": 0.2330420307948398,
"grad_norm": 1.5721896886825562,
"learning_rate": 2.2221488349019903e-05,
"loss": 0.4969,
"step": 35
},
{
"epoch": 0.2397003745318352,
"grad_norm": 2.0338633060455322,
"learning_rate": 1.9561928549563968e-05,
"loss": 0.5316,
"step": 36
},
{
"epoch": 0.24635871826883063,
"grad_norm": 2.7098116874694824,
"learning_rate": 1.703270924499656e-05,
"loss": 0.5699,
"step": 37
},
{
"epoch": 0.2530170620058261,
"grad_norm": 3.2819511890411377,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.5692,
"step": 38
},
{
"epoch": 0.2596754057428215,
"grad_norm": 0.6997650861740112,
"learning_rate": 1.2408009626051137e-05,
"loss": 0.3947,
"step": 39
},
{
"epoch": 0.2663337494798169,
"grad_norm": 0.7984439730644226,
"learning_rate": 1.0332332985438248e-05,
"loss": 0.395,
"step": 40
},
{
"epoch": 0.27299209321681234,
"grad_norm": 0.9441525936126709,
"learning_rate": 8.426519384872733e-06,
"loss": 0.3733,
"step": 41
},
{
"epoch": 0.27965043695380776,
"grad_norm": 0.9665208458900452,
"learning_rate": 6.698729810778065e-06,
"loss": 0.3955,
"step": 42
},
{
"epoch": 0.2863087806908032,
"grad_norm": 1.0408518314361572,
"learning_rate": 5.156362923365588e-06,
"loss": 0.3756,
"step": 43
},
{
"epoch": 0.2929671244277986,
"grad_norm": 1.1118501424789429,
"learning_rate": 3.8060233744356633e-06,
"loss": 0.4042,
"step": 44
},
{
"epoch": 0.299625468164794,
"grad_norm": 1.1715872287750244,
"learning_rate": 2.653493525244721e-06,
"loss": 0.3959,
"step": 45
},
{
"epoch": 0.30628381190178944,
"grad_norm": 1.1747242212295532,
"learning_rate": 1.70370868554659e-06,
"loss": 0.4306,
"step": 46
},
{
"epoch": 0.31294215563878486,
"grad_norm": 1.2841401100158691,
"learning_rate": 9.607359798384785e-07,
"loss": 0.4725,
"step": 47
},
{
"epoch": 0.3196004993757803,
"grad_norm": 2.1822011470794678,
"learning_rate": 4.277569313094809e-07,
"loss": 0.4955,
"step": 48
},
{
"epoch": 0.3262588431127757,
"grad_norm": 5.10789155960083,
"learning_rate": 1.0705383806982606e-07,
"loss": 0.5343,
"step": 49
},
{
"epoch": 0.3329171868497711,
"grad_norm": 4.15449857711792,
"learning_rate": 0.0,
"loss": 0.7024,
"step": 50
},
{
"epoch": 0.3329171868497711,
"eval_loss": 0.4515899121761322,
"eval_runtime": 68.2577,
"eval_samples_per_second": 14.826,
"eval_steps_per_second": 1.861,
"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": 1.0234452164906844e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}