{
"best_metric": 1.6293056011199951,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.14174344436569808,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002834868887313962,
"grad_norm": 82.76422119140625,
"learning_rate": 5e-05,
"loss": 2.6787,
"step": 1
},
{
"epoch": 0.002834868887313962,
"eval_loss": 2.6504859924316406,
"eval_runtime": 160.1175,
"eval_samples_per_second": 14.845,
"eval_steps_per_second": 1.861,
"step": 1
},
{
"epoch": 0.005669737774627924,
"grad_norm": 84.41320037841797,
"learning_rate": 0.0001,
"loss": 2.622,
"step": 2
},
{
"epoch": 0.008504606661941885,
"grad_norm": 55.366302490234375,
"learning_rate": 9.989294616193017e-05,
"loss": 2.3187,
"step": 3
},
{
"epoch": 0.011339475549255847,
"grad_norm": 138.09754943847656,
"learning_rate": 9.957224306869053e-05,
"loss": 2.3139,
"step": 4
},
{
"epoch": 0.014174344436569808,
"grad_norm": 59.256290435791016,
"learning_rate": 9.903926402016153e-05,
"loss": 2.0885,
"step": 5
},
{
"epoch": 0.01700921332388377,
"grad_norm": 36.487586975097656,
"learning_rate": 9.829629131445342e-05,
"loss": 1.9252,
"step": 6
},
{
"epoch": 0.019844082211197732,
"grad_norm": 28.441709518432617,
"learning_rate": 9.73465064747553e-05,
"loss": 1.9532,
"step": 7
},
{
"epoch": 0.022678951098511695,
"grad_norm": 26.23267936706543,
"learning_rate": 9.619397662556435e-05,
"loss": 1.8558,
"step": 8
},
{
"epoch": 0.025513819985825654,
"grad_norm": 27.839563369750977,
"learning_rate": 9.484363707663442e-05,
"loss": 1.806,
"step": 9
},
{
"epoch": 0.028348688873139617,
"grad_norm": 29.07710838317871,
"learning_rate": 9.330127018922194e-05,
"loss": 1.8041,
"step": 10
},
{
"epoch": 0.03118355776045358,
"grad_norm": 28.12234878540039,
"learning_rate": 9.157348061512727e-05,
"loss": 1.7231,
"step": 11
},
{
"epoch": 0.03401842664776754,
"grad_norm": 52.291473388671875,
"learning_rate": 8.966766701456177e-05,
"loss": 1.6255,
"step": 12
},
{
"epoch": 0.0368532955350815,
"grad_norm": 34.03739929199219,
"learning_rate": 8.759199037394887e-05,
"loss": 1.8048,
"step": 13
},
{
"epoch": 0.039688164422395464,
"grad_norm": 37.482479095458984,
"learning_rate": 8.535533905932738e-05,
"loss": 1.8117,
"step": 14
},
{
"epoch": 0.042523033309709427,
"grad_norm": 35.63401794433594,
"learning_rate": 8.296729075500344e-05,
"loss": 1.8129,
"step": 15
},
{
"epoch": 0.04535790219702339,
"grad_norm": 31.891372680664062,
"learning_rate": 8.043807145043604e-05,
"loss": 1.8834,
"step": 16
},
{
"epoch": 0.04819277108433735,
"grad_norm": 25.988798141479492,
"learning_rate": 7.777851165098012e-05,
"loss": 1.7296,
"step": 17
},
{
"epoch": 0.05102763997165131,
"grad_norm": 27.491472244262695,
"learning_rate": 7.500000000000001e-05,
"loss": 1.7901,
"step": 18
},
{
"epoch": 0.05386250885896527,
"grad_norm": 24.449907302856445,
"learning_rate": 7.211443451095007e-05,
"loss": 1.7715,
"step": 19
},
{
"epoch": 0.05669737774627923,
"grad_norm": 34.63983154296875,
"learning_rate": 6.91341716182545e-05,
"loss": 1.7285,
"step": 20
},
{
"epoch": 0.059532246633593196,
"grad_norm": 28.08819580078125,
"learning_rate": 6.607197326515808e-05,
"loss": 1.6562,
"step": 21
},
{
"epoch": 0.06236711552090716,
"grad_norm": 23.91188621520996,
"learning_rate": 6.294095225512603e-05,
"loss": 1.697,
"step": 22
},
{
"epoch": 0.06520198440822111,
"grad_norm": 24.417360305786133,
"learning_rate": 5.9754516100806423e-05,
"loss": 1.5958,
"step": 23
},
{
"epoch": 0.06803685329553508,
"grad_norm": 24.551523208618164,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.6066,
"step": 24
},
{
"epoch": 0.07087172218284904,
"grad_norm": 26.343568801879883,
"learning_rate": 5.327015646150716e-05,
"loss": 1.6065,
"step": 25
},
{
"epoch": 0.07087172218284904,
"eval_loss": 1.6741278171539307,
"eval_runtime": 160.0002,
"eval_samples_per_second": 14.856,
"eval_steps_per_second": 1.862,
"step": 25
},
{
"epoch": 0.073706591070163,
"grad_norm": 22.38184928894043,
"learning_rate": 5e-05,
"loss": 1.8156,
"step": 26
},
{
"epoch": 0.07654145995747696,
"grad_norm": 23.945520401000977,
"learning_rate": 4.6729843538492847e-05,
"loss": 1.7574,
"step": 27
},
{
"epoch": 0.07937632884479093,
"grad_norm": 23.31159782409668,
"learning_rate": 4.347369038899744e-05,
"loss": 1.7373,
"step": 28
},
{
"epoch": 0.08221119773210489,
"grad_norm": 25.977811813354492,
"learning_rate": 4.0245483899193595e-05,
"loss": 1.7842,
"step": 29
},
{
"epoch": 0.08504606661941885,
"grad_norm": 21.673782348632812,
"learning_rate": 3.705904774487396e-05,
"loss": 1.6762,
"step": 30
},
{
"epoch": 0.08788093550673282,
"grad_norm": 21.713336944580078,
"learning_rate": 3.392802673484193e-05,
"loss": 1.7385,
"step": 31
},
{
"epoch": 0.09071580439404678,
"grad_norm": 21.830078125,
"learning_rate": 3.086582838174551e-05,
"loss": 1.675,
"step": 32
},
{
"epoch": 0.09355067328136074,
"grad_norm": 21.631311416625977,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.6472,
"step": 33
},
{
"epoch": 0.0963855421686747,
"grad_norm": 27.561161041259766,
"learning_rate": 2.500000000000001e-05,
"loss": 1.6344,
"step": 34
},
{
"epoch": 0.09922041105598867,
"grad_norm": 21.6464900970459,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.5111,
"step": 35
},
{
"epoch": 0.10205527994330262,
"grad_norm": 22.276697158813477,
"learning_rate": 1.9561928549563968e-05,
"loss": 1.5228,
"step": 36
},
{
"epoch": 0.10489014883061658,
"grad_norm": 22.53538703918457,
"learning_rate": 1.703270924499656e-05,
"loss": 1.5246,
"step": 37
},
{
"epoch": 0.10772501771793054,
"grad_norm": 22.093549728393555,
"learning_rate": 1.4644660940672627e-05,
"loss": 1.6248,
"step": 38
},
{
"epoch": 0.1105598866052445,
"grad_norm": 20.847719192504883,
"learning_rate": 1.2408009626051137e-05,
"loss": 1.8001,
"step": 39
},
{
"epoch": 0.11339475549255847,
"grad_norm": 20.62337875366211,
"learning_rate": 1.0332332985438248e-05,
"loss": 1.6768,
"step": 40
},
{
"epoch": 0.11622962437987243,
"grad_norm": 22.74907875061035,
"learning_rate": 8.426519384872733e-06,
"loss": 1.6919,
"step": 41
},
{
"epoch": 0.11906449326718639,
"grad_norm": 20.205062866210938,
"learning_rate": 6.698729810778065e-06,
"loss": 1.6404,
"step": 42
},
{
"epoch": 0.12189936215450035,
"grad_norm": 23.588899612426758,
"learning_rate": 5.156362923365588e-06,
"loss": 1.7393,
"step": 43
},
{
"epoch": 0.12473423104181432,
"grad_norm": 21.78782081604004,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.6166,
"step": 44
},
{
"epoch": 0.12756909992912827,
"grad_norm": 21.997955322265625,
"learning_rate": 2.653493525244721e-06,
"loss": 1.5793,
"step": 45
},
{
"epoch": 0.13040396881644223,
"grad_norm": 22.398887634277344,
"learning_rate": 1.70370868554659e-06,
"loss": 1.5697,
"step": 46
},
{
"epoch": 0.1332388377037562,
"grad_norm": 22.767236709594727,
"learning_rate": 9.607359798384785e-07,
"loss": 1.5949,
"step": 47
},
{
"epoch": 0.13607370659107015,
"grad_norm": 23.64896583557129,
"learning_rate": 4.277569313094809e-07,
"loss": 1.5412,
"step": 48
},
{
"epoch": 0.13890857547838412,
"grad_norm": 23.149717330932617,
"learning_rate": 1.0705383806982606e-07,
"loss": 1.5032,
"step": 49
},
{
"epoch": 0.14174344436569808,
"grad_norm": 26.819599151611328,
"learning_rate": 0.0,
"loss": 1.4897,
"step": 50
},
{
"epoch": 0.14174344436569808,
"eval_loss": 1.6293056011199951,
"eval_runtime": 160.7258,
"eval_samples_per_second": 14.789,
"eval_steps_per_second": 1.854,
"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": 5.6721728367650406e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}