jssky's picture
Training in progress, step 50, checkpoint
7557879 verified
{
"best_metric": 5.9604641222676946e-08,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.18565792527268507,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0037131585054537017,
"grad_norm": 107.71508026123047,
"learning_rate": 5e-05,
"loss": 10.0429,
"step": 1
},
{
"epoch": 0.0037131585054537017,
"eval_loss": 10.04294490814209,
"eval_runtime": 73.7866,
"eval_samples_per_second": 24.598,
"eval_steps_per_second": 3.076,
"step": 1
},
{
"epoch": 0.0074263170109074034,
"grad_norm": 106.53510284423828,
"learning_rate": 0.0001,
"loss": 10.0429,
"step": 2
},
{
"epoch": 0.011139475516361104,
"grad_norm": 109.58079528808594,
"learning_rate": 9.989294616193017e-05,
"loss": 7.4162,
"step": 3
},
{
"epoch": 0.014852634021814807,
"grad_norm": 540.6641235351562,
"learning_rate": 9.957224306869053e-05,
"loss": 4.7977,
"step": 4
},
{
"epoch": 0.018565792527268508,
"grad_norm": 415.4353332519531,
"learning_rate": 9.903926402016153e-05,
"loss": 2.2481,
"step": 5
},
{
"epoch": 0.02227895103272221,
"grad_norm": 19.99170684814453,
"learning_rate": 9.829629131445342e-05,
"loss": 0.4043,
"step": 6
},
{
"epoch": 0.02599210953817591,
"grad_norm": 7.834036350250244,
"learning_rate": 9.73465064747553e-05,
"loss": 0.1081,
"step": 7
},
{
"epoch": 0.029705268043629614,
"grad_norm": 6.151876926422119,
"learning_rate": 9.619397662556435e-05,
"loss": 0.0412,
"step": 8
},
{
"epoch": 0.033418426549083315,
"grad_norm": 1.9499025344848633,
"learning_rate": 9.484363707663442e-05,
"loss": 0.0072,
"step": 9
},
{
"epoch": 0.037131585054537015,
"grad_norm": 0.19495820999145508,
"learning_rate": 9.330127018922194e-05,
"loss": 0.0011,
"step": 10
},
{
"epoch": 0.040844743559990716,
"grad_norm": 0.0696907564997673,
"learning_rate": 9.157348061512727e-05,
"loss": 0.0004,
"step": 11
},
{
"epoch": 0.04455790206544442,
"grad_norm": 0.02167157456278801,
"learning_rate": 8.966766701456177e-05,
"loss": 0.0001,
"step": 12
},
{
"epoch": 0.04827106057089812,
"grad_norm": 0.006874413695186377,
"learning_rate": 8.759199037394887e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.05198421907635182,
"grad_norm": 0.002045618835836649,
"learning_rate": 8.535533905932738e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.05569737758180553,
"grad_norm": 0.0006932233809493482,
"learning_rate": 8.296729075500344e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.05941053608725923,
"grad_norm": 0.0003306287690065801,
"learning_rate": 8.043807145043604e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.06312369459271293,
"grad_norm": 0.0002045152650680393,
"learning_rate": 7.777851165098012e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.06683685309816663,
"grad_norm": 0.0002016606304096058,
"learning_rate": 7.500000000000001e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.07055001160362033,
"grad_norm": 0.0004319296858739108,
"learning_rate": 7.211443451095007e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.07426317010907403,
"grad_norm": 0.0011289763497188687,
"learning_rate": 6.91341716182545e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.07797632861452773,
"grad_norm": 0.0035218556877225637,
"learning_rate": 6.607197326515808e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.08168948711998143,
"grad_norm": 0.0014450587332248688,
"learning_rate": 6.294095225512603e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.08540264562543513,
"grad_norm": 0.002081787446513772,
"learning_rate": 5.9754516100806423e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.08911580413088883,
"grad_norm": 0.0067098611034452915,
"learning_rate": 5.6526309611002594e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.09282896263634254,
"grad_norm": 0.013898885808885098,
"learning_rate": 5.327015646150716e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.09282896263634254,
"eval_loss": 1.6629419405944645e-05,
"eval_runtime": 73.7726,
"eval_samples_per_second": 24.603,
"eval_steps_per_second": 3.077,
"step": 25
},
{
"epoch": 0.09654212114179624,
"grad_norm": 0.004678704310208559,
"learning_rate": 5e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.10025527964724994,
"grad_norm": 0.009269794449210167,
"learning_rate": 4.6729843538492847e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.10396843815270364,
"grad_norm": 0.0021353906486183405,
"learning_rate": 4.347369038899744e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.10768159665815734,
"grad_norm": 0.0019365429179742932,
"learning_rate": 4.0245483899193595e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.11139475516361105,
"grad_norm": 0.001062785042449832,
"learning_rate": 3.705904774487396e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.11510791366906475,
"grad_norm": 0.007692957296967506,
"learning_rate": 3.392802673484193e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.11882107217451846,
"grad_norm": 0.0004157963558100164,
"learning_rate": 3.086582838174551e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.12253423067997216,
"grad_norm": 0.0002727754763327539,
"learning_rate": 2.7885565489049946e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.12624738918542586,
"grad_norm": 0.00023943185806274414,
"learning_rate": 2.500000000000001e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.12996054769087956,
"grad_norm": 8.647178765386343e-05,
"learning_rate": 2.2221488349019903e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.13367370619633326,
"grad_norm": 0.00021716480841860175,
"learning_rate": 1.9561928549563968e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.13738686470178696,
"grad_norm": 0.00011382108641555533,
"learning_rate": 1.703270924499656e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.14110002320724066,
"grad_norm": 7.642527634743601e-05,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.14481318171269436,
"grad_norm": 7.74165746406652e-05,
"learning_rate": 1.2408009626051137e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.14852634021814806,
"grad_norm": 3.6338700738269836e-05,
"learning_rate": 1.0332332985438248e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.15223949872360176,
"grad_norm": 3.927394936908968e-05,
"learning_rate": 8.426519384872733e-06,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.15595265722905546,
"grad_norm": 0.00011530683696037158,
"learning_rate": 6.698729810778065e-06,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.15966581573450916,
"grad_norm": 3.756599107873626e-05,
"learning_rate": 5.156362923365588e-06,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.16337897423996287,
"grad_norm": 9.324763232143596e-05,
"learning_rate": 3.8060233744356633e-06,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.16709213274541657,
"grad_norm": 4.730185173684731e-05,
"learning_rate": 2.653493525244721e-06,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.17080529125087027,
"grad_norm": 6.137853051768616e-05,
"learning_rate": 1.70370868554659e-06,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.17451844975632397,
"grad_norm": 2.7098336431663483e-05,
"learning_rate": 9.607359798384785e-07,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.17823160826177767,
"grad_norm": 7.346120401052758e-05,
"learning_rate": 4.277569313094809e-07,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.18194476676723137,
"grad_norm": 2.8820741135859862e-05,
"learning_rate": 1.0705383806982606e-07,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.18565792527268507,
"grad_norm": 4.6881395974196494e-05,
"learning_rate": 0.0,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.18565792527268507,
"eval_loss": 5.9604641222676946e-08,
"eval_runtime": 73.7395,
"eval_samples_per_second": 24.614,
"eval_steps_per_second": 3.078,
"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": 2.229252309123072e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}