TracyTank's picture
Training in progress, step 50, checkpoint
8557200 verified
{
"best_metric": 0.9236457347869873,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 1.941747572815534,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.038834951456310676,
"grad_norm": 81.57666778564453,
"learning_rate": 5e-05,
"loss": 65.2999,
"step": 1
},
{
"epoch": 0.038834951456310676,
"eval_loss": 4.374122142791748,
"eval_runtime": 1.0736,
"eval_samples_per_second": 46.573,
"eval_steps_per_second": 12.109,
"step": 1
},
{
"epoch": 0.07766990291262135,
"grad_norm": 76.71562957763672,
"learning_rate": 0.0001,
"loss": 67.4241,
"step": 2
},
{
"epoch": 0.11650485436893204,
"grad_norm": 83.1052017211914,
"learning_rate": 9.990365154573717e-05,
"loss": 65.8555,
"step": 3
},
{
"epoch": 0.1553398058252427,
"grad_norm": 106.08079528808594,
"learning_rate": 9.961501876182148e-05,
"loss": 60.6198,
"step": 4
},
{
"epoch": 0.1941747572815534,
"grad_norm": 88.97116088867188,
"learning_rate": 9.913533761814537e-05,
"loss": 39.5446,
"step": 5
},
{
"epoch": 0.23300970873786409,
"grad_norm": 63.881900787353516,
"learning_rate": 9.846666218300807e-05,
"loss": 26.5183,
"step": 6
},
{
"epoch": 0.27184466019417475,
"grad_norm": 50.206546783447266,
"learning_rate": 9.761185582727977e-05,
"loss": 22.2245,
"step": 7
},
{
"epoch": 0.3106796116504854,
"grad_norm": 39.16106033325195,
"learning_rate": 9.657457896300791e-05,
"loss": 21.4471,
"step": 8
},
{
"epoch": 0.34951456310679613,
"grad_norm": 57.89680862426758,
"learning_rate": 9.535927336897098e-05,
"loss": 21.3461,
"step": 9
},
{
"epoch": 0.3883495145631068,
"grad_norm": 79.03782653808594,
"learning_rate": 9.397114317029975e-05,
"loss": 21.4476,
"step": 10
},
{
"epoch": 0.42718446601941745,
"grad_norm": 30.68959617614746,
"learning_rate": 9.241613255361455e-05,
"loss": 20.206,
"step": 11
},
{
"epoch": 0.46601941747572817,
"grad_norm": 26.674922943115234,
"learning_rate": 9.070090031310558e-05,
"loss": 20.3681,
"step": 12
},
{
"epoch": 0.5048543689320388,
"grad_norm": 21.133214950561523,
"learning_rate": 8.883279133655399e-05,
"loss": 19.7297,
"step": 13
},
{
"epoch": 0.5436893203883495,
"grad_norm": 25.70758819580078,
"learning_rate": 8.681980515339464e-05,
"loss": 18.2531,
"step": 14
},
{
"epoch": 0.5825242718446602,
"grad_norm": 29.906238555908203,
"learning_rate": 8.467056167950311e-05,
"loss": 18.1375,
"step": 15
},
{
"epoch": 0.6213592233009708,
"grad_norm": 20.696022033691406,
"learning_rate": 8.239426430539243e-05,
"loss": 19.0771,
"step": 16
},
{
"epoch": 0.6601941747572816,
"grad_norm": 17.145883560180664,
"learning_rate": 8.000066048588211e-05,
"loss": 17.3158,
"step": 17
},
{
"epoch": 0.6990291262135923,
"grad_norm": 9.157857894897461,
"learning_rate": 7.75e-05,
"loss": 18.6342,
"step": 18
},
{
"epoch": 0.7378640776699029,
"grad_norm": 20.948427200317383,
"learning_rate": 7.490299105985507e-05,
"loss": 18.246,
"step": 19
},
{
"epoch": 0.7766990291262136,
"grad_norm": 33.383487701416016,
"learning_rate": 7.222075445642904e-05,
"loss": 15.1743,
"step": 20
},
{
"epoch": 0.8155339805825242,
"grad_norm": 15.724166870117188,
"learning_rate": 6.946477593864228e-05,
"loss": 16.3248,
"step": 21
},
{
"epoch": 0.8543689320388349,
"grad_norm": 16.168956756591797,
"learning_rate": 6.664685702961344e-05,
"loss": 17.2484,
"step": 22
},
{
"epoch": 0.8932038834951457,
"grad_norm": 13.848753929138184,
"learning_rate": 6.377906449072578e-05,
"loss": 15.4465,
"step": 23
},
{
"epoch": 0.9320388349514563,
"grad_norm": 9.256131172180176,
"learning_rate": 6.087367864990233e-05,
"loss": 18.5114,
"step": 24
},
{
"epoch": 0.970873786407767,
"grad_norm": 13.819438934326172,
"learning_rate": 5.794314081535644e-05,
"loss": 17.9887,
"step": 25
},
{
"epoch": 0.970873786407767,
"eval_loss": 0.9972949028015137,
"eval_runtime": 1.0585,
"eval_samples_per_second": 47.238,
"eval_steps_per_second": 12.282,
"step": 25
},
{
"epoch": 1.0097087378640777,
"grad_norm": 25.719419479370117,
"learning_rate": 5.500000000000001e-05,
"loss": 16.4112,
"step": 26
},
{
"epoch": 1.0485436893203883,
"grad_norm": 29.739490509033203,
"learning_rate": 5.205685918464356e-05,
"loss": 13.7014,
"step": 27
},
{
"epoch": 1.087378640776699,
"grad_norm": 34.622406005859375,
"learning_rate": 4.912632135009769e-05,
"loss": 14.9217,
"step": 28
},
{
"epoch": 1.1262135922330097,
"grad_norm": 30.102741241455078,
"learning_rate": 4.6220935509274235e-05,
"loss": 17.4172,
"step": 29
},
{
"epoch": 1.1650485436893203,
"grad_norm": 11.93884563446045,
"learning_rate": 4.3353142970386564e-05,
"loss": 14.4702,
"step": 30
},
{
"epoch": 1.203883495145631,
"grad_norm": 6.051325798034668,
"learning_rate": 4.053522406135775e-05,
"loss": 18.1343,
"step": 31
},
{
"epoch": 1.2427184466019416,
"grad_norm": 21.685884475708008,
"learning_rate": 3.777924554357096e-05,
"loss": 18.9043,
"step": 32
},
{
"epoch": 1.2815533980582523,
"grad_norm": 103.92913055419922,
"learning_rate": 3.509700894014496e-05,
"loss": 17.5716,
"step": 33
},
{
"epoch": 1.3203883495145632,
"grad_norm": 41.143226623535156,
"learning_rate": 3.250000000000001e-05,
"loss": 16.5813,
"step": 34
},
{
"epoch": 1.3592233009708738,
"grad_norm": 13.322393417358398,
"learning_rate": 2.9999339514117912e-05,
"loss": 17.0534,
"step": 35
},
{
"epoch": 1.3980582524271845,
"grad_norm": 26.480480194091797,
"learning_rate": 2.760573569460757e-05,
"loss": 14.6343,
"step": 36
},
{
"epoch": 1.4368932038834952,
"grad_norm": 4.912123680114746,
"learning_rate": 2.53294383204969e-05,
"loss": 17.8308,
"step": 37
},
{
"epoch": 1.4757281553398058,
"grad_norm": 7.7494282722473145,
"learning_rate": 2.3180194846605367e-05,
"loss": 18.1934,
"step": 38
},
{
"epoch": 1.5145631067961165,
"grad_norm": 28.394657135009766,
"learning_rate": 2.1167208663446025e-05,
"loss": 15.4537,
"step": 39
},
{
"epoch": 1.5533980582524272,
"grad_norm": 29.47159767150879,
"learning_rate": 1.9299099686894423e-05,
"loss": 12.7481,
"step": 40
},
{
"epoch": 1.5922330097087378,
"grad_norm": 23.724668502807617,
"learning_rate": 1.758386744638546e-05,
"loss": 16.9,
"step": 41
},
{
"epoch": 1.6310679611650487,
"grad_norm": 23.437341690063477,
"learning_rate": 1.602885682970026e-05,
"loss": 15.56,
"step": 42
},
{
"epoch": 1.6699029126213594,
"grad_norm": 17.16952133178711,
"learning_rate": 1.464072663102903e-05,
"loss": 16.7025,
"step": 43
},
{
"epoch": 1.70873786407767,
"grad_norm": 16.27042579650879,
"learning_rate": 1.3425421036992098e-05,
"loss": 17.9029,
"step": 44
},
{
"epoch": 1.7475728155339807,
"grad_norm": 16.81924057006836,
"learning_rate": 1.2388144172720251e-05,
"loss": 14.544,
"step": 45
},
{
"epoch": 1.7864077669902914,
"grad_norm": 17.303743362426758,
"learning_rate": 1.1533337816991932e-05,
"loss": 11.5598,
"step": 46
},
{
"epoch": 1.825242718446602,
"grad_norm": 24.92502212524414,
"learning_rate": 1.0864662381854632e-05,
"loss": 15.3898,
"step": 47
},
{
"epoch": 1.8640776699029127,
"grad_norm": 12.400360107421875,
"learning_rate": 1.0384981238178534e-05,
"loss": 16.3068,
"step": 48
},
{
"epoch": 1.9029126213592233,
"grad_norm": 11.315818786621094,
"learning_rate": 1.0096348454262845e-05,
"loss": 16.1665,
"step": 49
},
{
"epoch": 1.941747572815534,
"grad_norm": 8.587471961975098,
"learning_rate": 1e-05,
"loss": 17.7138,
"step": 50
},
{
"epoch": 1.941747572815534,
"eval_loss": 0.9236457347869873,
"eval_runtime": 1.0598,
"eval_samples_per_second": 47.178,
"eval_steps_per_second": 12.266,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 2.967137622687744e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}