vdos's picture
Training in progress, step 50, checkpoint
cee1485 verified
{
"best_metric": 0.392264187335968,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.04747774480712166,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0009495548961424333,
"grad_norm": 7.7639288902282715,
"learning_rate": 5e-05,
"loss": 2.5959,
"step": 1
},
{
"epoch": 0.0009495548961424333,
"eval_loss": 4.306151866912842,
"eval_runtime": 91.9226,
"eval_samples_per_second": 77.184,
"eval_steps_per_second": 9.649,
"step": 1
},
{
"epoch": 0.0018991097922848666,
"grad_norm": 11.612013816833496,
"learning_rate": 0.0001,
"loss": 3.3436,
"step": 2
},
{
"epoch": 0.0028486646884273,
"grad_norm": 7.625513553619385,
"learning_rate": 9.989294616193017e-05,
"loss": 2.3691,
"step": 3
},
{
"epoch": 0.003798219584569733,
"grad_norm": 5.3779730796813965,
"learning_rate": 9.957224306869053e-05,
"loss": 1.5922,
"step": 4
},
{
"epoch": 0.004747774480712166,
"grad_norm": 3.9368231296539307,
"learning_rate": 9.903926402016153e-05,
"loss": 1.0797,
"step": 5
},
{
"epoch": 0.0056973293768546,
"grad_norm": 4.963187217712402,
"learning_rate": 9.829629131445342e-05,
"loss": 0.9303,
"step": 6
},
{
"epoch": 0.006646884272997033,
"grad_norm": 3.513078212738037,
"learning_rate": 9.73465064747553e-05,
"loss": 0.7227,
"step": 7
},
{
"epoch": 0.007596439169139466,
"grad_norm": 1.9068372249603271,
"learning_rate": 9.619397662556435e-05,
"loss": 0.5974,
"step": 8
},
{
"epoch": 0.0085459940652819,
"grad_norm": 1.931948184967041,
"learning_rate": 9.484363707663442e-05,
"loss": 0.624,
"step": 9
},
{
"epoch": 0.009495548961424332,
"grad_norm": 1.7695870399475098,
"learning_rate": 9.330127018922194e-05,
"loss": 0.5292,
"step": 10
},
{
"epoch": 0.010445103857566765,
"grad_norm": 1.3401875495910645,
"learning_rate": 9.157348061512727e-05,
"loss": 0.5026,
"step": 11
},
{
"epoch": 0.0113946587537092,
"grad_norm": 1.604765772819519,
"learning_rate": 8.966766701456177e-05,
"loss": 0.573,
"step": 12
},
{
"epoch": 0.012344213649851632,
"grad_norm": 1.3100688457489014,
"learning_rate": 8.759199037394887e-05,
"loss": 0.5107,
"step": 13
},
{
"epoch": 0.013293768545994065,
"grad_norm": 1.411363124847412,
"learning_rate": 8.535533905932738e-05,
"loss": 0.5638,
"step": 14
},
{
"epoch": 0.014243323442136498,
"grad_norm": 1.4153975248336792,
"learning_rate": 8.296729075500344e-05,
"loss": 0.6142,
"step": 15
},
{
"epoch": 0.015192878338278933,
"grad_norm": 1.2447761297225952,
"learning_rate": 8.043807145043604e-05,
"loss": 0.4627,
"step": 16
},
{
"epoch": 0.016142433234421365,
"grad_norm": 1.094689965248108,
"learning_rate": 7.777851165098012e-05,
"loss": 0.5305,
"step": 17
},
{
"epoch": 0.0170919881305638,
"grad_norm": 1.1024848222732544,
"learning_rate": 7.500000000000001e-05,
"loss": 0.5075,
"step": 18
},
{
"epoch": 0.01804154302670623,
"grad_norm": 0.9719968438148499,
"learning_rate": 7.211443451095007e-05,
"loss": 0.3903,
"step": 19
},
{
"epoch": 0.018991097922848664,
"grad_norm": 1.10643470287323,
"learning_rate": 6.91341716182545e-05,
"loss": 0.4737,
"step": 20
},
{
"epoch": 0.019940652818991097,
"grad_norm": 1.0399558544158936,
"learning_rate": 6.607197326515808e-05,
"loss": 0.4157,
"step": 21
},
{
"epoch": 0.02089020771513353,
"grad_norm": 1.028935194015503,
"learning_rate": 6.294095225512603e-05,
"loss": 0.3913,
"step": 22
},
{
"epoch": 0.021839762611275966,
"grad_norm": 1.307973861694336,
"learning_rate": 5.9754516100806423e-05,
"loss": 0.4277,
"step": 23
},
{
"epoch": 0.0227893175074184,
"grad_norm": 1.6136342287063599,
"learning_rate": 5.6526309611002594e-05,
"loss": 0.4724,
"step": 24
},
{
"epoch": 0.02373887240356083,
"grad_norm": 1.435404658317566,
"learning_rate": 5.327015646150716e-05,
"loss": 0.4427,
"step": 25
},
{
"epoch": 0.02373887240356083,
"eval_loss": 0.4159088730812073,
"eval_runtime": 91.609,
"eval_samples_per_second": 77.449,
"eval_steps_per_second": 9.682,
"step": 25
},
{
"epoch": 0.024688427299703265,
"grad_norm": 1.7106653451919556,
"learning_rate": 5e-05,
"loss": 0.4651,
"step": 26
},
{
"epoch": 0.025637982195845697,
"grad_norm": 1.322445273399353,
"learning_rate": 4.6729843538492847e-05,
"loss": 0.4095,
"step": 27
},
{
"epoch": 0.02658753709198813,
"grad_norm": 1.363024115562439,
"learning_rate": 4.347369038899744e-05,
"loss": 0.4447,
"step": 28
},
{
"epoch": 0.027537091988130563,
"grad_norm": 1.0911495685577393,
"learning_rate": 4.0245483899193595e-05,
"loss": 0.4959,
"step": 29
},
{
"epoch": 0.028486646884272996,
"grad_norm": 1.0770279169082642,
"learning_rate": 3.705904774487396e-05,
"loss": 0.4371,
"step": 30
},
{
"epoch": 0.02943620178041543,
"grad_norm": 1.1779959201812744,
"learning_rate": 3.392802673484193e-05,
"loss": 0.4116,
"step": 31
},
{
"epoch": 0.030385756676557865,
"grad_norm": 1.0283995866775513,
"learning_rate": 3.086582838174551e-05,
"loss": 0.3238,
"step": 32
},
{
"epoch": 0.031335311572700295,
"grad_norm": 1.1943073272705078,
"learning_rate": 2.7885565489049946e-05,
"loss": 0.4475,
"step": 33
},
{
"epoch": 0.03228486646884273,
"grad_norm": 1.43560791015625,
"learning_rate": 2.500000000000001e-05,
"loss": 0.4978,
"step": 34
},
{
"epoch": 0.03323442136498516,
"grad_norm": 1.288859486579895,
"learning_rate": 2.2221488349019903e-05,
"loss": 0.3934,
"step": 35
},
{
"epoch": 0.0341839762611276,
"grad_norm": 1.3092143535614014,
"learning_rate": 1.9561928549563968e-05,
"loss": 0.4076,
"step": 36
},
{
"epoch": 0.03513353115727003,
"grad_norm": 1.3240766525268555,
"learning_rate": 1.703270924499656e-05,
"loss": 0.4086,
"step": 37
},
{
"epoch": 0.03608308605341246,
"grad_norm": 0.9453262686729431,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.4139,
"step": 38
},
{
"epoch": 0.0370326409495549,
"grad_norm": 1.0400198698043823,
"learning_rate": 1.2408009626051137e-05,
"loss": 0.4421,
"step": 39
},
{
"epoch": 0.03798219584569733,
"grad_norm": 1.1390429735183716,
"learning_rate": 1.0332332985438248e-05,
"loss": 0.3825,
"step": 40
},
{
"epoch": 0.038931750741839764,
"grad_norm": 1.109674334526062,
"learning_rate": 8.426519384872733e-06,
"loss": 0.418,
"step": 41
},
{
"epoch": 0.039881305637982194,
"grad_norm": 1.0239107608795166,
"learning_rate": 6.698729810778065e-06,
"loss": 0.4396,
"step": 42
},
{
"epoch": 0.04083086053412463,
"grad_norm": 0.9508967399597168,
"learning_rate": 5.156362923365588e-06,
"loss": 0.4177,
"step": 43
},
{
"epoch": 0.04178041543026706,
"grad_norm": 0.9765400290489197,
"learning_rate": 3.8060233744356633e-06,
"loss": 0.4324,
"step": 44
},
{
"epoch": 0.042729970326409496,
"grad_norm": 1.0129822492599487,
"learning_rate": 2.653493525244721e-06,
"loss": 0.3481,
"step": 45
},
{
"epoch": 0.04367952522255193,
"grad_norm": 1.1066875457763672,
"learning_rate": 1.70370868554659e-06,
"loss": 0.4676,
"step": 46
},
{
"epoch": 0.04462908011869436,
"grad_norm": 0.9519398808479309,
"learning_rate": 9.607359798384785e-07,
"loss": 0.4375,
"step": 47
},
{
"epoch": 0.0455786350148368,
"grad_norm": 1.2050330638885498,
"learning_rate": 4.277569313094809e-07,
"loss": 0.3596,
"step": 48
},
{
"epoch": 0.04652818991097923,
"grad_norm": 1.1099382638931274,
"learning_rate": 1.0705383806982606e-07,
"loss": 0.4083,
"step": 49
},
{
"epoch": 0.04747774480712166,
"grad_norm": 1.1943883895874023,
"learning_rate": 0.0,
"loss": 0.4605,
"step": 50
},
{
"epoch": 0.04747774480712166,
"eval_loss": 0.392264187335968,
"eval_runtime": 91.633,
"eval_samples_per_second": 77.428,
"eval_steps_per_second": 9.68,
"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": 1.589463780163584e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}