RoyJoy's picture
Training in progress, step 50, checkpoint
2a336de verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.15293442936341045,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003058688587268209,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 38.4578,
"step": 1
},
{
"epoch": 0.003058688587268209,
"eval_loss": NaN,
"eval_runtime": 64.0693,
"eval_samples_per_second": 34.385,
"eval_steps_per_second": 4.308,
"step": 1
},
{
"epoch": 0.006117377174536418,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.009176065761804627,
"grad_norm": NaN,
"learning_rate": 9.989294616193017e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.012234754349072835,
"grad_norm": NaN,
"learning_rate": 9.957224306869053e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.015293442936341044,
"grad_norm": NaN,
"learning_rate": 9.903926402016153e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.018352131523609254,
"grad_norm": NaN,
"learning_rate": 9.829629131445342e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.02141082011087746,
"grad_norm": NaN,
"learning_rate": 9.73465064747553e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.02446950869814567,
"grad_norm": NaN,
"learning_rate": 9.619397662556435e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.027528197285413877,
"grad_norm": NaN,
"learning_rate": 9.484363707663442e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.030586885872682087,
"grad_norm": NaN,
"learning_rate": 9.330127018922194e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.0336455744599503,
"grad_norm": NaN,
"learning_rate": 9.157348061512727e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.03670426304721851,
"grad_norm": NaN,
"learning_rate": 8.966766701456177e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.03976295163448671,
"grad_norm": NaN,
"learning_rate": 8.759199037394887e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.04282164022175492,
"grad_norm": NaN,
"learning_rate": 8.535533905932738e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.04588032880902313,
"grad_norm": NaN,
"learning_rate": 8.296729075500344e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.04893901739629134,
"grad_norm": NaN,
"learning_rate": 8.043807145043604e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.05199770598355955,
"grad_norm": NaN,
"learning_rate": 7.777851165098012e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.055056394570827755,
"grad_norm": NaN,
"learning_rate": 7.500000000000001e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.058115083158095965,
"grad_norm": NaN,
"learning_rate": 7.211443451095007e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.061173771745364175,
"grad_norm": NaN,
"learning_rate": 6.91341716182545e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.06423246033263239,
"grad_norm": NaN,
"learning_rate": 6.607197326515808e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.0672911489199006,
"grad_norm": NaN,
"learning_rate": 6.294095225512603e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.0703498375071688,
"grad_norm": NaN,
"learning_rate": 5.9754516100806423e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.07340852609443702,
"grad_norm": NaN,
"learning_rate": 5.6526309611002594e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.07646721468170523,
"grad_norm": NaN,
"learning_rate": 5.327015646150716e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.07646721468170523,
"eval_loss": NaN,
"eval_runtime": 64.1454,
"eval_samples_per_second": 34.344,
"eval_steps_per_second": 4.303,
"step": 25
},
{
"epoch": 0.07952590326897342,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.08258459185624163,
"grad_norm": NaN,
"learning_rate": 4.6729843538492847e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.08564328044350984,
"grad_norm": NaN,
"learning_rate": 4.347369038899744e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.08870196903077805,
"grad_norm": NaN,
"learning_rate": 4.0245483899193595e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.09176065761804626,
"grad_norm": NaN,
"learning_rate": 3.705904774487396e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.09481934620531447,
"grad_norm": NaN,
"learning_rate": 3.392802673484193e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.09787803479258268,
"grad_norm": NaN,
"learning_rate": 3.086582838174551e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.10093672337985089,
"grad_norm": NaN,
"learning_rate": 2.7885565489049946e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.1039954119671191,
"grad_norm": NaN,
"learning_rate": 2.500000000000001e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.10705410055438731,
"grad_norm": NaN,
"learning_rate": 2.2221488349019903e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.11011278914165551,
"grad_norm": NaN,
"learning_rate": 1.9561928549563968e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.11317147772892372,
"grad_norm": NaN,
"learning_rate": 1.703270924499656e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.11623016631619193,
"grad_norm": NaN,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.11928885490346014,
"grad_norm": NaN,
"learning_rate": 1.2408009626051137e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.12234754349072835,
"grad_norm": NaN,
"learning_rate": 1.0332332985438248e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.12540623207799656,
"grad_norm": NaN,
"learning_rate": 8.426519384872733e-06,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.12846492066526477,
"grad_norm": NaN,
"learning_rate": 6.698729810778065e-06,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.13152360925253298,
"grad_norm": NaN,
"learning_rate": 5.156362923365588e-06,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.1345822978398012,
"grad_norm": NaN,
"learning_rate": 3.8060233744356633e-06,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.1376409864270694,
"grad_norm": NaN,
"learning_rate": 2.653493525244721e-06,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.1406996750143376,
"grad_norm": NaN,
"learning_rate": 1.70370868554659e-06,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.14375836360160582,
"grad_norm": NaN,
"learning_rate": 9.607359798384785e-07,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.14681705218887403,
"grad_norm": NaN,
"learning_rate": 4.277569313094809e-07,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.14987574077614224,
"grad_norm": NaN,
"learning_rate": 1.0705383806982606e-07,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.15293442936341045,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.15293442936341045,
"eval_loss": NaN,
"eval_runtime": 63.6494,
"eval_samples_per_second": 34.611,
"eval_steps_per_second": 4.336,
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.4412321768236646e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}