lesso's picture
Training in progress, step 50, checkpoint
a970251 verified
raw
history blame
9.99 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 1.5037593984962405,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03007518796992481,
"grad_norm": 9.266636334359646e-05,
"learning_rate": 1.0100000000000002e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.03007518796992481,
"eval_loss": 11.5,
"eval_runtime": 0.3095,
"eval_samples_per_second": 1437.638,
"eval_steps_per_second": 45.229,
"step": 1
},
{
"epoch": 0.06015037593984962,
"grad_norm": 9.364843572257087e-05,
"learning_rate": 2.0200000000000003e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.09022556390977443,
"grad_norm": 0.00010662364365998656,
"learning_rate": 3.0299999999999998e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.12030075187969924,
"grad_norm": 9.021838195621967e-05,
"learning_rate": 4.0400000000000006e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.15037593984962405,
"grad_norm": 7.925021054688841e-05,
"learning_rate": 5.05e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.18045112781954886,
"grad_norm": 8.351929864147678e-05,
"learning_rate": 6.0599999999999996e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.21052631578947367,
"grad_norm": 9.711394523037598e-05,
"learning_rate": 7.07e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.24060150375939848,
"grad_norm": 9.60054385359399e-05,
"learning_rate": 8.080000000000001e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.2706766917293233,
"grad_norm": 0.00012731400784105062,
"learning_rate": 9.09e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.3007518796992481,
"grad_norm": 0.00011434268526500091,
"learning_rate": 0.000101,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.3308270676691729,
"grad_norm": 9.765291906660423e-05,
"learning_rate": 9.987777777777779e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.3609022556390977,
"grad_norm": 9.876976400846615e-05,
"learning_rate": 9.875555555555555e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.39097744360902253,
"grad_norm": 0.00011370878928573802,
"learning_rate": 9.763333333333334e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.42105263157894735,
"grad_norm": 0.0001137641811510548,
"learning_rate": 9.651111111111111e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.45112781954887216,
"grad_norm": 0.0001710877986624837,
"learning_rate": 9.538888888888889e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.48120300751879697,
"grad_norm": 0.0001575473725097254,
"learning_rate": 9.426666666666668e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.5112781954887218,
"grad_norm": 0.0001343897165497765,
"learning_rate": 9.314444444444445e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.5413533834586466,
"grad_norm": 0.00015038810670375824,
"learning_rate": 9.202222222222223e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.00013464110088534653,
"learning_rate": 9.09e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.6015037593984962,
"grad_norm": 0.0001557513460284099,
"learning_rate": 8.977777777777778e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.631578947368421,
"grad_norm": 0.00022612961765844375,
"learning_rate": 8.865555555555555e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.6616541353383458,
"grad_norm": 0.00020132240024395287,
"learning_rate": 8.753333333333334e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.6917293233082706,
"grad_norm": 0.00018423757865093648,
"learning_rate": 8.641111111111111e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.7218045112781954,
"grad_norm": 0.00016721716383472085,
"learning_rate": 8.528888888888889e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.7518796992481203,
"grad_norm": 0.0001902187941595912,
"learning_rate": 8.416666666666668e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.7819548872180451,
"grad_norm": 0.00020407498232088983,
"learning_rate": 8.304444444444444e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.8120300751879699,
"grad_norm": 0.0002489977050572634,
"learning_rate": 8.192222222222222e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.8421052631578947,
"grad_norm": 0.00030909531051293015,
"learning_rate": 8.080000000000001e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.8721804511278195,
"grad_norm": 0.000234145627473481,
"learning_rate": 7.967777777777777e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.9022556390977443,
"grad_norm": 0.0002202718605985865,
"learning_rate": 7.855555555555556e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.9323308270676691,
"grad_norm": 0.0002214343985542655,
"learning_rate": 7.743333333333334e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.9624060150375939,
"grad_norm": 0.00025516573805361986,
"learning_rate": 7.631111111111111e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.9924812030075187,
"grad_norm": 0.00025323766749352217,
"learning_rate": 7.51888888888889e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 1.0225563909774436,
"grad_norm": 0.00027011558995582163,
"learning_rate": 7.406666666666666e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 1.0526315789473684,
"grad_norm": 0.0002727561804931611,
"learning_rate": 7.294444444444445e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 1.0827067669172932,
"grad_norm": 0.00034800541470758617,
"learning_rate": 7.182222222222222e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 1.112781954887218,
"grad_norm": 0.0003243626852054149,
"learning_rate": 7.07e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.0002872659242711961,
"learning_rate": 6.957777777777777e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 1.1729323308270676,
"grad_norm": 0.00030295943724922836,
"learning_rate": 6.845555555555556e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 1.2030075187969924,
"grad_norm": 0.00025122929946519434,
"learning_rate": 6.733333333333333e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 1.2330827067669172,
"grad_norm": 0.00027522369055077434,
"learning_rate": 6.621111111111111e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 1.263157894736842,
"grad_norm": 0.00043568338151089847,
"learning_rate": 6.50888888888889e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 1.2932330827067668,
"grad_norm": 0.0003823314909823239,
"learning_rate": 6.396666666666666e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 1.3233082706766917,
"grad_norm": 0.00034535420127213,
"learning_rate": 6.284444444444445e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 1.3533834586466165,
"grad_norm": 0.0003590960695873946,
"learning_rate": 6.172222222222223e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 1.3834586466165413,
"grad_norm": 0.00029228764469735324,
"learning_rate": 6.0599999999999996e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 1.413533834586466,
"grad_norm": 0.0002954736119136214,
"learning_rate": 5.9477777777777784e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 1.443609022556391,
"grad_norm": 0.0005244979402050376,
"learning_rate": 5.835555555555555e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 1.4736842105263157,
"grad_norm": 0.00042245551594533026,
"learning_rate": 5.723333333333333e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 1.5037593984962405,
"grad_norm": 0.00039055367233231664,
"learning_rate": 5.6111111111111114e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 1.5037593984962405,
"eval_loss": 11.5,
"eval_runtime": 0.305,
"eval_samples_per_second": 1458.84,
"eval_steps_per_second": 45.896,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"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": false
},
"attributes": {}
}
},
"total_flos": 64316925542400.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}