grids / r256_s2_lr5e-4 /trainer_state.json
Linksome's picture
Upload folder using huggingface_hub
a4d48a7 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.32,
"grad_norm": 0.2739750300719972,
"learning_rate": 0.0,
"loss": 1.855,
"step": 1
},
{
"epoch": 0.64,
"grad_norm": 0.28054571111334337,
"learning_rate": 0.0005,
"loss": 1.9926,
"step": 2
},
{
"epoch": 0.96,
"grad_norm": 2.128401802524351,
"learning_rate": 0.0004991893270335525,
"loss": 2.1933,
"step": 3
},
{
"epoch": 1.0,
"grad_norm": 2.128401802524351,
"learning_rate": 0.0004967625656594782,
"loss": 1.9076,
"step": 4
},
{
"epoch": 1.32,
"grad_norm": 3.0309462475893536,
"learning_rate": 0.000492735454356513,
"loss": 2.9948,
"step": 5
},
{
"epoch": 1.6400000000000001,
"grad_norm": 91.22732083476453,
"learning_rate": 0.00048713411048678635,
"loss": 8.0886,
"step": 6
},
{
"epoch": 1.96,
"grad_norm": 47.878206615403805,
"learning_rate": 0.0004799948609147061,
"loss": 7.5137,
"step": 7
},
{
"epoch": 2.0,
"grad_norm": 47.878206615403805,
"learning_rate": 0.00047136400641330245,
"loss": 4.1529,
"step": 8
},
{
"epoch": 2.32,
"grad_norm": 286.0201825414575,
"learning_rate": 0.00046129752138594874,
"loss": 5.9446,
"step": 9
},
{
"epoch": 2.64,
"grad_norm": 341.5398969396347,
"learning_rate": 0.0004498606908508753,
"loss": 11.244,
"step": 10
},
{
"epoch": 2.96,
"grad_norm": 37.42447637462269,
"learning_rate": 0.00043712768704277526,
"loss": 8.9972,
"step": 11
},
{
"epoch": 3.0,
"grad_norm": 37.42447637462269,
"learning_rate": 0.00042318108837739987,
"loss": 8.798,
"step": 12
},
{
"epoch": 3.32,
"grad_norm": 55.03031576723723,
"learning_rate": 0.0004081113438988443,
"loss": 8.901,
"step": 13
},
{
"epoch": 3.64,
"grad_norm": 8.430975912747524,
"learning_rate": 0.00039201618668278893,
"loss": 8.9821,
"step": 14
},
{
"epoch": 3.96,
"grad_norm": 2.8223996050275173,
"learning_rate": 0.000375,
"loss": 8.6843,
"step": 15
},
{
"epoch": 4.0,
"grad_norm": 2.8223996050275173,
"learning_rate": 0.0003571731403507635,
"loss": 8.696,
"step": 16
},
{
"epoch": 4.32,
"grad_norm": 48.46357587372076,
"learning_rate": 0.0003386512217606339,
"loss": 8.7265,
"step": 17
},
{
"epoch": 4.64,
"grad_norm": 41.92887751754919,
"learning_rate": 0.00031955436597911317,
"loss": 9.009,
"step": 18
},
{
"epoch": 4.96,
"grad_norm": 31.758319122148464,
"learning_rate": 0.00030000642344401115,
"loss": 8.5,
"step": 19
},
{
"epoch": 5.0,
"grad_norm": 31.758319122148464,
"learning_rate": 0.0002801341700638307,
"loss": 8.2996,
"step": 20
},
{
"epoch": 5.32,
"grad_norm": 14.70128239828777,
"learning_rate": 0.0002600664850273538,
"loss": 8.3669,
"step": 21
},
{
"epoch": 5.64,
"grad_norm": 17.809781006607658,
"learning_rate": 0.0002399335149726463,
"loss": 8.6131,
"step": 22
},
{
"epoch": 5.96,
"grad_norm": 11.697416261652242,
"learning_rate": 0.00021986582993616926,
"loss": 8.2586,
"step": 23
},
{
"epoch": 6.0,
"grad_norm": 11.697416261652242,
"learning_rate": 0.00019999357655598894,
"loss": 8.1573,
"step": 24
},
{
"epoch": 6.32,
"grad_norm": 12.853034613280684,
"learning_rate": 0.00018044563402088684,
"loss": 8.2205,
"step": 25
},
{
"epoch": 6.64,
"grad_norm": 6.4199413534358145,
"learning_rate": 0.00016134877823936609,
"loss": 8.4759,
"step": 26
},
{
"epoch": 6.96,
"grad_norm": 3.3744459037974504,
"learning_rate": 0.00014282685964923643,
"loss": 8.1023,
"step": 27
},
{
"epoch": 7.0,
"grad_norm": 3.3744459037974504,
"learning_rate": 0.00012500000000000006,
"loss": 8.0367,
"step": 28
},
{
"epoch": 7.32,
"grad_norm": 17.76532346028763,
"learning_rate": 0.00010798381331721108,
"loss": 8.1026,
"step": 29
},
{
"epoch": 7.64,
"grad_norm": 2.8184601832950373,
"learning_rate": 9.18886561011557e-05,
"loss": 8.4163,
"step": 30
},
{
"epoch": 7.96,
"grad_norm": 10.061170313334989,
"learning_rate": 7.681891162260016e-05,
"loss": 8.0483,
"step": 31
},
{
"epoch": 8.0,
"grad_norm": 14.574560195962805,
"learning_rate": 6.28723129572247e-05,
"loss": 7.9823,
"step": 32
},
{
"epoch": 8.32,
"grad_norm": 2.124022308154106,
"learning_rate": 5.013930914912476e-05,
"loss": 8.0492,
"step": 33
},
{
"epoch": 8.64,
"grad_norm": 7.035805426335321,
"learning_rate": 3.870247861405135e-05,
"loss": 8.3445,
"step": 34
},
{
"epoch": 8.96,
"grad_norm": 10.748904334153226,
"learning_rate": 2.863599358669755e-05,
"loss": 8.0001,
"step": 35
},
{
"epoch": 9.0,
"grad_norm": 10.748904334153226,
"learning_rate": 2.0005139085293944e-05,
"loss": 7.924,
"step": 36
},
{
"epoch": 9.32,
"grad_norm": 18.923553673811107,
"learning_rate": 1.286588951321363e-05,
"loss": 8.0395,
"step": 37
},
{
"epoch": 9.64,
"grad_norm": 6.648663278570519,
"learning_rate": 7.2645456434869975e-06,
"loss": 8.3189,
"step": 38
},
{
"epoch": 9.96,
"grad_norm": 5.5105350833590965,
"learning_rate": 3.2374343405217886e-06,
"loss": 7.9682,
"step": 39
},
{
"epoch": 10.0,
"grad_norm": 5.5105350833590965,
"learning_rate": 8.106729664475177e-07,
"loss": 7.9127,
"step": 40
},
{
"epoch": 10.0,
"step": 40,
"total_flos": 16141963493376.0,
"train_loss": 7.470467883348465,
"train_runtime": 1715.6348,
"train_samples_per_second": 0.577,
"train_steps_per_second": 0.023
}
],
"logging_steps": 1,
"max_steps": 40,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 16141963493376.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}