dada22231's picture
Training in progress, step 25, checkpoint
6aad028 verified
raw
history blame
5.7 kB
{
"best_metric": 1.9105955362319946,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.3896736483195324,
"eval_steps": 25,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015586945932781296,
"grad_norm": 4.672861576080322,
"learning_rate": 3.3333333333333335e-05,
"loss": 7.3735,
"step": 1
},
{
"epoch": 0.015586945932781296,
"eval_loss": 8.586258888244629,
"eval_runtime": 4.3877,
"eval_samples_per_second": 11.396,
"eval_steps_per_second": 2.963,
"step": 1
},
{
"epoch": 0.031173891865562593,
"grad_norm": 4.721737384796143,
"learning_rate": 6.666666666666667e-05,
"loss": 7.4148,
"step": 2
},
{
"epoch": 0.046760837798343884,
"grad_norm": 4.43408203125,
"learning_rate": 0.0001,
"loss": 7.3302,
"step": 3
},
{
"epoch": 0.062347783731125185,
"grad_norm": 5.233772277832031,
"learning_rate": 9.997376600647783e-05,
"loss": 7.292,
"step": 4
},
{
"epoch": 0.07793472966390648,
"grad_norm": 5.694525718688965,
"learning_rate": 9.989509461357426e-05,
"loss": 5.9594,
"step": 5
},
{
"epoch": 0.09352167559668777,
"grad_norm": 6.35297966003418,
"learning_rate": 9.976407754861426e-05,
"loss": 5.2993,
"step": 6
},
{
"epoch": 0.10910862152946907,
"grad_norm": 6.337783336639404,
"learning_rate": 9.958086757163489e-05,
"loss": 4.2888,
"step": 7
},
{
"epoch": 0.12469556746225037,
"grad_norm": 4.447816371917725,
"learning_rate": 9.934567829727386e-05,
"loss": 3.478,
"step": 8
},
{
"epoch": 0.14028251339503167,
"grad_norm": 3.0322201251983643,
"learning_rate": 9.905878394570453e-05,
"loss": 2.7919,
"step": 9
},
{
"epoch": 0.15586945932781296,
"grad_norm": 2.2088980674743652,
"learning_rate": 9.872051902290737e-05,
"loss": 2.6674,
"step": 10
},
{
"epoch": 0.17145640526059425,
"grad_norm": 2.5988996028900146,
"learning_rate": 9.833127793065098e-05,
"loss": 2.7471,
"step": 11
},
{
"epoch": 0.18704335119337553,
"grad_norm": 2.1028494834899902,
"learning_rate": 9.789151450663723e-05,
"loss": 2.4486,
"step": 12
},
{
"epoch": 0.20263029712615685,
"grad_norm": 2.0794572830200195,
"learning_rate": 9.740174149534693e-05,
"loss": 2.2257,
"step": 13
},
{
"epoch": 0.21821724305893814,
"grad_norm": 2.3253426551818848,
"learning_rate": 9.686252995020249e-05,
"loss": 2.0009,
"step": 14
},
{
"epoch": 0.23380418899171942,
"grad_norm": 2.1563546657562256,
"learning_rate": 9.627450856774539e-05,
"loss": 2.0154,
"step": 15
},
{
"epoch": 0.24939113492450074,
"grad_norm": 2.201171875,
"learning_rate": 9.563836295460398e-05,
"loss": 2.1214,
"step": 16
},
{
"epoch": 0.26497808085728203,
"grad_norm": 2.189023494720459,
"learning_rate": 9.495483482810688e-05,
"loss": 2.1833,
"step": 17
},
{
"epoch": 0.28056502679006334,
"grad_norm": 1.9457616806030273,
"learning_rate": 9.422472115147382e-05,
"loss": 2.173,
"step": 18
},
{
"epoch": 0.2961519727228446,
"grad_norm": 1.6344696283340454,
"learning_rate": 9.3448873204592e-05,
"loss": 1.9725,
"step": 19
},
{
"epoch": 0.3117389186556259,
"grad_norm": 1.5604714155197144,
"learning_rate": 9.2628195591462e-05,
"loss": 1.828,
"step": 20
},
{
"epoch": 0.32732586458840723,
"grad_norm": 1.8877439498901367,
"learning_rate": 9.176364518546989e-05,
"loss": 2.1535,
"step": 21
},
{
"epoch": 0.3429128105211885,
"grad_norm": 1.4603512287139893,
"learning_rate": 9.08562300137157e-05,
"loss": 2.0067,
"step": 22
},
{
"epoch": 0.3584997564539698,
"grad_norm": 1.745575189590454,
"learning_rate": 8.990700808169889e-05,
"loss": 2.2415,
"step": 23
},
{
"epoch": 0.37408670238675107,
"grad_norm": 1.5076897144317627,
"learning_rate": 8.891708613973126e-05,
"loss": 1.9426,
"step": 24
},
{
"epoch": 0.3896736483195324,
"grad_norm": 1.871128797531128,
"learning_rate": 8.788761839251559e-05,
"loss": 1.9749,
"step": 25
},
{
"epoch": 0.3896736483195324,
"eval_loss": 1.9105955362319946,
"eval_runtime": 4.4309,
"eval_samples_per_second": 11.284,
"eval_steps_per_second": 2.934,
"step": 25
}
],
"logging_steps": 1,
"max_steps": 95,
"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": false
},
"attributes": {}
}
},
"total_flos": 1.327074698592256e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}