prxy5606's picture
Training in progress, step 50, checkpoint
9772adf verified
raw
history blame
9.95 kB
{
"best_metric": 1.254024863243103,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.1718213058419244,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003436426116838488,
"grad_norm": 0.39795026183128357,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.1706,
"step": 1
},
{
"epoch": 0.003436426116838488,
"eval_loss": 1.394996166229248,
"eval_runtime": 41.1487,
"eval_samples_per_second": 11.908,
"eval_steps_per_second": 5.954,
"step": 1
},
{
"epoch": 0.006872852233676976,
"grad_norm": 0.43744540214538574,
"learning_rate": 6.666666666666667e-06,
"loss": 1.217,
"step": 2
},
{
"epoch": 0.010309278350515464,
"grad_norm": 0.45329102873802185,
"learning_rate": 1e-05,
"loss": 1.2021,
"step": 3
},
{
"epoch": 0.013745704467353952,
"grad_norm": 0.47084182500839233,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.235,
"step": 4
},
{
"epoch": 0.01718213058419244,
"grad_norm": 0.4676068127155304,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.27,
"step": 5
},
{
"epoch": 0.020618556701030927,
"grad_norm": 0.4271283447742462,
"learning_rate": 2e-05,
"loss": 1.1783,
"step": 6
},
{
"epoch": 0.024054982817869417,
"grad_norm": 0.4685676395893097,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.2112,
"step": 7
},
{
"epoch": 0.027491408934707903,
"grad_norm": 0.434590220451355,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.1869,
"step": 8
},
{
"epoch": 0.030927835051546393,
"grad_norm": 0.44050467014312744,
"learning_rate": 3e-05,
"loss": 1.2167,
"step": 9
},
{
"epoch": 0.03436426116838488,
"grad_norm": 0.3955245316028595,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.1806,
"step": 10
},
{
"epoch": 0.037800687285223365,
"grad_norm": 0.3721248507499695,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.1545,
"step": 11
},
{
"epoch": 0.041237113402061855,
"grad_norm": 0.31409817934036255,
"learning_rate": 4e-05,
"loss": 1.2273,
"step": 12
},
{
"epoch": 0.044673539518900345,
"grad_norm": 0.29699209332466125,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.1168,
"step": 13
},
{
"epoch": 0.048109965635738834,
"grad_norm": 0.2954188585281372,
"learning_rate": 4.666666666666667e-05,
"loss": 1.2048,
"step": 14
},
{
"epoch": 0.05154639175257732,
"grad_norm": 0.2993329167366028,
"learning_rate": 5e-05,
"loss": 1.1181,
"step": 15
},
{
"epoch": 0.054982817869415807,
"grad_norm": 0.28740134835243225,
"learning_rate": 5.333333333333333e-05,
"loss": 1.1234,
"step": 16
},
{
"epoch": 0.058419243986254296,
"grad_norm": 0.31010302901268005,
"learning_rate": 5.666666666666667e-05,
"loss": 1.2198,
"step": 17
},
{
"epoch": 0.061855670103092786,
"grad_norm": 0.30725136399269104,
"learning_rate": 6e-05,
"loss": 1.1898,
"step": 18
},
{
"epoch": 0.06529209621993128,
"grad_norm": 0.26591724157333374,
"learning_rate": 6.333333333333333e-05,
"loss": 1.2076,
"step": 19
},
{
"epoch": 0.06872852233676977,
"grad_norm": 0.25425398349761963,
"learning_rate": 6.666666666666667e-05,
"loss": 1.1782,
"step": 20
},
{
"epoch": 0.07216494845360824,
"grad_norm": 0.25563672184944153,
"learning_rate": 7e-05,
"loss": 1.102,
"step": 21
},
{
"epoch": 0.07560137457044673,
"grad_norm": 0.2525363564491272,
"learning_rate": 7.333333333333333e-05,
"loss": 1.1132,
"step": 22
},
{
"epoch": 0.07903780068728522,
"grad_norm": 0.27992483973503113,
"learning_rate": 7.666666666666667e-05,
"loss": 1.1971,
"step": 23
},
{
"epoch": 0.08247422680412371,
"grad_norm": 0.24994660913944244,
"learning_rate": 8e-05,
"loss": 1.1438,
"step": 24
},
{
"epoch": 0.0859106529209622,
"grad_norm": 0.27021530270576477,
"learning_rate": 8.333333333333334e-05,
"loss": 1.2105,
"step": 25
},
{
"epoch": 0.08934707903780069,
"grad_norm": 0.26155591011047363,
"learning_rate": 8.666666666666667e-05,
"loss": 1.2296,
"step": 26
},
{
"epoch": 0.09278350515463918,
"grad_norm": 0.25747400522232056,
"learning_rate": 9e-05,
"loss": 1.1667,
"step": 27
},
{
"epoch": 0.09621993127147767,
"grad_norm": 0.25319820642471313,
"learning_rate": 9.333333333333334e-05,
"loss": 1.262,
"step": 28
},
{
"epoch": 0.09965635738831616,
"grad_norm": 0.26420244574546814,
"learning_rate": 9.666666666666667e-05,
"loss": 1.2049,
"step": 29
},
{
"epoch": 0.10309278350515463,
"grad_norm": 0.25196051597595215,
"learning_rate": 0.0001,
"loss": 1.1626,
"step": 30
},
{
"epoch": 0.10652920962199312,
"grad_norm": 0.2579573690891266,
"learning_rate": 9.994965332706573e-05,
"loss": 1.2421,
"step": 31
},
{
"epoch": 0.10996563573883161,
"grad_norm": 0.24934573471546173,
"learning_rate": 9.979871469976196e-05,
"loss": 1.1968,
"step": 32
},
{
"epoch": 0.1134020618556701,
"grad_norm": 0.2536607086658478,
"learning_rate": 9.954748808839674e-05,
"loss": 1.1794,
"step": 33
},
{
"epoch": 0.11683848797250859,
"grad_norm": 0.2625012695789337,
"learning_rate": 9.919647942993148e-05,
"loss": 1.1416,
"step": 34
},
{
"epoch": 0.12027491408934708,
"grad_norm": 0.257440447807312,
"learning_rate": 9.874639560909117e-05,
"loss": 1.2098,
"step": 35
},
{
"epoch": 0.12371134020618557,
"grad_norm": 0.2822026014328003,
"learning_rate": 9.819814303479267e-05,
"loss": 1.1966,
"step": 36
},
{
"epoch": 0.12714776632302405,
"grad_norm": 0.27574318647384644,
"learning_rate": 9.755282581475769e-05,
"loss": 1.2154,
"step": 37
},
{
"epoch": 0.13058419243986255,
"grad_norm": 0.27795401215553284,
"learning_rate": 9.681174353198687e-05,
"loss": 1.1431,
"step": 38
},
{
"epoch": 0.13402061855670103,
"grad_norm": 0.26681026816368103,
"learning_rate": 9.597638862757255e-05,
"loss": 1.1735,
"step": 39
},
{
"epoch": 0.13745704467353953,
"grad_norm": 0.2776302397251129,
"learning_rate": 9.504844339512095e-05,
"loss": 1.24,
"step": 40
},
{
"epoch": 0.140893470790378,
"grad_norm": 0.3019616901874542,
"learning_rate": 9.40297765928369e-05,
"loss": 1.201,
"step": 41
},
{
"epoch": 0.14432989690721648,
"grad_norm": 0.291785329580307,
"learning_rate": 9.292243968009331e-05,
"loss": 1.1569,
"step": 42
},
{
"epoch": 0.14776632302405499,
"grad_norm": 0.29259058833122253,
"learning_rate": 9.172866268606513e-05,
"loss": 1.1203,
"step": 43
},
{
"epoch": 0.15120274914089346,
"grad_norm": 0.31598636507987976,
"learning_rate": 9.045084971874738e-05,
"loss": 1.2352,
"step": 44
},
{
"epoch": 0.15463917525773196,
"grad_norm": 0.3215610086917877,
"learning_rate": 8.90915741234015e-05,
"loss": 1.1668,
"step": 45
},
{
"epoch": 0.15807560137457044,
"grad_norm": 0.3626932203769684,
"learning_rate": 8.765357330018056e-05,
"loss": 1.1811,
"step": 46
},
{
"epoch": 0.16151202749140894,
"grad_norm": 0.40073418617248535,
"learning_rate": 8.613974319136958e-05,
"loss": 1.2598,
"step": 47
},
{
"epoch": 0.16494845360824742,
"grad_norm": 0.39903056621551514,
"learning_rate": 8.455313244934324e-05,
"loss": 1.2176,
"step": 48
},
{
"epoch": 0.16838487972508592,
"grad_norm": 0.4395723342895508,
"learning_rate": 8.289693629698564e-05,
"loss": 1.2958,
"step": 49
},
{
"epoch": 0.1718213058419244,
"grad_norm": 0.479213684797287,
"learning_rate": 8.117449009293668e-05,
"loss": 1.2257,
"step": 50
},
{
"epoch": 0.1718213058419244,
"eval_loss": 1.254024863243103,
"eval_runtime": 41.6511,
"eval_samples_per_second": 11.764,
"eval_steps_per_second": 5.882,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 7.21793957536727e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}