bbytxt's picture
Training in progress, step 50, checkpoint
d92d90d verified
raw
history blame
9.92 kB
{
"best_metric": 0.006671774201095104,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.08064516129032258,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0016129032258064516,
"grad_norm": 0.6049064993858337,
"learning_rate": 1e-05,
"loss": 0.9039,
"step": 1
},
{
"epoch": 0.0016129032258064516,
"eval_loss": 0.7379059195518494,
"eval_runtime": 106.5243,
"eval_samples_per_second": 9.801,
"eval_steps_per_second": 2.45,
"step": 1
},
{
"epoch": 0.0032258064516129032,
"grad_norm": 0.7415255904197693,
"learning_rate": 2e-05,
"loss": 1.1299,
"step": 2
},
{
"epoch": 0.004838709677419355,
"grad_norm": 0.8382638692855835,
"learning_rate": 3e-05,
"loss": 1.2151,
"step": 3
},
{
"epoch": 0.0064516129032258064,
"grad_norm": 0.862156331539154,
"learning_rate": 4e-05,
"loss": 1.2969,
"step": 4
},
{
"epoch": 0.008064516129032258,
"grad_norm": 0.9778095483779907,
"learning_rate": 5e-05,
"loss": 1.2646,
"step": 5
},
{
"epoch": 0.00967741935483871,
"grad_norm": 0.9458996057510376,
"learning_rate": 6e-05,
"loss": 1.2015,
"step": 6
},
{
"epoch": 0.01129032258064516,
"grad_norm": 0.981987476348877,
"learning_rate": 7e-05,
"loss": 1.0207,
"step": 7
},
{
"epoch": 0.012903225806451613,
"grad_norm": 0.8597192764282227,
"learning_rate": 8e-05,
"loss": 0.7901,
"step": 8
},
{
"epoch": 0.014516129032258065,
"grad_norm": 0.9466065764427185,
"learning_rate": 9e-05,
"loss": 0.7297,
"step": 9
},
{
"epoch": 0.016129032258064516,
"grad_norm": 1.1080763339996338,
"learning_rate": 0.0001,
"loss": 0.4713,
"step": 10
},
{
"epoch": 0.017741935483870968,
"grad_norm": 0.8401578068733215,
"learning_rate": 9.999316524962345e-05,
"loss": 0.2136,
"step": 11
},
{
"epoch": 0.01935483870967742,
"grad_norm": 0.9712587594985962,
"learning_rate": 9.997266286704631e-05,
"loss": 0.2193,
"step": 12
},
{
"epoch": 0.020967741935483872,
"grad_norm": 1.2566802501678467,
"learning_rate": 9.993849845741524e-05,
"loss": 0.2793,
"step": 13
},
{
"epoch": 0.02258064516129032,
"grad_norm": 0.9939321875572205,
"learning_rate": 9.989068136093873e-05,
"loss": 0.1432,
"step": 14
},
{
"epoch": 0.024193548387096774,
"grad_norm": 1.6880418062210083,
"learning_rate": 9.98292246503335e-05,
"loss": 0.1768,
"step": 15
},
{
"epoch": 0.025806451612903226,
"grad_norm": 1.028950810432434,
"learning_rate": 9.975414512725057e-05,
"loss": 0.1185,
"step": 16
},
{
"epoch": 0.027419354838709678,
"grad_norm": 0.7586027383804321,
"learning_rate": 9.966546331768191e-05,
"loss": 0.0659,
"step": 17
},
{
"epoch": 0.02903225806451613,
"grad_norm": 0.9536590576171875,
"learning_rate": 9.956320346634876e-05,
"loss": 0.072,
"step": 18
},
{
"epoch": 0.03064516129032258,
"grad_norm": 0.7935003638267517,
"learning_rate": 9.944739353007344e-05,
"loss": 0.0533,
"step": 19
},
{
"epoch": 0.03225806451612903,
"grad_norm": 0.9564946293830872,
"learning_rate": 9.931806517013612e-05,
"loss": 0.0539,
"step": 20
},
{
"epoch": 0.03387096774193549,
"grad_norm": 0.6796997785568237,
"learning_rate": 9.917525374361912e-05,
"loss": 0.0269,
"step": 21
},
{
"epoch": 0.035483870967741936,
"grad_norm": 1.2710872888565063,
"learning_rate": 9.901899829374047e-05,
"loss": 0.1013,
"step": 22
},
{
"epoch": 0.037096774193548385,
"grad_norm": 0.5349439382553101,
"learning_rate": 9.884934153917997e-05,
"loss": 0.0248,
"step": 23
},
{
"epoch": 0.03870967741935484,
"grad_norm": 1.372443437576294,
"learning_rate": 9.86663298624003e-05,
"loss": 0.1846,
"step": 24
},
{
"epoch": 0.04032258064516129,
"grad_norm": 0.7447899580001831,
"learning_rate": 9.847001329696653e-05,
"loss": 0.0277,
"step": 25
},
{
"epoch": 0.041935483870967745,
"grad_norm": 0.2933860719203949,
"learning_rate": 9.826044551386744e-05,
"loss": 0.0103,
"step": 26
},
{
"epoch": 0.043548387096774194,
"grad_norm": 1.2192440032958984,
"learning_rate": 9.803768380684242e-05,
"loss": 0.0694,
"step": 27
},
{
"epoch": 0.04516129032258064,
"grad_norm": 1.3143314123153687,
"learning_rate": 9.780178907671789e-05,
"loss": 0.0395,
"step": 28
},
{
"epoch": 0.0467741935483871,
"grad_norm": 0.8509743213653564,
"learning_rate": 9.755282581475769e-05,
"loss": 0.1224,
"step": 29
},
{
"epoch": 0.04838709677419355,
"grad_norm": 0.9023564457893372,
"learning_rate": 9.729086208503174e-05,
"loss": 0.0558,
"step": 30
},
{
"epoch": 0.05,
"grad_norm": 0.3841659128665924,
"learning_rate": 9.701596950580806e-05,
"loss": 0.0202,
"step": 31
},
{
"epoch": 0.05161290322580645,
"grad_norm": 2.0831139087677,
"learning_rate": 9.672822322997305e-05,
"loss": 0.0486,
"step": 32
},
{
"epoch": 0.0532258064516129,
"grad_norm": 0.3329290747642517,
"learning_rate": 9.642770192448536e-05,
"loss": 0.0155,
"step": 33
},
{
"epoch": 0.054838709677419356,
"grad_norm": 0.3646816313266754,
"learning_rate": 9.611448774886924e-05,
"loss": 0.0219,
"step": 34
},
{
"epoch": 0.056451612903225805,
"grad_norm": 0.5079269409179688,
"learning_rate": 9.578866633275288e-05,
"loss": 0.0392,
"step": 35
},
{
"epoch": 0.05806451612903226,
"grad_norm": 1.1356701850891113,
"learning_rate": 9.545032675245813e-05,
"loss": 0.0314,
"step": 36
},
{
"epoch": 0.05967741935483871,
"grad_norm": 0.7165648341178894,
"learning_rate": 9.509956150664796e-05,
"loss": 0.0622,
"step": 37
},
{
"epoch": 0.06129032258064516,
"grad_norm": 0.9975515604019165,
"learning_rate": 9.473646649103818e-05,
"loss": 0.0386,
"step": 38
},
{
"epoch": 0.06290322580645161,
"grad_norm": 0.5520864725112915,
"learning_rate": 9.43611409721806e-05,
"loss": 0.0421,
"step": 39
},
{
"epoch": 0.06451612903225806,
"grad_norm": 0.6942296028137207,
"learning_rate": 9.397368756032445e-05,
"loss": 0.0219,
"step": 40
},
{
"epoch": 0.06612903225806452,
"grad_norm": 1.3481652736663818,
"learning_rate": 9.357421218136386e-05,
"loss": 0.143,
"step": 41
},
{
"epoch": 0.06774193548387097,
"grad_norm": 2.7365214824676514,
"learning_rate": 9.316282404787871e-05,
"loss": 0.0288,
"step": 42
},
{
"epoch": 0.06935483870967742,
"grad_norm": 0.2986465394496918,
"learning_rate": 9.273963562927695e-05,
"loss": 0.0081,
"step": 43
},
{
"epoch": 0.07096774193548387,
"grad_norm": 0.42408058047294617,
"learning_rate": 9.230476262104677e-05,
"loss": 0.013,
"step": 44
},
{
"epoch": 0.07258064516129033,
"grad_norm": 1.1357313394546509,
"learning_rate": 9.185832391312644e-05,
"loss": 0.0186,
"step": 45
},
{
"epoch": 0.07419354838709677,
"grad_norm": 0.9855334162712097,
"learning_rate": 9.140044155740101e-05,
"loss": 0.0275,
"step": 46
},
{
"epoch": 0.07580645161290323,
"grad_norm": 0.14201870560646057,
"learning_rate": 9.093124073433463e-05,
"loss": 0.0036,
"step": 47
},
{
"epoch": 0.07741935483870968,
"grad_norm": 1.7319813966751099,
"learning_rate": 9.045084971874738e-05,
"loss": 0.0958,
"step": 48
},
{
"epoch": 0.07903225806451612,
"grad_norm": 1.869276523590088,
"learning_rate": 8.995939984474624e-05,
"loss": 0.0504,
"step": 49
},
{
"epoch": 0.08064516129032258,
"grad_norm": 1.4869447946548462,
"learning_rate": 8.945702546981969e-05,
"loss": 0.0542,
"step": 50
},
{
"epoch": 0.08064516129032258,
"eval_loss": 0.006671774201095104,
"eval_runtime": 107.2911,
"eval_samples_per_second": 9.731,
"eval_steps_per_second": 2.433,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"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": 1.27296891518976e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}