autoprogrammer's picture
Upload sdar_1.7b_multi_block_causal_math-checkpoint-174
040e341 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 174,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08733624454148471,
"grad_norm": 4.145501613616943,
"learning_rate": 6.666666666666667e-06,
"loss": 0.4128,
"step": 5
},
{
"epoch": 0.17467248908296942,
"grad_norm": 5.076199531555176,
"learning_rate": 9.992134075089085e-06,
"loss": 0.3862,
"step": 10
},
{
"epoch": 0.26200873362445415,
"grad_norm": 4.170598983764648,
"learning_rate": 9.944154131125643e-06,
"loss": 0.3491,
"step": 15
},
{
"epoch": 0.34934497816593885,
"grad_norm": 3.074150562286377,
"learning_rate": 9.852982837266955e-06,
"loss": 0.2981,
"step": 20
},
{
"epoch": 0.4366812227074236,
"grad_norm": 2.965071201324463,
"learning_rate": 9.719416651541839e-06,
"loss": 0.2567,
"step": 25
},
{
"epoch": 0.5240174672489083,
"grad_norm": 2.526233673095703,
"learning_rate": 9.544622387061055e-06,
"loss": 0.1965,
"step": 30
},
{
"epoch": 0.611353711790393,
"grad_norm": 2.4919331073760986,
"learning_rate": 9.330127018922195e-06,
"loss": 0.2105,
"step": 35
},
{
"epoch": 0.6986899563318777,
"grad_norm": 2.2303683757781982,
"learning_rate": 9.077804344796302e-06,
"loss": 0.1874,
"step": 40
},
{
"epoch": 0.7860262008733624,
"grad_norm": 2.2244021892547607,
"learning_rate": 8.789858615727266e-06,
"loss": 0.1631,
"step": 45
},
{
"epoch": 0.8733624454148472,
"grad_norm": 1.7161848545074463,
"learning_rate": 8.46880528014271e-06,
"loss": 0.1682,
"step": 50
},
{
"epoch": 0.9606986899563319,
"grad_norm": 2.00079083442688,
"learning_rate": 8.117449009293668e-06,
"loss": 0.1569,
"step": 55
},
{
"epoch": 1.034934497816594,
"grad_norm": 1.4984843730926514,
"learning_rate": 7.738859196089358e-06,
"loss": 0.1106,
"step": 60
},
{
"epoch": 1.1222707423580787,
"grad_norm": 1.579668402671814,
"learning_rate": 7.336343141365311e-06,
"loss": 0.0842,
"step": 65
},
{
"epoch": 1.2096069868995634,
"grad_norm": 1.8298442363739014,
"learning_rate": 6.913417161825449e-06,
"loss": 0.0686,
"step": 70
},
{
"epoch": 1.296943231441048,
"grad_norm": 2.102452516555786,
"learning_rate": 6.473775872054522e-06,
"loss": 0.0719,
"step": 75
},
{
"epoch": 1.3842794759825328,
"grad_norm": 2.2235753536224365,
"learning_rate": 6.0212599089484026e-06,
"loss": 0.0684,
"step": 80
},
{
"epoch": 1.4716157205240175,
"grad_norm": 2.161390781402588,
"learning_rate": 5.559822380516539e-06,
"loss": 0.0729,
"step": 85
},
{
"epoch": 1.5589519650655022,
"grad_norm": 1.6066176891326904,
"learning_rate": 5.093494332154511e-06,
"loss": 0.0714,
"step": 90
},
{
"epoch": 1.6462882096069869,
"grad_norm": 1.727308750152588,
"learning_rate": 4.626349532067879e-06,
"loss": 0.063,
"step": 95
},
{
"epoch": 1.7336244541484715,
"grad_norm": 1.7369672060012817,
"learning_rate": 4.162468883476319e-06,
"loss": 0.0692,
"step": 100
},
{
"epoch": 1.8209606986899565,
"grad_norm": 1.6199991703033447,
"learning_rate": 3.705904774487396e-06,
"loss": 0.0628,
"step": 105
},
{
"epoch": 1.908296943231441,
"grad_norm": 1.5599461793899536,
"learning_rate": 3.2606456770738636e-06,
"loss": 0.0606,
"step": 110
},
{
"epoch": 1.9956331877729259,
"grad_norm": 2.0383946895599365,
"learning_rate": 2.83058130441221e-06,
"loss": 0.0639,
"step": 115
},
{
"epoch": 2.069868995633188,
"grad_norm": 0.7870892286300659,
"learning_rate": 2.4194686309624664e-06,
"loss": 0.0228,
"step": 120
},
{
"epoch": 2.1572052401746724,
"grad_norm": 0.9626556038856506,
"learning_rate": 2.030899072132493e-06,
"loss": 0.0268,
"step": 125
},
{
"epoch": 2.2445414847161573,
"grad_norm": 1.016351342201233,
"learning_rate": 1.6682671102399806e-06,
"loss": 0.0226,
"step": 130
},
{
"epoch": 2.331877729257642,
"grad_norm": 1.057066559791565,
"learning_rate": 1.3347406408508695e-06,
"loss": 0.0223,
"step": 135
},
{
"epoch": 2.4192139737991267,
"grad_norm": 1.0260076522827148,
"learning_rate": 1.0332332985438248e-06,
"loss": 0.0216,
"step": 140
},
{
"epoch": 2.506550218340611,
"grad_norm": 0.9998378753662109,
"learning_rate": 7.663790038585794e-07,
"loss": 0.0224,
"step": 145
},
{
"epoch": 2.593886462882096,
"grad_norm": 1.1601568460464478,
"learning_rate": 5.365089537819435e-07,
"loss": 0.0205,
"step": 150
},
{
"epoch": 2.681222707423581,
"grad_norm": 1.052849292755127,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.0216,
"step": 155
},
{
"epoch": 2.7685589519650655,
"grad_norm": 1.0757461786270142,
"learning_rate": 1.9541339027450256e-07,
"loss": 0.0206,
"step": 160
},
{
"epoch": 2.85589519650655,
"grad_norm": 0.9472755789756775,
"learning_rate": 8.716763383355863e-08,
"loss": 0.0188,
"step": 165
},
{
"epoch": 2.943231441048035,
"grad_norm": 1.485182523727417,
"learning_rate": 2.1839605294330935e-08,
"loss": 0.0193,
"step": 170
}
],
"logging_steps": 5,
"max_steps": 174,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.323975476776796e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}