autoprogrammer's picture
Add checkpoint-228
82d476d verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 228,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02197802197802198,
"grad_norm": 103.67326354980469,
"learning_rate": 1.904761904761905e-06,
"loss": 4.2805,
"step": 5
},
{
"epoch": 0.04395604395604396,
"grad_norm": 32.411102294921875,
"learning_rate": 4.2857142857142855e-06,
"loss": 3.0271,
"step": 10
},
{
"epoch": 0.06593406593406594,
"grad_norm": 28.436738967895508,
"learning_rate": 6.666666666666667e-06,
"loss": 1.3784,
"step": 15
},
{
"epoch": 0.08791208791208792,
"grad_norm": 12.037949562072754,
"learning_rate": 9.047619047619049e-06,
"loss": 0.6998,
"step": 20
},
{
"epoch": 0.10989010989010989,
"grad_norm": 7.629189968109131,
"learning_rate": 9.999494817970498e-06,
"loss": 0.379,
"step": 25
},
{
"epoch": 0.13186813186813187,
"grad_norm": 8.154747009277344,
"learning_rate": 9.996407964134416e-06,
"loss": 0.3151,
"step": 30
},
{
"epoch": 0.15384615384615385,
"grad_norm": 6.2271504402160645,
"learning_rate": 9.990516643685222e-06,
"loss": 0.2672,
"step": 35
},
{
"epoch": 0.17582417582417584,
"grad_norm": 8.859386444091797,
"learning_rate": 9.981824163400827e-06,
"loss": 0.2517,
"step": 40
},
{
"epoch": 0.1978021978021978,
"grad_norm": 7.118361949920654,
"learning_rate": 9.970335402340534e-06,
"loss": 0.2419,
"step": 45
},
{
"epoch": 0.21978021978021978,
"grad_norm": 3.8278748989105225,
"learning_rate": 9.956056809106426e-06,
"loss": 0.1812,
"step": 50
},
{
"epoch": 0.24175824175824176,
"grad_norm": 5.752965927124023,
"learning_rate": 9.938996398223802e-06,
"loss": 0.1831,
"step": 55
},
{
"epoch": 0.26373626373626374,
"grad_norm": 6.167332172393799,
"learning_rate": 9.919163745642633e-06,
"loss": 0.1958,
"step": 60
},
{
"epoch": 0.2857142857142857,
"grad_norm": 4.087945461273193,
"learning_rate": 9.896569983362632e-06,
"loss": 0.1636,
"step": 65
},
{
"epoch": 0.3076923076923077,
"grad_norm": 3.906132459640503,
"learning_rate": 9.871227793184893e-06,
"loss": 0.1847,
"step": 70
},
{
"epoch": 0.32967032967032966,
"grad_norm": 4.176023006439209,
"learning_rate": 9.843151399593636e-06,
"loss": 0.1879,
"step": 75
},
{
"epoch": 0.3516483516483517,
"grad_norm": 4.196691036224365,
"learning_rate": 9.81235656177206e-06,
"loss": 0.1914,
"step": 80
},
{
"epoch": 0.37362637362637363,
"grad_norm": 7.6894378662109375,
"learning_rate": 9.778860564756769e-06,
"loss": 0.1889,
"step": 85
},
{
"epoch": 0.3956043956043956,
"grad_norm": 3.593900203704834,
"learning_rate": 9.742682209735727e-06,
"loss": 0.1475,
"step": 90
},
{
"epoch": 0.4175824175824176,
"grad_norm": 4.0512566566467285,
"learning_rate": 9.703841803495234e-06,
"loss": 0.1618,
"step": 95
},
{
"epoch": 0.43956043956043955,
"grad_norm": 5.384514808654785,
"learning_rate": 9.66236114702178e-06,
"loss": 0.1849,
"step": 100
},
{
"epoch": 0.46153846153846156,
"grad_norm": 5.403944492340088,
"learning_rate": 9.618263523265238e-06,
"loss": 0.1994,
"step": 105
},
{
"epoch": 0.4835164835164835,
"grad_norm": 3.8065085411071777,
"learning_rate": 9.57157368407022e-06,
"loss": 0.1643,
"step": 110
},
{
"epoch": 0.5054945054945055,
"grad_norm": 4.197083473205566,
"learning_rate": 9.522317836282949e-06,
"loss": 0.1589,
"step": 115
},
{
"epoch": 0.5274725274725275,
"grad_norm": 2.402940511703491,
"learning_rate": 9.470523627041452e-06,
"loss": 0.1246,
"step": 120
},
{
"epoch": 0.5494505494505495,
"grad_norm": 4.854755878448486,
"learning_rate": 9.416220128257317e-06,
"loss": 0.1561,
"step": 125
},
{
"epoch": 0.5714285714285714,
"grad_norm": 2.570319414138794,
"learning_rate": 9.359437820297716e-06,
"loss": 0.13,
"step": 130
},
{
"epoch": 0.5934065934065934,
"grad_norm": 3.1551403999328613,
"learning_rate": 9.300208574876897e-06,
"loss": 0.1064,
"step": 135
},
{
"epoch": 0.6153846153846154,
"grad_norm": 3.110960006713867,
"learning_rate": 9.238565637166692e-06,
"loss": 0.1985,
"step": 140
},
{
"epoch": 0.6373626373626373,
"grad_norm": 3.1644997596740723,
"learning_rate": 9.174543607136111e-06,
"loss": 0.1587,
"step": 145
},
{
"epoch": 0.6593406593406593,
"grad_norm": 6.993527412414551,
"learning_rate": 9.108178420130514e-06,
"loss": 0.1558,
"step": 150
},
{
"epoch": 0.6813186813186813,
"grad_norm": 3.0573744773864746,
"learning_rate": 9.039507326701207e-06,
"loss": 0.1562,
"step": 155
},
{
"epoch": 0.7032967032967034,
"grad_norm": 3.820344924926758,
"learning_rate": 8.968568871696847e-06,
"loss": 0.1243,
"step": 160
},
{
"epoch": 0.7252747252747253,
"grad_norm": 2.475353956222534,
"learning_rate": 8.895402872628352e-06,
"loss": 0.1176,
"step": 165
},
{
"epoch": 0.7472527472527473,
"grad_norm": 4.724120140075684,
"learning_rate": 8.82005039731946e-06,
"loss": 0.1382,
"step": 170
},
{
"epoch": 0.7692307692307693,
"grad_norm": 3.1053123474121094,
"learning_rate": 8.742553740855507e-06,
"loss": 0.1343,
"step": 175
},
{
"epoch": 0.7912087912087912,
"grad_norm": 3.0429627895355225,
"learning_rate": 8.66295640184334e-06,
"loss": 0.1503,
"step": 180
},
{
"epoch": 0.8131868131868132,
"grad_norm": 2.8905272483825684,
"learning_rate": 8.581303057995697e-06,
"loss": 0.1009,
"step": 185
},
{
"epoch": 0.8351648351648352,
"grad_norm": 2.9303762912750244,
"learning_rate": 8.497639541053769e-06,
"loss": 0.1297,
"step": 190
},
{
"epoch": 0.8571428571428571,
"grad_norm": 3.473829746246338,
"learning_rate": 8.412012811061985e-06,
"loss": 0.1501,
"step": 195
},
{
"epoch": 0.8791208791208791,
"grad_norm": 4.055568218231201,
"learning_rate": 8.324470930009514e-06,
"loss": 0.1333,
"step": 200
},
{
"epoch": 0.9010989010989011,
"grad_norm": 2.477252244949341,
"learning_rate": 8.235063034853228e-06,
"loss": 0.1034,
"step": 205
},
{
"epoch": 0.9230769230769231,
"grad_norm": 2.2709848880767822,
"learning_rate": 8.143839309937307e-06,
"loss": 0.1048,
"step": 210
},
{
"epoch": 0.945054945054945,
"grad_norm": 5.626249313354492,
"learning_rate": 8.050850958824926e-06,
"loss": 0.068,
"step": 215
},
{
"epoch": 0.967032967032967,
"grad_norm": 4.006984710693359,
"learning_rate": 7.95615017555788e-06,
"loss": 0.1117,
"step": 220
},
{
"epoch": 0.989010989010989,
"grad_norm": 3.718461275100708,
"learning_rate": 7.859790115360243e-06,
"loss": 0.1327,
"step": 225
}
],
"logging_steps": 5,
"max_steps": 684,
"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": false
},
"attributes": {}
}
},
"total_flos": 3.598364773219041e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}