dimasik1987's picture
Training in progress, step 50, checkpoint
33fb5fc verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.002591680704937152,
"eval_steps": 500,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 5.183361409874304e-05,
"grad_norm": 2.239365577697754,
"learning_rate": 0.0001,
"loss": 3.5313,
"step": 1
},
{
"epoch": 0.00010366722819748608,
"grad_norm": 2.232938766479492,
"learning_rate": 0.0002,
"loss": 3.4008,
"step": 2
},
{
"epoch": 0.00015550084229622911,
"grad_norm": 2.102663993835449,
"learning_rate": 0.00019978589232386035,
"loss": 3.4453,
"step": 3
},
{
"epoch": 0.00020733445639497215,
"grad_norm": 2.2084500789642334,
"learning_rate": 0.00019914448613738106,
"loss": 3.2059,
"step": 4
},
{
"epoch": 0.0002591680704937152,
"grad_norm": 2.298299789428711,
"learning_rate": 0.00019807852804032305,
"loss": 2.8714,
"step": 5
},
{
"epoch": 0.00031100168459245823,
"grad_norm": 2.7205018997192383,
"learning_rate": 0.00019659258262890683,
"loss": 2.8709,
"step": 6
},
{
"epoch": 0.00036283529869120127,
"grad_norm": 2.676346778869629,
"learning_rate": 0.0001946930129495106,
"loss": 2.7284,
"step": 7
},
{
"epoch": 0.0004146689127899443,
"grad_norm": 2.102119207382202,
"learning_rate": 0.0001923879532511287,
"loss": 2.6003,
"step": 8
},
{
"epoch": 0.0004665025268886873,
"grad_norm": 1.9926272630691528,
"learning_rate": 0.00018968727415326884,
"loss": 2.6009,
"step": 9
},
{
"epoch": 0.0005183361409874304,
"grad_norm": 1.8869287967681885,
"learning_rate": 0.00018660254037844388,
"loss": 2.4702,
"step": 10
},
{
"epoch": 0.0005701697550861734,
"grad_norm": 1.9936801195144653,
"learning_rate": 0.00018314696123025454,
"loss": 2.4459,
"step": 11
},
{
"epoch": 0.0006220033691849165,
"grad_norm": 2.1325602531433105,
"learning_rate": 0.00017933533402912354,
"loss": 2.4536,
"step": 12
},
{
"epoch": 0.0006738369832836595,
"grad_norm": 1.832174301147461,
"learning_rate": 0.00017518398074789775,
"loss": 2.418,
"step": 13
},
{
"epoch": 0.0007256705973824025,
"grad_norm": 1.9308825731277466,
"learning_rate": 0.00017071067811865476,
"loss": 2.6394,
"step": 14
},
{
"epoch": 0.0007775042114811456,
"grad_norm": 1.5413264036178589,
"learning_rate": 0.00016593458151000688,
"loss": 2.2739,
"step": 15
},
{
"epoch": 0.0008293378255798886,
"grad_norm": 1.7187122106552124,
"learning_rate": 0.00016087614290087208,
"loss": 2.5579,
"step": 16
},
{
"epoch": 0.0008811714396786315,
"grad_norm": 1.8877888917922974,
"learning_rate": 0.00015555702330196023,
"loss": 2.3709,
"step": 17
},
{
"epoch": 0.0009330050537773746,
"grad_norm": 1.6428775787353516,
"learning_rate": 0.00015000000000000001,
"loss": 2.4452,
"step": 18
},
{
"epoch": 0.0009848386678761177,
"grad_norm": 1.731712818145752,
"learning_rate": 0.00014422886902190014,
"loss": 2.4443,
"step": 19
},
{
"epoch": 0.0010366722819748608,
"grad_norm": 1.5395678281784058,
"learning_rate": 0.000138268343236509,
"loss": 2.4999,
"step": 20
},
{
"epoch": 0.0010885058960736038,
"grad_norm": 1.6540272235870361,
"learning_rate": 0.00013214394653031616,
"loss": 2.3792,
"step": 21
},
{
"epoch": 0.0011403395101723468,
"grad_norm": 1.572550654411316,
"learning_rate": 0.00012588190451025207,
"loss": 2.4802,
"step": 22
},
{
"epoch": 0.0011921731242710899,
"grad_norm": 1.7922344207763672,
"learning_rate": 0.00011950903220161285,
"loss": 2.3397,
"step": 23
},
{
"epoch": 0.001244006738369833,
"grad_norm": 1.4903393983840942,
"learning_rate": 0.00011305261922200519,
"loss": 2.3837,
"step": 24
},
{
"epoch": 0.001295840352468576,
"grad_norm": 1.4521564245224,
"learning_rate": 0.00010654031292301432,
"loss": 2.3092,
"step": 25
},
{
"epoch": 0.001347673966567319,
"grad_norm": 1.8183993101119995,
"learning_rate": 0.0001,
"loss": 2.2552,
"step": 26
},
{
"epoch": 0.001399507580666062,
"grad_norm": 1.5538502931594849,
"learning_rate": 9.345968707698569e-05,
"loss": 2.3462,
"step": 27
},
{
"epoch": 0.001451341194764805,
"grad_norm": 1.5595468282699585,
"learning_rate": 8.694738077799488e-05,
"loss": 2.3715,
"step": 28
},
{
"epoch": 0.001503174808863548,
"grad_norm": 2.1476974487304688,
"learning_rate": 8.049096779838719e-05,
"loss": 2.293,
"step": 29
},
{
"epoch": 0.0015550084229622911,
"grad_norm": 1.9469425678253174,
"learning_rate": 7.411809548974792e-05,
"loss": 2.3133,
"step": 30
},
{
"epoch": 0.0016068420370610342,
"grad_norm": 1.6128257513046265,
"learning_rate": 6.785605346968386e-05,
"loss": 2.2834,
"step": 31
},
{
"epoch": 0.0016586756511597772,
"grad_norm": 1.5214881896972656,
"learning_rate": 6.173165676349103e-05,
"loss": 2.5029,
"step": 32
},
{
"epoch": 0.0017105092652585203,
"grad_norm": 1.5626273155212402,
"learning_rate": 5.577113097809989e-05,
"loss": 2.4548,
"step": 33
},
{
"epoch": 0.001762342879357263,
"grad_norm": 1.8093630075454712,
"learning_rate": 5.000000000000002e-05,
"loss": 2.5801,
"step": 34
},
{
"epoch": 0.0018141764934560061,
"grad_norm": 1.7555335760116577,
"learning_rate": 4.444297669803981e-05,
"loss": 2.3909,
"step": 35
},
{
"epoch": 0.0018660101075547492,
"grad_norm": 1.7623857259750366,
"learning_rate": 3.9123857099127936e-05,
"loss": 2.3654,
"step": 36
},
{
"epoch": 0.0019178437216534922,
"grad_norm": 1.8313246965408325,
"learning_rate": 3.406541848999312e-05,
"loss": 2.053,
"step": 37
},
{
"epoch": 0.0019696773357522354,
"grad_norm": 1.8312631845474243,
"learning_rate": 2.9289321881345254e-05,
"loss": 2.2619,
"step": 38
},
{
"epoch": 0.0020215109498509785,
"grad_norm": 1.3328640460968018,
"learning_rate": 2.4816019252102273e-05,
"loss": 2.2884,
"step": 39
},
{
"epoch": 0.0020733445639497215,
"grad_norm": 1.395845890045166,
"learning_rate": 2.0664665970876496e-05,
"loss": 2.1892,
"step": 40
},
{
"epoch": 0.0021251781780484646,
"grad_norm": 1.6217460632324219,
"learning_rate": 1.6853038769745467e-05,
"loss": 2.4114,
"step": 41
},
{
"epoch": 0.0021770117921472076,
"grad_norm": 1.482170581817627,
"learning_rate": 1.339745962155613e-05,
"loss": 2.3014,
"step": 42
},
{
"epoch": 0.0022288454062459506,
"grad_norm": 1.5318725109100342,
"learning_rate": 1.0312725846731175e-05,
"loss": 2.3725,
"step": 43
},
{
"epoch": 0.0022806790203446937,
"grad_norm": 1.729251742362976,
"learning_rate": 7.612046748871327e-06,
"loss": 2.306,
"step": 44
},
{
"epoch": 0.0023325126344434367,
"grad_norm": 1.675718903541565,
"learning_rate": 5.306987050489442e-06,
"loss": 2.3207,
"step": 45
},
{
"epoch": 0.0023843462485421798,
"grad_norm": 1.5841999053955078,
"learning_rate": 3.40741737109318e-06,
"loss": 2.1703,
"step": 46
},
{
"epoch": 0.002436179862640923,
"grad_norm": 1.4216182231903076,
"learning_rate": 1.921471959676957e-06,
"loss": 2.2403,
"step": 47
},
{
"epoch": 0.002488013476739666,
"grad_norm": 1.5462912321090698,
"learning_rate": 8.555138626189618e-07,
"loss": 2.3091,
"step": 48
},
{
"epoch": 0.002539847090838409,
"grad_norm": 1.3521757125854492,
"learning_rate": 2.141076761396521e-07,
"loss": 2.4685,
"step": 49
},
{
"epoch": 0.002591680704937152,
"grad_norm": 1.295125961303711,
"learning_rate": 0.0,
"loss": 2.1998,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7.41887283560448e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}