Muqeeth's picture
Training in progress, step 730, checkpoint
77089bd verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.40024672743472,
"eval_steps": 365,
"global_step": 730,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005482831882667398,
"grad_norm": 1.8271640439809084e-13,
"learning_rate": 9.999257569732963e-06,
"loss": 0.0547,
"step": 10
},
{
"epoch": 0.010965663765334796,
"grad_norm": 1.8681511551469146e-14,
"learning_rate": 9.997030499412933e-06,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.016448495648002194,
"grad_norm": 1.2511433729323063e-11,
"learning_rate": 9.993319450417669e-06,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.021931327530669592,
"grad_norm": 3.090452546650191e-11,
"learning_rate": 9.988125524825216e-06,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.02741415941333699,
"grad_norm": 1.458404726736688e-14,
"learning_rate": 9.981450265086598e-06,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.03289699129600439,
"grad_norm": 3.242672515051115e-14,
"learning_rate": 9.973295653567764e-06,
"loss": 0.0,
"step": 60
},
{
"epoch": 0.038379823178671786,
"grad_norm": 2.718872761479918e-14,
"learning_rate": 9.963664111960875e-06,
"loss": 0.0,
"step": 70
},
{
"epoch": 0.043862655061339184,
"grad_norm": 9.169036085943105e-10,
"learning_rate": 9.952558500565135e-06,
"loss": 0.0,
"step": 80
},
{
"epoch": 0.04934548694400658,
"grad_norm": 6.057082835297933e-09,
"learning_rate": 9.939982117437356e-06,
"loss": 0.0,
"step": 90
},
{
"epoch": 0.05482831882667398,
"grad_norm": 2.746146947174566e-06,
"learning_rate": 9.925938697412536e-06,
"loss": 0.0,
"step": 100
},
{
"epoch": 0.06031115070934138,
"grad_norm": 2.1543860384554137e-07,
"learning_rate": 9.910432410994701e-06,
"loss": 0.0,
"step": 110
},
{
"epoch": 0.06579398259200878,
"grad_norm": 1.2734583378914976e-06,
"learning_rate": 9.893467863118402e-06,
"loss": 0.0,
"step": 120
},
{
"epoch": 0.07127681447467617,
"grad_norm": 3.238647128256389e-09,
"learning_rate": 9.87505009178116e-06,
"loss": 0.0,
"step": 130
},
{
"epoch": 0.07675964635734357,
"grad_norm": 1.8630474585279444e-07,
"learning_rate": 9.855184566547333e-06,
"loss": 0.0,
"step": 140
},
{
"epoch": 0.08224247824001096,
"grad_norm": 1.8918351329944016e-09,
"learning_rate": 9.833877186923803e-06,
"loss": 0.0,
"step": 150
},
{
"epoch": 0.08772531012267837,
"grad_norm": 1.6541060188224321e-10,
"learning_rate": 9.811134280607988e-06,
"loss": 0.0,
"step": 160
},
{
"epoch": 0.09320814200534576,
"grad_norm": 0.0067967576906085014,
"learning_rate": 9.786962601608689e-06,
"loss": 0.0015,
"step": 170
},
{
"epoch": 0.09869097388801316,
"grad_norm": 7.394525164272636e-05,
"learning_rate": 9.761369328240347e-06,
"loss": 0.0,
"step": 180
},
{
"epoch": 0.10417380577068056,
"grad_norm": 2.62540652329335e-07,
"learning_rate": 9.734362060991274e-06,
"loss": 0.0,
"step": 190
},
{
"epoch": 0.10965663765334796,
"grad_norm": 4.609726822479843e-09,
"learning_rate": 9.70594882026652e-06,
"loss": 0.0,
"step": 200
},
{
"epoch": 0.11513946953601535,
"grad_norm": 8.970529319363152e-10,
"learning_rate": 9.676138044006051e-06,
"loss": 0.0,
"step": 210
},
{
"epoch": 0.12062230141868276,
"grad_norm": 7.758627629250725e-10,
"learning_rate": 9.644938585178894e-06,
"loss": 0.0,
"step": 220
},
{
"epoch": 0.12610513330135015,
"grad_norm": 3.484149357912969e-10,
"learning_rate": 9.61235970915407e-06,
"loss": 0.0,
"step": 230
},
{
"epoch": 0.13158796518401755,
"grad_norm": 3.5987784974267356e-10,
"learning_rate": 9.57841109094903e-06,
"loss": 0.0,
"step": 240
},
{
"epoch": 0.13707079706668493,
"grad_norm": 2.9926486289078014e-10,
"learning_rate": 9.543102812356446e-06,
"loss": 0.0,
"step": 250
},
{
"epoch": 0.14255362894935233,
"grad_norm": 2.17573001282112e-10,
"learning_rate": 9.506445358950199e-06,
"loss": 0.0,
"step": 260
},
{
"epoch": 0.14803646083201974,
"grad_norm": 1.5743054082584251e-10,
"learning_rate": 9.468449616971458e-06,
"loss": 0.0,
"step": 270
},
{
"epoch": 0.15351929271468714,
"grad_norm": 3.0337881185005244e-07,
"learning_rate": 9.429126870095766e-06,
"loss": 0.0,
"step": 280
},
{
"epoch": 0.15900212459735452,
"grad_norm": 2.075781768695606e-10,
"learning_rate": 9.388488796082113e-06,
"loss": 0.0,
"step": 290
},
{
"epoch": 0.16448495648002193,
"grad_norm": 2.6534453922977264e-07,
"learning_rate": 9.346547463304953e-06,
"loss": 0.0,
"step": 300
},
{
"epoch": 0.16996778836268933,
"grad_norm": 2.213984316767892e-06,
"learning_rate": 9.303315327170244e-06,
"loss": 0.0,
"step": 310
},
{
"epoch": 0.17545062024535674,
"grad_norm": 1.0965933022744068e-10,
"learning_rate": 9.258805226416536e-06,
"loss": 0.0,
"step": 320
},
{
"epoch": 0.1809334521280241,
"grad_norm": 9.682482593476038e-11,
"learning_rate": 9.213030379302223e-06,
"loss": 0.0,
"step": 330
},
{
"epoch": 0.18641628401069152,
"grad_norm": 1.8911376631347565e-10,
"learning_rate": 9.166004379680094e-06,
"loss": 0.0,
"step": 340
},
{
"epoch": 0.19189911589335892,
"grad_norm": 2.287967731939844e-10,
"learning_rate": 9.11774119296033e-06,
"loss": 0.0,
"step": 350
},
{
"epoch": 0.19738194777602633,
"grad_norm": 1.6538861946635564e-10,
"learning_rate": 9.068255151963174e-06,
"loss": 0.0,
"step": 360
},
{
"epoch": 0.20012336371736,
"eval_accuracy": 1.0,
"eval_loss": 8.152250430271124e-09,
"eval_runtime": 172.1258,
"eval_samples_per_second": 37.455,
"eval_steps_per_second": 4.683,
"step": 365
},
{
"epoch": 0.2028647796586937,
"grad_norm": 1.5171223139986978e-06,
"learning_rate": 9.017560952662478e-06,
"loss": 0.0,
"step": 370
},
{
"epoch": 0.2083476115413611,
"grad_norm": 1.40862849162815e-10,
"learning_rate": 8.965673649821411e-06,
"loss": 0.0,
"step": 380
},
{
"epoch": 0.21383044342402852,
"grad_norm": 1.6394713364675795e-10,
"learning_rate": 8.912608652521618e-06,
"loss": 0.0,
"step": 390
},
{
"epoch": 0.21931327530669592,
"grad_norm": 9.934635752939514e-11,
"learning_rate": 8.858381719587143e-06,
"loss": 0.0,
"step": 400
},
{
"epoch": 0.2247961071893633,
"grad_norm": 1.0912845627153445e-10,
"learning_rate": 8.803008954904504e-06,
"loss": 0.0,
"step": 410
},
{
"epoch": 0.2302789390720307,
"grad_norm": 4.275700121070258e-05,
"learning_rate": 8.74650680264029e-06,
"loss": 0.0001,
"step": 420
},
{
"epoch": 0.2357617709546981,
"grad_norm": 3.5764787753578275e-05,
"learning_rate": 8.688892042357703e-06,
"loss": 0.0,
"step": 430
},
{
"epoch": 0.2412446028373655,
"grad_norm": 8.193592657335103e-05,
"learning_rate": 8.63018178403348e-06,
"loss": 0.0,
"step": 440
},
{
"epoch": 0.2467274347200329,
"grad_norm": 9.473233149037696e-06,
"learning_rate": 8.570393462976731e-06,
"loss": 0.0,
"step": 450
},
{
"epoch": 0.2522102666027003,
"grad_norm": 0.00011029987945221364,
"learning_rate": 8.509544834651124e-06,
"loss": 0.0,
"step": 460
},
{
"epoch": 0.2576930984853677,
"grad_norm": 6.70829012960894e-06,
"learning_rate": 8.44765396940201e-06,
"loss": 0.0,
"step": 470
},
{
"epoch": 0.2631759303680351,
"grad_norm": 6.388377641997067e-06,
"learning_rate": 8.384739247090032e-06,
"loss": 0.0,
"step": 480
},
{
"epoch": 0.2686587622507025,
"grad_norm": 5.076117304270156e-06,
"learning_rate": 8.320819351632828e-06,
"loss": 0.0,
"step": 490
},
{
"epoch": 0.27414159413336986,
"grad_norm": 8.84547353052767e-06,
"learning_rate": 8.255913265456416e-06,
"loss": 0.0,
"step": 500
},
{
"epoch": 0.27962442601603726,
"grad_norm": 3.398100943741156e-06,
"learning_rate": 8.190040263857955e-06,
"loss": 0.0,
"step": 510
},
{
"epoch": 0.28510725789870467,
"grad_norm": 8.591404366597999e-06,
"learning_rate": 8.123219909281511e-06,
"loss": 0.0,
"step": 520
},
{
"epoch": 0.2905900897813721,
"grad_norm": 3.0375645110325422e-06,
"learning_rate": 8.05547204550856e-06,
"loss": 0.0,
"step": 530
},
{
"epoch": 0.2960729216640395,
"grad_norm": 3.1508220672549214e-06,
"learning_rate": 7.986816791764942e-06,
"loss": 0.0,
"step": 540
},
{
"epoch": 0.3015557535467069,
"grad_norm": 4.118597907165622e-09,
"learning_rate": 7.917274536746002e-06,
"loss": 0.0,
"step": 550
},
{
"epoch": 0.3070385854293743,
"grad_norm": 6.056056697789636e-12,
"learning_rate": 7.846865932561727e-06,
"loss": 0.0,
"step": 560
},
{
"epoch": 0.3125214173120417,
"grad_norm": 1.4811193160824132e-08,
"learning_rate": 7.775611888603641e-06,
"loss": 0.0,
"step": 570
},
{
"epoch": 0.31800424919470904,
"grad_norm": 1.5655763144217794e-11,
"learning_rate": 7.703533565335293e-06,
"loss": 0.0,
"step": 580
},
{
"epoch": 0.32348708107737645,
"grad_norm": 2.8082117187189226e-10,
"learning_rate": 7.630652368008202e-06,
"loss": 0.0,
"step": 590
},
{
"epoch": 0.32896991296004385,
"grad_norm": 1.598878668351844e-10,
"learning_rate": 7.556989940305087e-06,
"loss": 0.0,
"step": 600
},
{
"epoch": 0.33445274484271126,
"grad_norm": 2.0122902455455005e-08,
"learning_rate": 7.482568157912293e-06,
"loss": 0.0,
"step": 610
},
{
"epoch": 0.33993557672537866,
"grad_norm": 4.7687648101202296e-12,
"learning_rate": 7.407409122023334e-06,
"loss": 0.0,
"step": 620
},
{
"epoch": 0.34541840860804607,
"grad_norm": 4.5280151156346093e-11,
"learning_rate": 7.3315351527754405e-06,
"loss": 0.0,
"step": 630
},
{
"epoch": 0.3509012404907135,
"grad_norm": 1.5659229291031806e-07,
"learning_rate": 7.254968782621115e-06,
"loss": 0.0,
"step": 640
},
{
"epoch": 0.3563840723733809,
"grad_norm": 1.5579940115806323e-11,
"learning_rate": 7.177732749636612e-06,
"loss": 0.0,
"step": 650
},
{
"epoch": 0.3618669042560482,
"grad_norm": 9.450333493532526e-08,
"learning_rate": 7.099849990769371e-06,
"loss": 0.0,
"step": 660
},
{
"epoch": 0.36734973613871563,
"grad_norm": 4.771372630330006e-09,
"learning_rate": 7.021343635026373e-06,
"loss": 0.0,
"step": 670
},
{
"epoch": 0.37283256802138304,
"grad_norm": 9.640462733662147e-11,
"learning_rate": 6.9422369966054856e-06,
"loss": 0.0,
"step": 680
},
{
"epoch": 0.37831539990405044,
"grad_norm": 5.622925458581562e-10,
"learning_rate": 6.862553567971782e-06,
"loss": 0.0,
"step": 690
},
{
"epoch": 0.38379823178671785,
"grad_norm": 1.4773490590591631e-12,
"learning_rate": 6.782317012880941e-06,
"loss": 0.0,
"step": 700
},
{
"epoch": 0.38928106366938525,
"grad_norm": 1.792624208796223e-11,
"learning_rate": 6.7015511593517735e-06,
"loss": 0.0,
"step": 710
},
{
"epoch": 0.39476389555205266,
"grad_norm": 1.1963580126561624e-10,
"learning_rate": 6.6202799925899595e-06,
"loss": 0.0,
"step": 720
},
{
"epoch": 0.40024672743472,
"grad_norm": 4.0963617047029555e-12,
"learning_rate": 6.5385276478651164e-06,
"loss": 0.0,
"step": 730
},
{
"epoch": 0.40024672743472,
"eval_accuracy": 1.0,
"eval_loss": 1.5134760111834566e-10,
"eval_runtime": 172.6946,
"eval_samples_per_second": 37.332,
"eval_steps_per_second": 4.667,
"step": 730
}
],
"logging_steps": 10,
"max_steps": 1823,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 365,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}