| { | |
| "best_metric": 0.7384209036827087, | |
| "best_model_checkpoint": "Phi-3.5-mini-instruct_text_to_sql_vera\\checkpoint-2000", | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 2013, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07451564828614009, | |
| "grad_norm": 0.24109168350696564, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6897, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07451564828614009, | |
| "eval_loss": 1.628873586654663, | |
| "eval_runtime": 21.2268, | |
| "eval_samples_per_second": 5.842, | |
| "eval_steps_per_second": 0.754, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "grad_norm": 0.20446562767028809, | |
| "learning_rate": 0.0001996800092633612, | |
| "loss": 1.4635, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "eval_loss": 1.3007014989852905, | |
| "eval_runtime": 21.2354, | |
| "eval_samples_per_second": 5.839, | |
| "eval_steps_per_second": 0.753, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "grad_norm": 0.15634676814079285, | |
| "learning_rate": 0.00019872208493487546, | |
| "loss": 1.1822, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "eval_loss": 1.1080372333526611, | |
| "eval_runtime": 21.2322, | |
| "eval_samples_per_second": 5.84, | |
| "eval_steps_per_second": 0.754, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 0.060426872223615646, | |
| "learning_rate": 0.0001971323575527731, | |
| "loss": 1.0493, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "eval_loss": 1.023650884628296, | |
| "eval_runtime": 23.9023, | |
| "eval_samples_per_second": 5.188, | |
| "eval_steps_per_second": 0.669, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "grad_norm": 0.04907995089888573, | |
| "learning_rate": 0.0001949210010777752, | |
| "loss": 0.9908, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "eval_loss": 0.9761372208595276, | |
| "eval_runtime": 22.3409, | |
| "eval_samples_per_second": 5.55, | |
| "eval_steps_per_second": 0.716, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "grad_norm": 0.03899872675538063, | |
| "learning_rate": 0.00019210216778162994, | |
| "loss": 0.9539, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "eval_loss": 0.9452499151229858, | |
| "eval_runtime": 22.4213, | |
| "eval_samples_per_second": 5.53, | |
| "eval_steps_per_second": 0.714, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "grad_norm": 0.039957139641046524, | |
| "learning_rate": 0.0001886938976751951, | |
| "loss": 0.9301, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "eval_loss": 0.9224702715873718, | |
| "eval_runtime": 22.4498, | |
| "eval_samples_per_second": 5.523, | |
| "eval_steps_per_second": 0.713, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 0.025905804708600044, | |
| "learning_rate": 0.00018471800305571129, | |
| "loss": 0.9065, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "eval_loss": 0.9051175713539124, | |
| "eval_runtime": 21.5395, | |
| "eval_samples_per_second": 5.757, | |
| "eval_steps_per_second": 0.743, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "grad_norm": 0.020609112456440926, | |
| "learning_rate": 0.00018019992891214008, | |
| "loss": 0.8916, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "eval_loss": 0.8914369940757751, | |
| "eval_runtime": 21.6547, | |
| "eval_samples_per_second": 5.726, | |
| "eval_steps_per_second": 0.739, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "grad_norm": 0.01633381098508835, | |
| "learning_rate": 0.00017516859008194938, | |
| "loss": 0.8799, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "eval_loss": 0.880242109298706, | |
| "eval_runtime": 21.6819, | |
| "eval_samples_per_second": 5.719, | |
| "eval_steps_per_second": 0.738, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 0.015875136479735374, | |
| "learning_rate": 0.00016965618620151017, | |
| "loss": 0.8691, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "eval_loss": 0.8673625588417053, | |
| "eval_runtime": 23.0842, | |
| "eval_samples_per_second": 5.372, | |
| "eval_steps_per_second": 0.693, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "grad_norm": 0.015761110931634903, | |
| "learning_rate": 0.00016369799563438958, | |
| "loss": 0.8574, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "eval_loss": 0.8584086894989014, | |
| "eval_runtime": 21.4811, | |
| "eval_samples_per_second": 5.773, | |
| "eval_steps_per_second": 0.745, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9687034277198212, | |
| "grad_norm": 0.013795309700071812, | |
| "learning_rate": 0.00015733214969635968, | |
| "loss": 0.854, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9687034277198212, | |
| "eval_loss": 0.8501254916191101, | |
| "eval_runtime": 21.7846, | |
| "eval_samples_per_second": 5.692, | |
| "eval_steps_per_second": 0.734, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0432190760059612, | |
| "grad_norm": 0.01314204279333353, | |
| "learning_rate": 0.00015059938862204127, | |
| "loss": 0.8436, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.0432190760059612, | |
| "eval_loss": 0.8421516418457031, | |
| "eval_runtime": 21.4589, | |
| "eval_samples_per_second": 5.778, | |
| "eval_steps_per_second": 0.746, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1177347242921014, | |
| "grad_norm": 0.014487664215266705, | |
| "learning_rate": 0.00014354280083495006, | |
| "loss": 0.8402, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1177347242921014, | |
| "eval_loss": 0.8345963358879089, | |
| "eval_runtime": 21.5388, | |
| "eval_samples_per_second": 5.757, | |
| "eval_steps_per_second": 0.743, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1922503725782414, | |
| "grad_norm": 0.012593415565788746, | |
| "learning_rate": 0.000136207547189569, | |
| "loss": 0.8302, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1922503725782414, | |
| "eval_loss": 0.8273870348930359, | |
| "eval_runtime": 21.494, | |
| "eval_samples_per_second": 5.769, | |
| "eval_steps_per_second": 0.744, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2667660208643814, | |
| "grad_norm": 0.011890560388565063, | |
| "learning_rate": 0.00012864057195024643, | |
| "loss": 0.8222, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.2667660208643814, | |
| "eval_loss": 0.8204250931739807, | |
| "eval_runtime": 21.6934, | |
| "eval_samples_per_second": 5.716, | |
| "eval_steps_per_second": 0.738, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.3412816691505216, | |
| "grad_norm": 0.01334091741591692, | |
| "learning_rate": 0.00012089030235660155, | |
| "loss": 0.81, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.3412816691505216, | |
| "eval_loss": 0.8137892484664917, | |
| "eval_runtime": 22.3403, | |
| "eval_samples_per_second": 5.55, | |
| "eval_steps_per_second": 0.716, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4157973174366618, | |
| "grad_norm": 0.012158791534602642, | |
| "learning_rate": 0.00011300633869816275, | |
| "loss": 0.8081, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.4157973174366618, | |
| "eval_loss": 0.807340681552887, | |
| "eval_runtime": 21.5174, | |
| "eval_samples_per_second": 5.763, | |
| "eval_steps_per_second": 0.744, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.4903129657228018, | |
| "grad_norm": 0.011660942807793617, | |
| "learning_rate": 0.00010503913688170396, | |
| "loss": 0.7994, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4903129657228018, | |
| "eval_loss": 0.8010362982749939, | |
| "eval_runtime": 21.55, | |
| "eval_samples_per_second": 5.754, | |
| "eval_steps_per_second": 0.742, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5648286140089418, | |
| "grad_norm": 0.010989319533109665, | |
| "learning_rate": 9.703968552278915e-05, | |
| "loss": 0.7958, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.5648286140089418, | |
| "eval_loss": 0.7949212789535522, | |
| "eval_runtime": 21.402, | |
| "eval_samples_per_second": 5.794, | |
| "eval_steps_per_second": 0.748, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "grad_norm": 0.011820629239082336, | |
| "learning_rate": 8.905917962807927e-05, | |
| "loss": 0.7893, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "eval_loss": 0.7889001965522766, | |
| "eval_runtime": 21.7151, | |
| "eval_samples_per_second": 5.71, | |
| "eval_steps_per_second": 0.737, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.713859910581222, | |
| "grad_norm": 0.011526989750564098, | |
| "learning_rate": 8.114869295677425e-05, | |
| "loss": 0.7812, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.713859910581222, | |
| "eval_loss": 0.7832813858985901, | |
| "eval_runtime": 21.1842, | |
| "eval_samples_per_second": 5.853, | |
| "eval_steps_per_second": 0.755, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.788375558867362, | |
| "grad_norm": 0.013003380037844181, | |
| "learning_rate": 7.335885115801656e-05, | |
| "loss": 0.7846, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.788375558867362, | |
| "eval_loss": 0.7778643369674683, | |
| "eval_runtime": 21.7578, | |
| "eval_samples_per_second": 5.699, | |
| "eval_steps_per_second": 0.735, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.8628912071535022, | |
| "grad_norm": 0.011233557015657425, | |
| "learning_rate": 6.573950777611587e-05, | |
| "loss": 0.7695, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.8628912071535022, | |
| "eval_loss": 0.7728994488716125, | |
| "eval_runtime": 21.828, | |
| "eval_samples_per_second": 5.681, | |
| "eval_steps_per_second": 0.733, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.9374068554396424, | |
| "grad_norm": 0.011392244137823582, | |
| "learning_rate": 5.833942519710177e-05, | |
| "loss": 0.7697, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.9374068554396424, | |
| "eval_loss": 0.7685559988021851, | |
| "eval_runtime": 21.1933, | |
| "eval_samples_per_second": 5.851, | |
| "eval_steps_per_second": 0.755, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.0119225037257826, | |
| "grad_norm": 0.01131096575409174, | |
| "learning_rate": 5.1205962578487155e-05, | |
| "loss": 0.7606, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.0119225037257826, | |
| "eval_loss": 0.764735996723175, | |
| "eval_runtime": 21.1907, | |
| "eval_samples_per_second": 5.852, | |
| "eval_steps_per_second": 0.755, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.0864381520119224, | |
| "grad_norm": 0.012029374949634075, | |
| "learning_rate": 4.4384772759434425e-05, | |
| "loss": 0.7619, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0864381520119224, | |
| "eval_loss": 0.7614848613739014, | |
| "eval_runtime": 21.1958, | |
| "eval_samples_per_second": 5.85, | |
| "eval_steps_per_second": 0.755, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.1609538002980626, | |
| "grad_norm": 0.011891283094882965, | |
| "learning_rate": 3.7919510091042566e-05, | |
| "loss": 0.7569, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.1609538002980626, | |
| "eval_loss": 0.7588434815406799, | |
| "eval_runtime": 21.1878, | |
| "eval_samples_per_second": 5.852, | |
| "eval_steps_per_second": 0.755, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.235469448584203, | |
| "grad_norm": 0.012809407897293568, | |
| "learning_rate": 3.185155105658798e-05, | |
| "loss": 0.7526, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.235469448584203, | |
| "eval_loss": 0.7565779089927673, | |
| "eval_runtime": 21.1534, | |
| "eval_samples_per_second": 5.862, | |
| "eval_steps_per_second": 0.756, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.3099850968703426, | |
| "grad_norm": 0.01183687336742878, | |
| "learning_rate": 2.6219729469697318e-05, | |
| "loss": 0.7504, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.3099850968703426, | |
| "eval_loss": 0.7436912655830383, | |
| "eval_runtime": 21.8493, | |
| "eval_samples_per_second": 5.858, | |
| "eval_steps_per_second": 0.732, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.384500745156483, | |
| "grad_norm": 0.011195004917681217, | |
| "learning_rate": 2.1060087945134677e-05, | |
| "loss": 0.7553, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.384500745156483, | |
| "eval_loss": 0.7422465682029724, | |
| "eval_runtime": 21.8534, | |
| "eval_samples_per_second": 5.857, | |
| "eval_steps_per_second": 0.732, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "grad_norm": 0.010784263722598553, | |
| "learning_rate": 1.640564723274486e-05, | |
| "loss": 0.7507, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "eval_loss": 0.7410176396369934, | |
| "eval_runtime": 21.8273, | |
| "eval_samples_per_second": 5.864, | |
| "eval_steps_per_second": 0.733, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.533532041728763, | |
| "grad_norm": 0.011086920276284218, | |
| "learning_rate": 1.2286194890771819e-05, | |
| "loss": 0.7456, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.533532041728763, | |
| "eval_loss": 0.7401486039161682, | |
| "eval_runtime": 21.8582, | |
| "eval_samples_per_second": 5.856, | |
| "eval_steps_per_second": 0.732, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.608047690014903, | |
| "grad_norm": 0.011054403148591518, | |
| "learning_rate": 8.728094651004648e-06, | |
| "loss": 0.7448, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.608047690014903, | |
| "eval_loss": 0.7393685579299927, | |
| "eval_runtime": 21.8448, | |
| "eval_samples_per_second": 5.86, | |
| "eval_steps_per_second": 0.732, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.682563338301043, | |
| "grad_norm": 0.010735660791397095, | |
| "learning_rate": 5.7541176957785605e-06, | |
| "loss": 0.7487, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.682563338301043, | |
| "eval_loss": 0.7390720248222351, | |
| "eval_runtime": 22.2346, | |
| "eval_samples_per_second": 5.757, | |
| "eval_steps_per_second": 0.72, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.7570789865871834, | |
| "grad_norm": 0.011423379182815552, | |
| "learning_rate": 3.3832969266265112e-06, | |
| "loss": 0.7476, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.7570789865871834, | |
| "eval_loss": 0.7386873960494995, | |
| "eval_runtime": 21.9986, | |
| "eval_samples_per_second": 5.819, | |
| "eval_steps_per_second": 0.727, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.8315946348733236, | |
| "grad_norm": 0.012488750740885735, | |
| "learning_rate": 1.6308051572357152e-06, | |
| "loss": 0.749, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.8315946348733236, | |
| "eval_loss": 0.7386685609817505, | |
| "eval_runtime": 22.2521, | |
| "eval_samples_per_second": 5.752, | |
| "eval_steps_per_second": 0.719, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.9061102831594634, | |
| "grad_norm": 0.010972470976412296, | |
| "learning_rate": 5.078580102509834e-07, | |
| "loss": 0.7461, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.9061102831594634, | |
| "eval_loss": 0.7385600805282593, | |
| "eval_runtime": 23.4712, | |
| "eval_samples_per_second": 5.453, | |
| "eval_steps_per_second": 0.682, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.9806259314456036, | |
| "grad_norm": 0.012074621394276619, | |
| "learning_rate": 2.164213936770576e-08, | |
| "loss": 0.7486, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.9806259314456036, | |
| "eval_loss": 0.7384209036827087, | |
| "eval_runtime": 22.0471, | |
| "eval_samples_per_second": 5.806, | |
| "eval_steps_per_second": 0.726, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2013, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.365572698728038e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |