| { | |
| "best_metric": 0.4530116021633148, | |
| "best_model_checkpoint": "Phi-3.5-mini-instruct_text_to_sql_lora\\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": 0.09373754262924194, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07451564828614009, | |
| "eval_loss": 0.5543281435966492, | |
| "eval_runtime": 19.9013, | |
| "eval_samples_per_second": 6.231, | |
| "eval_steps_per_second": 0.804, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "grad_norm": 0.04845063388347626, | |
| "learning_rate": 0.0001996800092633612, | |
| "loss": 0.5243, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "eval_loss": 0.5150236487388611, | |
| "eval_runtime": 19.8752, | |
| "eval_samples_per_second": 6.239, | |
| "eval_steps_per_second": 0.805, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "grad_norm": 0.06224009767174721, | |
| "learning_rate": 0.00019872208493487546, | |
| "loss": 0.5046, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "eval_loss": 0.504132091999054, | |
| "eval_runtime": 19.8753, | |
| "eval_samples_per_second": 6.239, | |
| "eval_steps_per_second": 0.805, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 0.053420498967170715, | |
| "learning_rate": 0.0001971323575527731, | |
| "loss": 0.4989, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "eval_loss": 0.49748167395591736, | |
| "eval_runtime": 19.873, | |
| "eval_samples_per_second": 6.24, | |
| "eval_steps_per_second": 0.805, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "grad_norm": 0.04381432756781578, | |
| "learning_rate": 0.0001949210010777752, | |
| "loss": 0.4873, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "eval_loss": 0.4926624298095703, | |
| "eval_runtime": 19.9753, | |
| "eval_samples_per_second": 6.208, | |
| "eval_steps_per_second": 0.801, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "grad_norm": 0.05697334185242653, | |
| "learning_rate": 0.00019210216778162994, | |
| "loss": 0.4854, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "eval_loss": 0.48829007148742676, | |
| "eval_runtime": 19.8877, | |
| "eval_samples_per_second": 6.235, | |
| "eval_steps_per_second": 0.805, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "grad_norm": 0.07128433138132095, | |
| "learning_rate": 0.0001886938976751951, | |
| "loss": 0.4788, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "eval_loss": 0.48432213068008423, | |
| "eval_runtime": 19.8588, | |
| "eval_samples_per_second": 6.244, | |
| "eval_steps_per_second": 0.806, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 0.049252185970544815, | |
| "learning_rate": 0.00018471800305571129, | |
| "loss": 0.4811, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "eval_loss": 0.4807914197444916, | |
| "eval_runtime": 19.8677, | |
| "eval_samples_per_second": 6.241, | |
| "eval_steps_per_second": 0.805, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "grad_norm": 0.05810828506946564, | |
| "learning_rate": 0.00018019992891214008, | |
| "loss": 0.4796, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "eval_loss": 0.478938490152359, | |
| "eval_runtime": 19.8654, | |
| "eval_samples_per_second": 6.242, | |
| "eval_steps_per_second": 0.805, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "grad_norm": 0.06429937481880188, | |
| "learning_rate": 0.00017516859008194938, | |
| "loss": 0.4738, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "eval_loss": 0.47758275270462036, | |
| "eval_runtime": 19.8891, | |
| "eval_samples_per_second": 6.235, | |
| "eval_steps_per_second": 0.804, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 0.057866841554641724, | |
| "learning_rate": 0.00016965618620151017, | |
| "loss": 0.4693, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "eval_loss": 0.47498929500579834, | |
| "eval_runtime": 19.8807, | |
| "eval_samples_per_second": 6.237, | |
| "eval_steps_per_second": 0.805, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "grad_norm": 0.07081956416368484, | |
| "learning_rate": 0.00016369799563438958, | |
| "loss": 0.4696, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "eval_loss": 0.4721943736076355, | |
| "eval_runtime": 19.8698, | |
| "eval_samples_per_second": 6.241, | |
| "eval_steps_per_second": 0.805, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9687034277198212, | |
| "grad_norm": 0.04943346604704857, | |
| "learning_rate": 0.00015733214969635968, | |
| "loss": 0.4682, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9687034277198212, | |
| "eval_loss": 0.4704548120498657, | |
| "eval_runtime": 21.0797, | |
| "eval_samples_per_second": 5.882, | |
| "eval_steps_per_second": 0.759, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0432190760059612, | |
| "grad_norm": 0.04892728850245476, | |
| "learning_rate": 0.00015059938862204127, | |
| "loss": 0.4607, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.0432190760059612, | |
| "eval_loss": 0.4692542850971222, | |
| "eval_runtime": 21.0437, | |
| "eval_samples_per_second": 5.893, | |
| "eval_steps_per_second": 0.76, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1177347242921014, | |
| "grad_norm": 0.05664736032485962, | |
| "learning_rate": 0.00014354280083495006, | |
| "loss": 0.4535, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1177347242921014, | |
| "eval_loss": 0.4676324725151062, | |
| "eval_runtime": 22.3216, | |
| "eval_samples_per_second": 5.555, | |
| "eval_steps_per_second": 0.717, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1922503725782414, | |
| "grad_norm": 0.04623207449913025, | |
| "learning_rate": 0.000136207547189569, | |
| "loss": 0.4538, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1922503725782414, | |
| "eval_loss": 0.4663061201572418, | |
| "eval_runtime": 19.8619, | |
| "eval_samples_per_second": 6.243, | |
| "eval_steps_per_second": 0.806, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2667660208643814, | |
| "grad_norm": 0.05065590888261795, | |
| "learning_rate": 0.00012864057195024643, | |
| "loss": 0.4508, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.2667660208643814, | |
| "eval_loss": 0.4653000235557556, | |
| "eval_runtime": 20.4016, | |
| "eval_samples_per_second": 6.078, | |
| "eval_steps_per_second": 0.784, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.3412816691505216, | |
| "grad_norm": 0.050148364156484604, | |
| "learning_rate": 0.00012089030235660155, | |
| "loss": 0.449, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.3412816691505216, | |
| "eval_loss": 0.4636177122592926, | |
| "eval_runtime": 20.3024, | |
| "eval_samples_per_second": 6.108, | |
| "eval_steps_per_second": 0.788, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4157973174366618, | |
| "grad_norm": 0.05486341193318367, | |
| "learning_rate": 0.00011300633869816275, | |
| "loss": 0.4493, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.4157973174366618, | |
| "eval_loss": 0.4632996618747711, | |
| "eval_runtime": 20.384, | |
| "eval_samples_per_second": 6.083, | |
| "eval_steps_per_second": 0.785, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.4903129657228018, | |
| "grad_norm": 0.05443250760436058, | |
| "learning_rate": 0.00010503913688170396, | |
| "loss": 0.4512, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4903129657228018, | |
| "eval_loss": 0.46247440576553345, | |
| "eval_runtime": 20.3518, | |
| "eval_samples_per_second": 6.093, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5648286140089418, | |
| "grad_norm": 0.050281789153814316, | |
| "learning_rate": 9.703968552278915e-05, | |
| "loss": 0.4517, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.5648286140089418, | |
| "eval_loss": 0.46042901277542114, | |
| "eval_runtime": 19.9596, | |
| "eval_samples_per_second": 6.213, | |
| "eval_steps_per_second": 0.802, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "grad_norm": 0.05282198637723923, | |
| "learning_rate": 8.905917962807927e-05, | |
| "loss": 0.4478, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "eval_loss": 0.4593241810798645, | |
| "eval_runtime": 19.9271, | |
| "eval_samples_per_second": 6.223, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.713859910581222, | |
| "grad_norm": 0.05663960054516792, | |
| "learning_rate": 8.114869295677425e-05, | |
| "loss": 0.4483, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.713859910581222, | |
| "eval_loss": 0.4582765996456146, | |
| "eval_runtime": 19.9072, | |
| "eval_samples_per_second": 6.229, | |
| "eval_steps_per_second": 0.804, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.788375558867362, | |
| "grad_norm": 0.05754128098487854, | |
| "learning_rate": 7.335885115801656e-05, | |
| "loss": 0.4479, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.788375558867362, | |
| "eval_loss": 0.4579518735408783, | |
| "eval_runtime": 19.883, | |
| "eval_samples_per_second": 6.236, | |
| "eval_steps_per_second": 0.805, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.8628912071535022, | |
| "grad_norm": 0.05780432000756264, | |
| "learning_rate": 6.573950777611587e-05, | |
| "loss": 0.4476, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.8628912071535022, | |
| "eval_loss": 0.456869512796402, | |
| "eval_runtime": 19.9094, | |
| "eval_samples_per_second": 6.228, | |
| "eval_steps_per_second": 0.804, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.9374068554396424, | |
| "grad_norm": 0.05665415897965431, | |
| "learning_rate": 5.833942519710177e-05, | |
| "loss": 0.4454, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.9374068554396424, | |
| "eval_loss": 0.45577672123908997, | |
| "eval_runtime": 19.9333, | |
| "eval_samples_per_second": 6.221, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.0119225037257826, | |
| "grad_norm": 0.057158373296260834, | |
| "learning_rate": 5.1205962578487155e-05, | |
| "loss": 0.4435, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.0119225037257826, | |
| "eval_loss": 0.45555853843688965, | |
| "eval_runtime": 19.9237, | |
| "eval_samples_per_second": 6.224, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.0864381520119224, | |
| "grad_norm": 0.05942057818174362, | |
| "learning_rate": 4.4384772759434425e-05, | |
| "loss": 0.4339, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0864381520119224, | |
| "eval_loss": 0.4557653069496155, | |
| "eval_runtime": 19.9268, | |
| "eval_samples_per_second": 6.223, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.1609538002980626, | |
| "grad_norm": 0.05777844041585922, | |
| "learning_rate": 3.7919510091042566e-05, | |
| "loss": 0.4322, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.1609538002980626, | |
| "eval_loss": 0.45560821890830994, | |
| "eval_runtime": 19.9533, | |
| "eval_samples_per_second": 6.215, | |
| "eval_steps_per_second": 0.802, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.235469448584203, | |
| "grad_norm": 0.05342744290828705, | |
| "learning_rate": 3.185155105658798e-05, | |
| "loss": 0.4295, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.235469448584203, | |
| "eval_loss": 0.4551125168800354, | |
| "eval_runtime": 19.9502, | |
| "eval_samples_per_second": 6.215, | |
| "eval_steps_per_second": 0.802, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.3099850968703426, | |
| "grad_norm": 0.05730094388127327, | |
| "learning_rate": 2.6219729469697318e-05, | |
| "loss": 0.4363, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.3099850968703426, | |
| "eval_loss": 0.45447057485580444, | |
| "eval_runtime": 19.938, | |
| "eval_samples_per_second": 6.219, | |
| "eval_steps_per_second": 0.802, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.384500745156483, | |
| "grad_norm": 0.05646738409996033, | |
| "learning_rate": 2.1060087945134677e-05, | |
| "loss": 0.4298, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.384500745156483, | |
| "eval_loss": 0.4543200731277466, | |
| "eval_runtime": 19.9365, | |
| "eval_samples_per_second": 6.22, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "grad_norm": 0.0644339844584465, | |
| "learning_rate": 1.640564723274486e-05, | |
| "loss": 0.4308, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "eval_loss": 0.4538328945636749, | |
| "eval_runtime": 19.9162, | |
| "eval_samples_per_second": 6.226, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.533532041728763, | |
| "grad_norm": 0.05787523835897446, | |
| "learning_rate": 1.2286194890771819e-05, | |
| "loss": 0.4363, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.533532041728763, | |
| "eval_loss": 0.45351502299308777, | |
| "eval_runtime": 19.9092, | |
| "eval_samples_per_second": 6.228, | |
| "eval_steps_per_second": 0.804, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.608047690014903, | |
| "grad_norm": 0.05828353762626648, | |
| "learning_rate": 8.728094651004648e-06, | |
| "loss": 0.4291, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.608047690014903, | |
| "eval_loss": 0.4533880949020386, | |
| "eval_runtime": 19.9085, | |
| "eval_samples_per_second": 6.229, | |
| "eval_steps_per_second": 0.804, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.682563338301043, | |
| "grad_norm": 0.05924544110894203, | |
| "learning_rate": 5.7541176957785605e-06, | |
| "loss": 0.4286, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.682563338301043, | |
| "eval_loss": 0.45319971442222595, | |
| "eval_runtime": 19.9089, | |
| "eval_samples_per_second": 6.228, | |
| "eval_steps_per_second": 0.804, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.7570789865871834, | |
| "grad_norm": 0.0565376915037632, | |
| "learning_rate": 3.3832969266265112e-06, | |
| "loss": 0.4259, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.7570789865871834, | |
| "eval_loss": 0.45311444997787476, | |
| "eval_runtime": 19.9241, | |
| "eval_samples_per_second": 6.224, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.8315946348733236, | |
| "grad_norm": 0.05949319526553154, | |
| "learning_rate": 1.6308051572357152e-06, | |
| "loss": 0.4313, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.8315946348733236, | |
| "eval_loss": 0.45298200845718384, | |
| "eval_runtime": 19.9172, | |
| "eval_samples_per_second": 6.226, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.9061102831594634, | |
| "grad_norm": 0.059121884405612946, | |
| "learning_rate": 5.078580102509834e-07, | |
| "loss": 0.4298, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.9061102831594634, | |
| "eval_loss": 0.45297005772590637, | |
| "eval_runtime": 19.9314, | |
| "eval_samples_per_second": 6.221, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.9806259314456036, | |
| "grad_norm": 0.055241379886865616, | |
| "learning_rate": 2.164213936770576e-08, | |
| "loss": 0.4298, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.9806259314456036, | |
| "eval_loss": 0.4530116021633148, | |
| "eval_runtime": 19.9318, | |
| "eval_samples_per_second": 6.221, | |
| "eval_steps_per_second": 0.803, | |
| "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": 7.514149576475935e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |