| { | |
| "best_metric": 0.45383939146995544, | |
| "best_model_checkpoint": "Phi-3.5-mini-instruct_text_to_sql\\checkpoint-2000", | |
| "epoch": 2.9806259314456036, | |
| "eval_steps": 50, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07451564828614009, | |
| "grad_norm": 0.05202275142073631, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07451564828614009, | |
| "eval_loss": 0.5696993470191956, | |
| "eval_runtime": 27.4333, | |
| "eval_samples_per_second": 4.593, | |
| "eval_steps_per_second": 0.583, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "grad_norm": 0.038158852607011795, | |
| "learning_rate": 0.0001996800092633612, | |
| "loss": 0.5364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "eval_loss": 0.5185158848762512, | |
| "eval_runtime": 26.2689, | |
| "eval_samples_per_second": 4.797, | |
| "eval_steps_per_second": 0.609, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "grad_norm": 0.12953701615333557, | |
| "learning_rate": 0.00019872208493487546, | |
| "loss": 0.5099, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "eval_loss": 0.5075405240058899, | |
| "eval_runtime": 26.9551, | |
| "eval_samples_per_second": 4.674, | |
| "eval_steps_per_second": 0.594, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 0.036496683955192566, | |
| "learning_rate": 0.0001971323575527731, | |
| "loss": 0.5012, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "eval_loss": 0.49924516677856445, | |
| "eval_runtime": 26.2588, | |
| "eval_samples_per_second": 4.798, | |
| "eval_steps_per_second": 0.609, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "grad_norm": 0.047366924583911896, | |
| "learning_rate": 0.0001949210010777752, | |
| "loss": 0.4915, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "eval_loss": 0.49416425824165344, | |
| "eval_runtime": 26.2568, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.609, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "grad_norm": 0.035322971642017365, | |
| "learning_rate": 0.00019210216778162994, | |
| "loss": 0.4908, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "eval_loss": 0.48849040269851685, | |
| "eval_runtime": 26.2674, | |
| "eval_samples_per_second": 4.797, | |
| "eval_steps_per_second": 0.609, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "grad_norm": 0.04145614430308342, | |
| "learning_rate": 0.0001886938976751951, | |
| "loss": 0.486, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "eval_loss": 0.48535990715026855, | |
| "eval_runtime": 26.2577, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.609, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 0.04975809529423714, | |
| "learning_rate": 0.00018471800305571129, | |
| "loss": 0.4867, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "eval_loss": 0.4834245443344116, | |
| "eval_runtime": 26.1969, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 0.611, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "grad_norm": 0.05116498842835426, | |
| "learning_rate": 0.00018019992891214008, | |
| "loss": 0.4792, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "eval_loss": 0.4825398325920105, | |
| "eval_runtime": 26.1757, | |
| "eval_samples_per_second": 4.814, | |
| "eval_steps_per_second": 0.611, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "grad_norm": 0.039921361953020096, | |
| "learning_rate": 0.00017516859008194938, | |
| "loss": 0.4781, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "eval_loss": 0.4772830307483673, | |
| "eval_runtime": 26.1948, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 0.611, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 0.04263721778988838, | |
| "learning_rate": 0.00016965618620151017, | |
| "loss": 0.4779, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "eval_loss": 0.4743432402610779, | |
| "eval_runtime": 26.2176, | |
| "eval_samples_per_second": 4.806, | |
| "eval_steps_per_second": 0.61, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "grad_norm": 0.04496975615620613, | |
| "learning_rate": 0.00016369799563438958, | |
| "loss": 0.4738, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "eval_loss": 0.47231313586235046, | |
| "eval_runtime": 26.1874, | |
| "eval_samples_per_second": 4.811, | |
| "eval_steps_per_second": 0.611, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9687034277198212, | |
| "grad_norm": 0.052979908883571625, | |
| "learning_rate": 0.00015733214969635968, | |
| "loss": 0.4727, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9687034277198212, | |
| "eval_loss": 0.47076416015625, | |
| "eval_runtime": 26.1834, | |
| "eval_samples_per_second": 4.812, | |
| "eval_steps_per_second": 0.611, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0432190760059612, | |
| "grad_norm": 0.037279509007930756, | |
| "learning_rate": 0.00015059938862204127, | |
| "loss": 0.4623, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.0432190760059612, | |
| "eval_loss": 0.47042036056518555, | |
| "eval_runtime": 26.1969, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 0.611, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1177347242921014, | |
| "grad_norm": 0.044078536331653595, | |
| "learning_rate": 0.00014354280083495006, | |
| "loss": 0.4578, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1177347242921014, | |
| "eval_loss": 0.4691551625728607, | |
| "eval_runtime": 26.1904, | |
| "eval_samples_per_second": 4.811, | |
| "eval_steps_per_second": 0.611, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1922503725782414, | |
| "grad_norm": 0.03993101418018341, | |
| "learning_rate": 0.000136207547189569, | |
| "loss": 0.459, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1922503725782414, | |
| "eval_loss": 0.4670138359069824, | |
| "eval_runtime": 26.8468, | |
| "eval_samples_per_second": 4.693, | |
| "eval_steps_per_second": 0.596, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2667660208643814, | |
| "grad_norm": 0.050710201263427734, | |
| "learning_rate": 0.00012864057195024643, | |
| "loss": 0.4572, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.2667660208643814, | |
| "eval_loss": 0.4661361575126648, | |
| "eval_runtime": 26.2737, | |
| "eval_samples_per_second": 4.796, | |
| "eval_steps_per_second": 0.609, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.3412816691505216, | |
| "grad_norm": 0.03542506694793701, | |
| "learning_rate": 0.00012089030235660155, | |
| "loss": 0.4543, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.3412816691505216, | |
| "eval_loss": 0.4644615650177002, | |
| "eval_runtime": 26.2789, | |
| "eval_samples_per_second": 4.795, | |
| "eval_steps_per_second": 0.609, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4157973174366618, | |
| "grad_norm": 0.03939700126647949, | |
| "learning_rate": 0.00011300633869816275, | |
| "loss": 0.456, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.4157973174366618, | |
| "eval_loss": 0.46352747082710266, | |
| "eval_runtime": 26.4386, | |
| "eval_samples_per_second": 4.766, | |
| "eval_steps_per_second": 0.605, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.4903129657228018, | |
| "grad_norm": 0.03840464726090431, | |
| "learning_rate": 0.00010503913688170396, | |
| "loss": 0.457, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4903129657228018, | |
| "eval_loss": 0.46207883954048157, | |
| "eval_runtime": 26.2982, | |
| "eval_samples_per_second": 4.791, | |
| "eval_steps_per_second": 0.608, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5648286140089418, | |
| "grad_norm": 0.04269999638199806, | |
| "learning_rate": 9.703968552278915e-05, | |
| "loss": 0.4459, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.5648286140089418, | |
| "eval_loss": 0.4622659385204315, | |
| "eval_runtime": 26.1338, | |
| "eval_samples_per_second": 4.783, | |
| "eval_steps_per_second": 0.612, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "grad_norm": 0.03784380853176117, | |
| "learning_rate": 8.905917962807927e-05, | |
| "loss": 0.4491, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "eval_loss": 0.46070215106010437, | |
| "eval_runtime": 26.2581, | |
| "eval_samples_per_second": 4.76, | |
| "eval_steps_per_second": 0.609, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.713859910581222, | |
| "grad_norm": 0.06169111654162407, | |
| "learning_rate": 8.114869295677425e-05, | |
| "loss": 0.4469, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.713859910581222, | |
| "eval_loss": 0.45989012718200684, | |
| "eval_runtime": 26.0654, | |
| "eval_samples_per_second": 4.796, | |
| "eval_steps_per_second": 0.614, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.788375558867362, | |
| "grad_norm": 0.04420630633831024, | |
| "learning_rate": 7.335885115801656e-05, | |
| "loss": 0.4436, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.788375558867362, | |
| "eval_loss": 0.4588496685028076, | |
| "eval_runtime": 26.1244, | |
| "eval_samples_per_second": 4.785, | |
| "eval_steps_per_second": 0.612, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.8628912071535022, | |
| "grad_norm": 0.04250326752662659, | |
| "learning_rate": 6.573950777611587e-05, | |
| "loss": 0.4437, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.8628912071535022, | |
| "eval_loss": 0.4583075940608978, | |
| "eval_runtime": 26.1348, | |
| "eval_samples_per_second": 4.783, | |
| "eval_steps_per_second": 0.612, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.9374068554396424, | |
| "grad_norm": 0.04410432279109955, | |
| "learning_rate": 5.833942519710177e-05, | |
| "loss": 0.443, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.9374068554396424, | |
| "eval_loss": 0.45751953125, | |
| "eval_runtime": 26.366, | |
| "eval_samples_per_second": 4.741, | |
| "eval_steps_per_second": 0.607, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.0119225037257826, | |
| "grad_norm": 0.04371315613389015, | |
| "learning_rate": 5.1205962578487155e-05, | |
| "loss": 0.4411, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.0119225037257826, | |
| "eval_loss": 0.45691409707069397, | |
| "eval_runtime": 26.3933, | |
| "eval_samples_per_second": 4.736, | |
| "eval_steps_per_second": 0.606, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.0864381520119224, | |
| "grad_norm": 0.051224980503320694, | |
| "learning_rate": 4.4384772759434425e-05, | |
| "loss": 0.4348, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0864381520119224, | |
| "eval_loss": 0.4565175175666809, | |
| "eval_runtime": 26.0441, | |
| "eval_samples_per_second": 4.8, | |
| "eval_steps_per_second": 0.614, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.1609538002980626, | |
| "grad_norm": 0.043918948620557785, | |
| "learning_rate": 3.7919510091042566e-05, | |
| "loss": 0.4347, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.1609538002980626, | |
| "eval_loss": 0.45600426197052, | |
| "eval_runtime": 26.8649, | |
| "eval_samples_per_second": 4.653, | |
| "eval_steps_per_second": 0.596, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.235469448584203, | |
| "grad_norm": 0.04387347772717476, | |
| "learning_rate": 3.185155105658798e-05, | |
| "loss": 0.4345, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.235469448584203, | |
| "eval_loss": 0.45609042048454285, | |
| "eval_runtime": 26.3484, | |
| "eval_samples_per_second": 4.744, | |
| "eval_steps_per_second": 0.607, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.3099850968703426, | |
| "grad_norm": 0.046535104513168335, | |
| "learning_rate": 2.6219729469697318e-05, | |
| "loss": 0.4334, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.3099850968703426, | |
| "eval_loss": 0.4557267725467682, | |
| "eval_runtime": 26.0467, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.614, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.384500745156483, | |
| "grad_norm": 0.07196968793869019, | |
| "learning_rate": 2.1060087945134677e-05, | |
| "loss": 0.4368, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.384500745156483, | |
| "eval_loss": 0.455086886882782, | |
| "eval_runtime": 26.0119, | |
| "eval_samples_per_second": 4.805, | |
| "eval_steps_per_second": 0.615, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "grad_norm": 0.043261125683784485, | |
| "learning_rate": 1.640564723274486e-05, | |
| "loss": 0.4371, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "eval_loss": 0.4548044502735138, | |
| "eval_runtime": 26.0005, | |
| "eval_samples_per_second": 4.808, | |
| "eval_steps_per_second": 0.615, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.533532041728763, | |
| "grad_norm": 0.041918862611055374, | |
| "learning_rate": 1.2286194890771819e-05, | |
| "loss": 0.435, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.533532041728763, | |
| "eval_loss": 0.4544830322265625, | |
| "eval_runtime": 26.0158, | |
| "eval_samples_per_second": 4.805, | |
| "eval_steps_per_second": 0.615, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.608047690014903, | |
| "grad_norm": 0.047430962324142456, | |
| "learning_rate": 8.728094651004648e-06, | |
| "loss": 0.4362, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.608047690014903, | |
| "eval_loss": 0.4543595314025879, | |
| "eval_runtime": 25.999, | |
| "eval_samples_per_second": 4.808, | |
| "eval_steps_per_second": 0.615, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.682563338301043, | |
| "grad_norm": 0.04513591527938843, | |
| "learning_rate": 5.7541176957785605e-06, | |
| "loss": 0.4336, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.682563338301043, | |
| "eval_loss": 0.4540981352329254, | |
| "eval_runtime": 25.9868, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 0.616, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.7570789865871834, | |
| "grad_norm": 0.042494237422943115, | |
| "learning_rate": 3.3832969266265112e-06, | |
| "loss": 0.4329, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.7570789865871834, | |
| "eval_loss": 0.45401909947395325, | |
| "eval_runtime": 26.0307, | |
| "eval_samples_per_second": 4.802, | |
| "eval_steps_per_second": 0.615, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.8315946348733236, | |
| "grad_norm": 0.043905071914196014, | |
| "learning_rate": 1.6308051572357152e-06, | |
| "loss": 0.4314, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.8315946348733236, | |
| "eval_loss": 0.45391929149627686, | |
| "eval_runtime": 26.0099, | |
| "eval_samples_per_second": 4.806, | |
| "eval_steps_per_second": 0.615, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.9061102831594634, | |
| "grad_norm": 0.0461781844496727, | |
| "learning_rate": 5.078580102509834e-07, | |
| "loss": 0.436, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.9061102831594634, | |
| "eval_loss": 0.4538543224334717, | |
| "eval_runtime": 25.9988, | |
| "eval_samples_per_second": 4.808, | |
| "eval_steps_per_second": 0.615, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.9806259314456036, | |
| "grad_norm": 0.04481622204184532, | |
| "learning_rate": 2.164213936770576e-08, | |
| "loss": 0.4332, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.9806259314456036, | |
| "eval_loss": 0.45383939146995544, | |
| "eval_runtime": 26.0241, | |
| "eval_samples_per_second": 4.803, | |
| "eval_steps_per_second": 0.615, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.614496189018276e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |