| { |
| "best_global_step": 220, |
| "best_metric": 0.010845971293747425, |
| "best_model_checkpoint": "/teamspace/studios/this_studio/DATN/output/medgemma_finetuned/checkpoint-220", |
| "epoch": 1.0116731517509727, |
| "eval_steps": 10, |
| "global_step": 260, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.019455252918287938, |
| "grad_norm": 3.7302613258361816, |
| "learning_rate": 1.777777777777778e-06, |
| "loss": 0.8239, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.038910505836575876, |
| "grad_norm": 3.058382034301758, |
| "learning_rate": 4e-06, |
| "loss": 0.7964, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.038910505836575876, |
| "eval_loss": 0.7571244239807129, |
| "eval_runtime": 152.7626, |
| "eval_samples_per_second": 3.339, |
| "eval_steps_per_second": 0.838, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.058365758754863814, |
| "grad_norm": 1.8304738998413086, |
| "learning_rate": 6.222222222222222e-06, |
| "loss": 0.6943, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.07782101167315175, |
| "grad_norm": 1.3162634372711182, |
| "learning_rate": 8.444444444444446e-06, |
| "loss": 0.5569, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07782101167315175, |
| "eval_loss": 0.5357815623283386, |
| "eval_runtime": 136.4123, |
| "eval_samples_per_second": 3.739, |
| "eval_steps_per_second": 0.938, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09727626459143969, |
| "grad_norm": 1.1865513324737549, |
| "learning_rate": 1.0666666666666667e-05, |
| "loss": 0.4222, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.11673151750972763, |
| "grad_norm": 1.2043355703353882, |
| "learning_rate": 1.2888888888888889e-05, |
| "loss": 0.2831, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11673151750972763, |
| "eval_loss": 0.28264933824539185, |
| "eval_runtime": 136.5183, |
| "eval_samples_per_second": 3.736, |
| "eval_steps_per_second": 0.938, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.13618677042801555, |
| "grad_norm": 0.9503483772277832, |
| "learning_rate": 1.511111111111111e-05, |
| "loss": 0.1405, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.1556420233463035, |
| "grad_norm": 0.34179583191871643, |
| "learning_rate": 1.7333333333333332e-05, |
| "loss": 0.0515, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1556420233463035, |
| "eval_loss": 0.05298379808664322, |
| "eval_runtime": 136.391, |
| "eval_samples_per_second": 3.739, |
| "eval_steps_per_second": 0.938, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.17509727626459143, |
| "grad_norm": 0.24818392097949982, |
| "learning_rate": 1.9555555555555557e-05, |
| "loss": 0.0302, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.19455252918287938, |
| "grad_norm": 0.19131316244602203, |
| "learning_rate": 2.177777777777778e-05, |
| "loss": 0.0221, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.19455252918287938, |
| "eval_loss": 0.024967821314930916, |
| "eval_runtime": 136.5245, |
| "eval_samples_per_second": 3.736, |
| "eval_steps_per_second": 0.938, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2140077821011673, |
| "grad_norm": 2.454702377319336, |
| "learning_rate": 2.4e-05, |
| "loss": 0.0169, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.23346303501945526, |
| "grad_norm": 0.12364993244409561, |
| "learning_rate": 2.6222222222222226e-05, |
| "loss": 0.0164, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.23346303501945526, |
| "eval_loss": 0.021661706268787384, |
| "eval_runtime": 136.8436, |
| "eval_samples_per_second": 3.727, |
| "eval_steps_per_second": 0.935, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2529182879377432, |
| "grad_norm": 0.14085163176059723, |
| "learning_rate": 2.8444444444444447e-05, |
| "loss": 0.0131, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.2723735408560311, |
| "grad_norm": 0.15322668850421906, |
| "learning_rate": 3.066666666666666e-05, |
| "loss": 0.0089, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2723735408560311, |
| "eval_loss": 0.016315119341015816, |
| "eval_runtime": 136.2077, |
| "eval_samples_per_second": 3.744, |
| "eval_steps_per_second": 0.94, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2918287937743191, |
| "grad_norm": 0.08343034237623215, |
| "learning_rate": 3.288888888888889e-05, |
| "loss": 0.0076, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.311284046692607, |
| "grad_norm": 0.11078440397977829, |
| "learning_rate": 3.511111111111111e-05, |
| "loss": 0.008, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.311284046692607, |
| "eval_loss": 0.015718888491392136, |
| "eval_runtime": 136.7712, |
| "eval_samples_per_second": 3.729, |
| "eval_steps_per_second": 0.936, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.33073929961089493, |
| "grad_norm": 0.08361168950796127, |
| "learning_rate": 3.733333333333334e-05, |
| "loss": 0.008, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.35019455252918286, |
| "grad_norm": 0.06539439409971237, |
| "learning_rate": 3.9555555555555556e-05, |
| "loss": 0.0083, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.35019455252918286, |
| "eval_loss": 0.015910081565380096, |
| "eval_runtime": 136.5187, |
| "eval_samples_per_second": 3.736, |
| "eval_steps_per_second": 0.938, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.36964980544747084, |
| "grad_norm": 0.14973388612270355, |
| "learning_rate": 4.177777777777778e-05, |
| "loss": 0.0085, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.38910505836575876, |
| "grad_norm": 0.08519362658262253, |
| "learning_rate": 4.4e-05, |
| "loss": 0.0077, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.38910505836575876, |
| "eval_loss": 0.01615685597062111, |
| "eval_runtime": 136.4452, |
| "eval_samples_per_second": 3.738, |
| "eval_steps_per_second": 0.938, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4085603112840467, |
| "grad_norm": 0.05565109848976135, |
| "learning_rate": 4.6222222222222224e-05, |
| "loss": 0.0085, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.4280155642023346, |
| "grad_norm": 0.07286959886550903, |
| "learning_rate": 4.844444444444445e-05, |
| "loss": 0.0082, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.4280155642023346, |
| "eval_loss": 0.015698084607720375, |
| "eval_runtime": 136.3832, |
| "eval_samples_per_second": 3.739, |
| "eval_steps_per_second": 0.939, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.4474708171206226, |
| "grad_norm": 0.13329896330833435, |
| "learning_rate": 5.066666666666667e-05, |
| "loss": 0.0085, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.4669260700389105, |
| "grad_norm": 0.04628467932343483, |
| "learning_rate": 5.288888888888889e-05, |
| "loss": 0.0075, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.4669260700389105, |
| "eval_loss": 0.015623296611011028, |
| "eval_runtime": 136.0422, |
| "eval_samples_per_second": 3.749, |
| "eval_steps_per_second": 0.941, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.48638132295719844, |
| "grad_norm": 0.058520544320344925, |
| "learning_rate": 5.511111111111111e-05, |
| "loss": 0.0079, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.5058365758754864, |
| "grad_norm": 0.06411632895469666, |
| "learning_rate": 5.7333333333333336e-05, |
| "loss": 0.0076, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5058365758754864, |
| "eval_loss": 0.014402530156075954, |
| "eval_runtime": 135.5623, |
| "eval_samples_per_second": 3.762, |
| "eval_steps_per_second": 0.944, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5252918287937743, |
| "grad_norm": 0.044081032276153564, |
| "learning_rate": 5.9555555555555554e-05, |
| "loss": 0.0072, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.5447470817120622, |
| "grad_norm": 0.04867592826485634, |
| "learning_rate": 6.177777777777779e-05, |
| "loss": 0.0077, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.5447470817120622, |
| "eval_loss": 0.012970623560249805, |
| "eval_runtime": 137.0137, |
| "eval_samples_per_second": 3.722, |
| "eval_steps_per_second": 0.934, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.5642023346303502, |
| "grad_norm": 0.044633813202381134, |
| "learning_rate": 6.4e-05, |
| "loss": 0.0077, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.5836575875486382, |
| "grad_norm": 0.052950419485569, |
| "learning_rate": 6.622222222222222e-05, |
| "loss": 0.008, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.5836575875486382, |
| "eval_loss": 0.012441293336451054, |
| "eval_runtime": 136.133, |
| "eval_samples_per_second": 3.746, |
| "eval_steps_per_second": 0.94, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.603112840466926, |
| "grad_norm": 0.039904553443193436, |
| "learning_rate": 6.844444444444445e-05, |
| "loss": 0.0078, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.622568093385214, |
| "grad_norm": 0.05680263414978981, |
| "learning_rate": 7.066666666666667e-05, |
| "loss": 0.0074, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.622568093385214, |
| "eval_loss": 0.01192025002092123, |
| "eval_runtime": 136.5582, |
| "eval_samples_per_second": 3.735, |
| "eval_steps_per_second": 0.937, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.642023346303502, |
| "grad_norm": 0.05537933111190796, |
| "learning_rate": 7.288888888888888e-05, |
| "loss": 0.0076, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.6614785992217899, |
| "grad_norm": 0.04935755953192711, |
| "learning_rate": 7.511111111111111e-05, |
| "loss": 0.0077, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.6614785992217899, |
| "eval_loss": 0.012302271090447903, |
| "eval_runtime": 136.6757, |
| "eval_samples_per_second": 3.731, |
| "eval_steps_per_second": 0.937, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.6809338521400778, |
| "grad_norm": 0.05575108528137207, |
| "learning_rate": 7.733333333333333e-05, |
| "loss": 0.0081, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.7003891050583657, |
| "grad_norm": 0.0551481656730175, |
| "learning_rate": 7.955555555555556e-05, |
| "loss": 0.0081, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7003891050583657, |
| "eval_loss": 0.011542496271431446, |
| "eval_runtime": 136.4051, |
| "eval_samples_per_second": 3.739, |
| "eval_steps_per_second": 0.938, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7198443579766537, |
| "grad_norm": 0.04738597571849823, |
| "learning_rate": 8.177777777777778e-05, |
| "loss": 0.0076, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.7392996108949417, |
| "grad_norm": 0.029748599976301193, |
| "learning_rate": 8.4e-05, |
| "loss": 0.0073, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.7392996108949417, |
| "eval_loss": 0.012059729546308517, |
| "eval_runtime": 135.8659, |
| "eval_samples_per_second": 3.754, |
| "eval_steps_per_second": 0.942, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.7587548638132295, |
| "grad_norm": 0.03995237499475479, |
| "learning_rate": 8.622222222222223e-05, |
| "loss": 0.0077, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.7782101167315175, |
| "grad_norm": 0.02774854749441147, |
| "learning_rate": 8.844444444444445e-05, |
| "loss": 0.0075, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7782101167315175, |
| "eval_loss": 0.011773883365094662, |
| "eval_runtime": 136.231, |
| "eval_samples_per_second": 3.744, |
| "eval_steps_per_second": 0.94, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7976653696498055, |
| "grad_norm": 0.026570243760943413, |
| "learning_rate": 9.066666666666667e-05, |
| "loss": 0.0072, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.8171206225680934, |
| "grad_norm": 0.047289494425058365, |
| "learning_rate": 9.288888888888888e-05, |
| "loss": 0.0074, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.8171206225680934, |
| "eval_loss": 0.011569861322641373, |
| "eval_runtime": 136.4761, |
| "eval_samples_per_second": 3.737, |
| "eval_steps_per_second": 0.938, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.8365758754863813, |
| "grad_norm": 0.036366503685712814, |
| "learning_rate": 9.511111111111112e-05, |
| "loss": 0.007, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.8560311284046692, |
| "grad_norm": 0.07178617268800735, |
| "learning_rate": 9.733333333333333e-05, |
| "loss": 0.0073, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.8560311284046692, |
| "eval_loss": 0.010845971293747425, |
| "eval_runtime": 136.7794, |
| "eval_samples_per_second": 3.729, |
| "eval_steps_per_second": 0.936, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.8754863813229572, |
| "grad_norm": 0.042044900357723236, |
| "learning_rate": 9.955555555555556e-05, |
| "loss": 0.0069, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.8949416342412452, |
| "grad_norm": 0.18266713619232178, |
| "learning_rate": 0.00010177777777777777, |
| "loss": 0.007, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.8949416342412452, |
| "eval_loss": 0.012411113828420639, |
| "eval_runtime": 136.7046, |
| "eval_samples_per_second": 3.731, |
| "eval_steps_per_second": 0.936, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.914396887159533, |
| "grad_norm": 0.04458538442850113, |
| "learning_rate": 0.00010400000000000001, |
| "loss": 0.0077, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.933852140077821, |
| "grad_norm": 0.04118124023079872, |
| "learning_rate": 0.00010622222222222222, |
| "loss": 0.0071, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.933852140077821, |
| "eval_loss": 0.016743971034884453, |
| "eval_runtime": 136.6604, |
| "eval_samples_per_second": 3.732, |
| "eval_steps_per_second": 0.937, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.953307392996109, |
| "grad_norm": 0.042440321296453476, |
| "learning_rate": 0.00010844444444444444, |
| "loss": 0.0071, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.9727626459143969, |
| "grad_norm": 0.03553004935383797, |
| "learning_rate": 0.00011066666666666668, |
| "loss": 0.0073, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.9727626459143969, |
| "eval_loss": 0.022762756794691086, |
| "eval_runtime": 136.4551, |
| "eval_samples_per_second": 3.737, |
| "eval_steps_per_second": 0.938, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.9922178988326849, |
| "grad_norm": 0.06393753737211227, |
| "learning_rate": 0.0001128888888888889, |
| "loss": 0.0076, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.0116731517509727, |
| "grad_norm": 0.030655624344944954, |
| "learning_rate": 0.00011511111111111112, |
| "loss": 0.0073, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.0116731517509727, |
| "eval_loss": 0.024547625333070755, |
| "eval_runtime": 136.5694, |
| "eval_samples_per_second": 3.734, |
| "eval_steps_per_second": 0.937, |
| "step": 260 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1799, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 30, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 12 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.535511208042892e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
