| { | |
| "best_metric": 0.08235077559947968, | |
| "best_model_checkpoint": "autotrain-fzudm-korrh/checkpoint-450", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.8473684787750244, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 2.4944, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 2.497635841369629, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 2.461, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 2.6727840900421143, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 2.3714, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 3.3866329193115234, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 2.3521, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 3.0266103744506836, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 2.2204, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 5.708084583282471, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 2.0935, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 2.413567543029785, | |
| "learning_rate": 4.950617283950618e-05, | |
| "loss": 1.9364, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 2.816483497619629, | |
| "learning_rate": 4.864197530864198e-05, | |
| "loss": 1.7083, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 3.948235273361206, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 1.6135, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 3.652134418487549, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 1.4522, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 3.7319400310516357, | |
| "learning_rate": 4.604938271604938e-05, | |
| "loss": 1.2261, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.1848716735839844, | |
| "learning_rate": 4.518518518518519e-05, | |
| "loss": 1.1589, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 2.331566572189331, | |
| "learning_rate": 4.432098765432099e-05, | |
| "loss": 0.9291, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 2.437225818634033, | |
| "learning_rate": 4.345679012345679e-05, | |
| "loss": 0.882, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 3.426419734954834, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.8062, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 27.056604385375977, | |
| "learning_rate": 4.17283950617284e-05, | |
| "loss": 0.8794, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 2.7623507976531982, | |
| "learning_rate": 4.0864197530864204e-05, | |
| "loss": 0.7981, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 1.0507307052612305, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6203, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 6.599649429321289, | |
| "learning_rate": 3.91358024691358e-05, | |
| "loss": 0.5586, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 1.9725279808044434, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.4613, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.9860884547233582, | |
| "learning_rate": 3.740740740740741e-05, | |
| "loss": 0.4811, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9866666666666667, | |
| "eval_f1_macro": 0.9824074074074073, | |
| "eval_f1_micro": 0.9866666666666668, | |
| "eval_f1_weighted": 0.9866666666666667, | |
| "eval_loss": 0.47558584809303284, | |
| "eval_precision_macro": 0.9824074074074073, | |
| "eval_precision_micro": 0.9866666666666667, | |
| "eval_precision_weighted": 0.9866666666666667, | |
| "eval_recall_macro": 0.9824074074074073, | |
| "eval_recall_micro": 0.9866666666666667, | |
| "eval_recall_weighted": 0.9866666666666667, | |
| "eval_runtime": 226.8158, | |
| "eval_samples_per_second": 1.323, | |
| "eval_steps_per_second": 0.084, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 1.572788953781128, | |
| "learning_rate": 3.654320987654321e-05, | |
| "loss": 0.4706, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 1.8391231298446655, | |
| "learning_rate": 3.567901234567901e-05, | |
| "loss": 0.4863, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.4992858171463013, | |
| "learning_rate": 3.481481481481482e-05, | |
| "loss": 0.3355, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 16.52165412902832, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.4208, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.8345728516578674, | |
| "learning_rate": 3.308641975308642e-05, | |
| "loss": 0.3104, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 1.0207165479660034, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.2553, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 4.886829853057861, | |
| "learning_rate": 3.135802469135803e-05, | |
| "loss": 0.3013, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.7672041654586792, | |
| "learning_rate": 3.0493827160493827e-05, | |
| "loss": 0.2357, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 1.1569510698318481, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.2197, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.44843003153800964, | |
| "learning_rate": 2.8765432098765432e-05, | |
| "loss": 0.1555, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.48682141304016113, | |
| "learning_rate": 2.7901234567901235e-05, | |
| "loss": 0.1917, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.6816083788871765, | |
| "learning_rate": 2.7037037037037037e-05, | |
| "loss": 0.1292, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.38534966111183167, | |
| "learning_rate": 2.617283950617284e-05, | |
| "loss": 0.1009, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.5634031891822815, | |
| "learning_rate": 2.5308641975308646e-05, | |
| "loss": 0.1725, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 1.3090158700942993, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.1355, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.2513110041618347, | |
| "learning_rate": 2.3580246913580247e-05, | |
| "loss": 0.077, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 4.024202346801758, | |
| "learning_rate": 2.271604938271605e-05, | |
| "loss": 0.0972, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.8751043677330017, | |
| "learning_rate": 2.1851851851851852e-05, | |
| "loss": 0.087, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.2541038990020752, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.0759, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.29228782653808594, | |
| "learning_rate": 2.0123456790123457e-05, | |
| "loss": 0.0715, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.42550790309906006, | |
| "learning_rate": 1.925925925925926e-05, | |
| "loss": 0.0689, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.99, | |
| "eval_f1_macro": 0.986759581881533, | |
| "eval_f1_micro": 0.99, | |
| "eval_f1_weighted": 0.9899790940766551, | |
| "eval_loss": 0.10256664454936981, | |
| "eval_precision_macro": 0.9871615312791784, | |
| "eval_precision_micro": 0.99, | |
| "eval_precision_weighted": 0.9901213818860879, | |
| "eval_recall_macro": 0.986574074074074, | |
| "eval_recall_micro": 0.99, | |
| "eval_recall_weighted": 0.99, | |
| "eval_runtime": 229.5963, | |
| "eval_samples_per_second": 1.307, | |
| "eval_steps_per_second": 0.083, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 0.2770730257034302, | |
| "learning_rate": 1.8395061728395062e-05, | |
| "loss": 0.1148, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 0.2336236983537674, | |
| "learning_rate": 1.7530864197530865e-05, | |
| "loss": 0.1179, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 0.32252636551856995, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0629, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 0.2286107987165451, | |
| "learning_rate": 1.580246913580247e-05, | |
| "loss": 0.112, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 0.34691134095191956, | |
| "learning_rate": 1.4938271604938272e-05, | |
| "loss": 0.0633, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.25500062108039856, | |
| "learning_rate": 1.4074074074074075e-05, | |
| "loss": 0.0512, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 0.44312888383865356, | |
| "learning_rate": 1.3209876543209876e-05, | |
| "loss": 0.0604, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 0.3760792016983032, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.0595, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 0.2281612902879715, | |
| "learning_rate": 1.1481481481481482e-05, | |
| "loss": 0.0619, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 0.2144249677658081, | |
| "learning_rate": 1.0617283950617285e-05, | |
| "loss": 0.0448, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 0.16961945593357086, | |
| "learning_rate": 9.753086419753086e-06, | |
| "loss": 0.0524, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 0.21082834899425507, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0417, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 0.21366652846336365, | |
| "learning_rate": 8.02469135802469e-06, | |
| "loss": 0.0473, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 0.19165301322937012, | |
| "learning_rate": 7.160493827160494e-06, | |
| "loss": 0.039, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 0.14223778247833252, | |
| "learning_rate": 6.296296296296296e-06, | |
| "loss": 0.0362, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 0.22010144591331482, | |
| "learning_rate": 5.432098765432099e-06, | |
| "loss": 0.112, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 0.2625073492527008, | |
| "learning_rate": 4.567901234567902e-06, | |
| "loss": 0.0441, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.13207264244556427, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.0393, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 0.14408986270427704, | |
| "learning_rate": 2.8395061728395062e-06, | |
| "loss": 0.047, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": 0.26891738176345825, | |
| "learning_rate": 1.9753086419753087e-06, | |
| "loss": 0.048, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 0.28397634625434875, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.0439, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 0.14882226288318634, | |
| "learning_rate": 2.469135802469136e-07, | |
| "loss": 0.0495, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.99, | |
| "eval_f1_macro": 0.986759581881533, | |
| "eval_f1_micro": 0.99, | |
| "eval_f1_weighted": 0.9899790940766551, | |
| "eval_loss": 0.08235077559947968, | |
| "eval_precision_macro": 0.9871615312791784, | |
| "eval_precision_micro": 0.99, | |
| "eval_precision_weighted": 0.9901213818860879, | |
| "eval_recall_macro": 0.986574074074074, | |
| "eval_recall_micro": 0.99, | |
| "eval_recall_weighted": 0.99, | |
| "eval_runtime": 236.6057, | |
| "eval_samples_per_second": 1.268, | |
| "eval_steps_per_second": 0.08, | |
| "step": 450 | |
| } | |
| ], | |
| "logging_steps": 7, | |
| "max_steps": 450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1044230397530112.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |