| { | |
| "best_metric": 0.9782797567332754, | |
| "best_model_checkpoint": "convnext-large-224-finetuned-dog-vs-cat/checkpoint-492", | |
| "epoch": 2.986342943854325, | |
| "eval_steps": 500, | |
| "global_step": 492, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06069802731411229, | |
| "grad_norm": 1.2104277610778809, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6885, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12139605462822459, | |
| "grad_norm": 1.1519063711166382, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6854, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18209408194233687, | |
| "grad_norm": 1.203668475151062, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6788, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24279210925644917, | |
| "grad_norm": 1.3230795860290527, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6664, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.30349013657056145, | |
| "grad_norm": 1.1332818269729614, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6511, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36418816388467373, | |
| "grad_norm": 1.1424264907836914, | |
| "learning_rate": 4.8868778280542986e-05, | |
| "loss": 0.6321, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.424886191198786, | |
| "grad_norm": 1.1293511390686035, | |
| "learning_rate": 4.7737556561085976e-05, | |
| "loss": 0.6115, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.48558421851289835, | |
| "grad_norm": 1.1212339401245117, | |
| "learning_rate": 4.660633484162896e-05, | |
| "loss": 0.5957, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5462822458270106, | |
| "grad_norm": 0.9936708807945251, | |
| "learning_rate": 4.547511312217195e-05, | |
| "loss": 0.5815, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6069802731411229, | |
| "grad_norm": 1.0561779737472534, | |
| "learning_rate": 4.434389140271493e-05, | |
| "loss": 0.5583, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6676783004552352, | |
| "grad_norm": 0.9779506921768188, | |
| "learning_rate": 4.321266968325792e-05, | |
| "loss": 0.5541, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7283763277693475, | |
| "grad_norm": 0.8941373825073242, | |
| "learning_rate": 4.2081447963800907e-05, | |
| "loss": 0.5408, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7890743550834598, | |
| "grad_norm": 0.9414535164833069, | |
| "learning_rate": 4.095022624434389e-05, | |
| "loss": 0.5288, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.849772382397572, | |
| "grad_norm": 0.8809621334075928, | |
| "learning_rate": 3.981900452488688e-05, | |
| "loss": 0.5194, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9104704097116844, | |
| "grad_norm": 0.8484501838684082, | |
| "learning_rate": 3.868778280542987e-05, | |
| "loss": 0.5038, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9711684370257967, | |
| "grad_norm": 0.8708747625350952, | |
| "learning_rate": 3.7556561085972854e-05, | |
| "loss": 0.496, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9954476479514416, | |
| "eval_loss": 0.4791725277900696, | |
| "eval_recall": 0.9200695047784535, | |
| "eval_runtime": 60.2024, | |
| "eval_samples_per_second": 38.885, | |
| "eval_steps_per_second": 1.229, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.031866464339909, | |
| "grad_norm": 0.8436847925186157, | |
| "learning_rate": 3.642533936651584e-05, | |
| "loss": 0.4861, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0925644916540211, | |
| "grad_norm": 0.7819939851760864, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.4844, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.1532625189681336, | |
| "grad_norm": 0.847568929195404, | |
| "learning_rate": 3.416289592760181e-05, | |
| "loss": 0.4673, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2139605462822458, | |
| "grad_norm": 0.7669057846069336, | |
| "learning_rate": 3.3031674208144794e-05, | |
| "loss": 0.4583, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.274658573596358, | |
| "grad_norm": 0.766395092010498, | |
| "learning_rate": 3.1900452488687784e-05, | |
| "loss": 0.4473, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.3353566009104705, | |
| "grad_norm": 0.8044094443321228, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.4531, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.3960546282245827, | |
| "grad_norm": 0.7774869799613953, | |
| "learning_rate": 2.9638009049773758e-05, | |
| "loss": 0.439, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.456752655538695, | |
| "grad_norm": 0.7320767641067505, | |
| "learning_rate": 2.850678733031674e-05, | |
| "loss": 0.436, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.5174506828528074, | |
| "grad_norm": 0.7127722501754761, | |
| "learning_rate": 2.737556561085973e-05, | |
| "loss": 0.4314, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.5781487101669196, | |
| "grad_norm": 0.7172250151634216, | |
| "learning_rate": 2.6244343891402718e-05, | |
| "loss": 0.4302, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.6388467374810318, | |
| "grad_norm": 0.7075967192649841, | |
| "learning_rate": 2.51131221719457e-05, | |
| "loss": 0.4174, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.699544764795144, | |
| "grad_norm": 0.7165055871009827, | |
| "learning_rate": 2.3981900452488688e-05, | |
| "loss": 0.4174, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.7602427921092565, | |
| "grad_norm": 0.6554096341133118, | |
| "learning_rate": 2.2850678733031675e-05, | |
| "loss": 0.4193, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.8209408194233687, | |
| "grad_norm": 0.7225818037986755, | |
| "learning_rate": 2.1719457013574662e-05, | |
| "loss": 0.3996, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.8816388467374812, | |
| "grad_norm": 0.6873008012771606, | |
| "learning_rate": 2.058823529411765e-05, | |
| "loss": 0.4011, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.9423368740515934, | |
| "grad_norm": 0.6827677488327026, | |
| "learning_rate": 1.9457013574660635e-05, | |
| "loss": 0.3996, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.9969650986342944, | |
| "eval_loss": 0.3836117684841156, | |
| "eval_recall": 0.9765421372719374, | |
| "eval_runtime": 60.251, | |
| "eval_samples_per_second": 38.854, | |
| "eval_steps_per_second": 1.228, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 2.0030349013657056, | |
| "grad_norm": 0.6939449906349182, | |
| "learning_rate": 1.832579185520362e-05, | |
| "loss": 0.4015, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.063732928679818, | |
| "grad_norm": 0.6604830026626587, | |
| "learning_rate": 1.7194570135746606e-05, | |
| "loss": 0.3934, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.12443095599393, | |
| "grad_norm": 0.6591904759407043, | |
| "learning_rate": 1.6063348416289596e-05, | |
| "loss": 0.3956, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.1851289833080423, | |
| "grad_norm": 0.6776930689811707, | |
| "learning_rate": 1.493212669683258e-05, | |
| "loss": 0.3904, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.245827010622155, | |
| "grad_norm": 0.6641884446144104, | |
| "learning_rate": 1.3800904977375568e-05, | |
| "loss": 0.3836, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.306525037936267, | |
| "grad_norm": 0.6640185117721558, | |
| "learning_rate": 1.2669683257918553e-05, | |
| "loss": 0.3849, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.3672230652503794, | |
| "grad_norm": 0.6439262628555298, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 0.3847, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.4279210925644916, | |
| "grad_norm": 0.6991675496101379, | |
| "learning_rate": 1.0407239819004526e-05, | |
| "loss": 0.3789, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.488619119878604, | |
| "grad_norm": 0.6298201680183411, | |
| "learning_rate": 9.276018099547511e-06, | |
| "loss": 0.3769, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.549317147192716, | |
| "grad_norm": 0.6205734014511108, | |
| "learning_rate": 8.144796380090498e-06, | |
| "loss": 0.3769, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.6100151745068283, | |
| "grad_norm": 0.6230446696281433, | |
| "learning_rate": 7.013574660633485e-06, | |
| "loss": 0.3802, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.670713201820941, | |
| "grad_norm": 0.6412050127983093, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.3805, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.731411229135053, | |
| "grad_norm": 0.6700997948646545, | |
| "learning_rate": 4.751131221719457e-06, | |
| "loss": 0.3725, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.7921092564491654, | |
| "grad_norm": 0.6392331123352051, | |
| "learning_rate": 3.619909502262444e-06, | |
| "loss": 0.3729, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.8528072837632776, | |
| "grad_norm": 0.6410810351371765, | |
| "learning_rate": 2.48868778280543e-06, | |
| "loss": 0.3582, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.91350531107739, | |
| "grad_norm": 0.6067666411399841, | |
| "learning_rate": 1.3574660633484164e-06, | |
| "loss": 0.3758, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.9742033383915025, | |
| "grad_norm": 0.6219173669815063, | |
| "learning_rate": 2.2624434389140275e-07, | |
| "loss": 0.373, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.986342943854325, | |
| "eval_loss": 0.35858574509620667, | |
| "eval_recall": 0.9782797567332754, | |
| "eval_runtime": 61.7184, | |
| "eval_samples_per_second": 37.93, | |
| "eval_steps_per_second": 1.199, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 2.986342943854325, | |
| "step": 492, | |
| "total_flos": 1.1154611028241981e+19, | |
| "train_loss": 0.4681245271510225, | |
| "train_runtime": 1816.2465, | |
| "train_samples_per_second": 34.801, | |
| "train_steps_per_second": 0.271 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 492, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1154611028241981e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |