| { | |
| "best_metric": 0.7794117647058824, | |
| "best_model_checkpoint": "convnext-tiny-224-finetuned-papsmear/checkpoint-269", | |
| "epoch": 14.805194805194805, | |
| "eval_steps": 500, | |
| "global_step": 285, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 2.7057783603668213, | |
| "learning_rate": 1.7241379310344828e-05, | |
| "loss": 1.8151, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.987012987012987, | |
| "eval_accuracy": 0.34558823529411764, | |
| "eval_loss": 1.6491025686264038, | |
| "eval_runtime": 28.2457, | |
| "eval_samples_per_second": 4.815, | |
| "eval_steps_per_second": 0.319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0389610389610389, | |
| "grad_norm": 2.921726703643799, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 1.7253, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5584415584415585, | |
| "grad_norm": 2.692876100540161, | |
| "learning_rate": 4.9804687500000004e-05, | |
| "loss": 1.6104, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.974025974025974, | |
| "eval_accuracy": 0.4264705882352941, | |
| "eval_loss": 1.4321942329406738, | |
| "eval_runtime": 28.4975, | |
| "eval_samples_per_second": 4.772, | |
| "eval_steps_per_second": 0.316, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0779220779220777, | |
| "grad_norm": 4.681018829345703, | |
| "learning_rate": 4.78515625e-05, | |
| "loss": 1.4815, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.5974025974025974, | |
| "grad_norm": 6.916051864624023, | |
| "learning_rate": 4.58984375e-05, | |
| "loss": 1.4002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.961038961038961, | |
| "eval_accuracy": 0.5882352941176471, | |
| "eval_loss": 1.2286293506622314, | |
| "eval_runtime": 28.7786, | |
| "eval_samples_per_second": 4.726, | |
| "eval_steps_per_second": 0.313, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.116883116883117, | |
| "grad_norm": 6.231860637664795, | |
| "learning_rate": 4.3945312500000005e-05, | |
| "loss": 1.2972, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 5.155839443206787, | |
| "learning_rate": 4.1992187500000003e-05, | |
| "loss": 1.203, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6544117647058824, | |
| "eval_loss": 1.0558613538742065, | |
| "eval_runtime": 29.1144, | |
| "eval_samples_per_second": 4.671, | |
| "eval_steps_per_second": 0.309, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.1558441558441555, | |
| "grad_norm": 4.061820983886719, | |
| "learning_rate": 4.00390625e-05, | |
| "loss": 1.1157, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.675324675324675, | |
| "grad_norm": 6.426987171173096, | |
| "learning_rate": 3.80859375e-05, | |
| "loss": 1.047, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.987012987012987, | |
| "eval_accuracy": 0.6764705882352942, | |
| "eval_loss": 0.9356656074523926, | |
| "eval_runtime": 28.6745, | |
| "eval_samples_per_second": 4.743, | |
| "eval_steps_per_second": 0.314, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.194805194805195, | |
| "grad_norm": 8.75316333770752, | |
| "learning_rate": 3.6132812500000005e-05, | |
| "loss": 0.9786, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 18.9505615234375, | |
| "learning_rate": 3.41796875e-05, | |
| "loss": 0.9083, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.974025974025974, | |
| "eval_accuracy": 0.7279411764705882, | |
| "eval_loss": 0.8477045893669128, | |
| "eval_runtime": 28.1374, | |
| "eval_samples_per_second": 4.833, | |
| "eval_steps_per_second": 0.32, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.233766233766234, | |
| "grad_norm": 10.591647148132324, | |
| "learning_rate": 3.22265625e-05, | |
| "loss": 0.8763, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.753246753246753, | |
| "grad_norm": 22.407350540161133, | |
| "learning_rate": 3.02734375e-05, | |
| "loss": 0.8756, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.961038961038961, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.7761698365211487, | |
| "eval_runtime": 28.746, | |
| "eval_samples_per_second": 4.731, | |
| "eval_steps_per_second": 0.313, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 14.485121726989746, | |
| "learning_rate": 2.83203125e-05, | |
| "loss": 0.7762, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.792207792207792, | |
| "grad_norm": 12.85451889038086, | |
| "learning_rate": 2.63671875e-05, | |
| "loss": 0.7853, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.7257648706436157, | |
| "eval_runtime": 28.5887, | |
| "eval_samples_per_second": 4.757, | |
| "eval_steps_per_second": 0.315, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 8.311688311688311, | |
| "grad_norm": 15.272162437438965, | |
| "learning_rate": 2.44140625e-05, | |
| "loss": 0.7991, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.831168831168831, | |
| "grad_norm": 23.24527931213379, | |
| "learning_rate": 2.24609375e-05, | |
| "loss": 0.7198, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.987012987012987, | |
| "eval_accuracy": 0.7573529411764706, | |
| "eval_loss": 0.7022554874420166, | |
| "eval_runtime": 28.5238, | |
| "eval_samples_per_second": 4.768, | |
| "eval_steps_per_second": 0.316, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 9.35064935064935, | |
| "grad_norm": 41.553192138671875, | |
| "learning_rate": 2.05078125e-05, | |
| "loss": 0.7277, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.87012987012987, | |
| "grad_norm": 17.23739242553711, | |
| "learning_rate": 1.85546875e-05, | |
| "loss": 0.7151, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.974025974025974, | |
| "eval_accuracy": 0.7573529411764706, | |
| "eval_loss": 0.6756320595741272, | |
| "eval_runtime": 28.3293, | |
| "eval_samples_per_second": 4.801, | |
| "eval_steps_per_second": 0.318, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 10.38961038961039, | |
| "grad_norm": 38.664608001708984, | |
| "learning_rate": 1.66015625e-05, | |
| "loss": 0.7012, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.909090909090908, | |
| "grad_norm": 16.148284912109375, | |
| "learning_rate": 1.4648437500000001e-05, | |
| "loss": 0.7049, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.96103896103896, | |
| "eval_accuracy": 0.7573529411764706, | |
| "eval_loss": 0.6492503881454468, | |
| "eval_runtime": 28.3206, | |
| "eval_samples_per_second": 4.802, | |
| "eval_steps_per_second": 0.318, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 11.50155258178711, | |
| "learning_rate": 1.2695312500000001e-05, | |
| "loss": 0.6742, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 11.948051948051948, | |
| "grad_norm": 7.969295978546143, | |
| "learning_rate": 1.0742187500000001e-05, | |
| "loss": 0.6387, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7720588235294118, | |
| "eval_loss": 0.6256288290023804, | |
| "eval_runtime": 28.2852, | |
| "eval_samples_per_second": 4.808, | |
| "eval_steps_per_second": 0.318, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 12.467532467532468, | |
| "grad_norm": 23.28668975830078, | |
| "learning_rate": 8.789062500000001e-06, | |
| "loss": 0.6393, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 12.987012987012987, | |
| "grad_norm": 20.532899856567383, | |
| "learning_rate": 6.8359375e-06, | |
| "loss": 0.6387, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.987012987012987, | |
| "eval_accuracy": 0.7720588235294118, | |
| "eval_loss": 0.6295046806335449, | |
| "eval_runtime": 27.9632, | |
| "eval_samples_per_second": 4.864, | |
| "eval_steps_per_second": 0.322, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 13.506493506493506, | |
| "grad_norm": 17.684839248657227, | |
| "learning_rate": 4.8828125e-06, | |
| "loss": 0.6233, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 13.974025974025974, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.6032511591911316, | |
| "eval_runtime": 28.638, | |
| "eval_samples_per_second": 4.749, | |
| "eval_steps_per_second": 0.314, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 14.025974025974026, | |
| "grad_norm": 7.872328281402588, | |
| "learning_rate": 2.9296875e-06, | |
| "loss": 0.6251, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 14.545454545454545, | |
| "grad_norm": 14.434428215026855, | |
| "learning_rate": 9.765625e-07, | |
| "loss": 0.632, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 14.805194805194805, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.6009563207626343, | |
| "eval_runtime": 28.5598, | |
| "eval_samples_per_second": 4.762, | |
| "eval_steps_per_second": 0.315, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 14.805194805194805, | |
| "step": 285, | |
| "total_flos": 4.55564191810388e+17, | |
| "train_loss": 0.9492872991059956, | |
| "train_runtime": 4189.5915, | |
| "train_samples_per_second": 4.382, | |
| "train_steps_per_second": 0.068 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 285, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "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": 4.55564191810388e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |