| { | |
| "best_metric": 1.1656934022903442, | |
| "best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-160", | |
| "epoch": 18.823529411764707, | |
| "eval_steps": 500, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9411764705882353, | |
| "eval_accuracy": { | |
| "accuracy": 0.18382352941176472 | |
| }, | |
| "eval_logLoss": 1.6071832180023193, | |
| "eval_loss": 1.6071830987930298, | |
| "eval_runtime": 244.9974, | |
| "eval_samples_per_second": 1.11, | |
| "eval_steps_per_second": 0.037, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 1.0974622964859009, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.6101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.31985294117647056 | |
| }, | |
| "eval_logLoss": 1.5668261051177979, | |
| "eval_loss": 1.5668261051177979, | |
| "eval_runtime": 4.797, | |
| "eval_samples_per_second": 56.702, | |
| "eval_steps_per_second": 1.876, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 1.2453666925430298, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.5645, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "eval_accuracy": { | |
| "accuracy": 0.33455882352941174 | |
| }, | |
| "eval_logLoss": 1.5246020555496216, | |
| "eval_loss": 1.5246021747589111, | |
| "eval_runtime": 4.7926, | |
| "eval_samples_per_second": 56.754, | |
| "eval_steps_per_second": 1.878, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 1.36457097530365, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 1.4902, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.4007352941176471 | |
| }, | |
| "eval_logLoss": 1.4773920774459839, | |
| "eval_loss": 1.4773920774459839, | |
| "eval_runtime": 4.9915, | |
| "eval_samples_per_second": 54.493, | |
| "eval_steps_per_second": 1.803, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 1.3080309629440308, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.4243, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "eval_accuracy": { | |
| "accuracy": 0.44485294117647056 | |
| }, | |
| "eval_logLoss": 1.4283257722854614, | |
| "eval_loss": 1.4283257722854614, | |
| "eval_runtime": 4.7862, | |
| "eval_samples_per_second": 56.831, | |
| "eval_steps_per_second": 1.88, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 1.7825312614440918, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 1.3502, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.48161764705882354 | |
| }, | |
| "eval_logLoss": 1.3747049570083618, | |
| "eval_loss": 1.3747047185897827, | |
| "eval_runtime": 4.9735, | |
| "eval_samples_per_second": 54.69, | |
| "eval_steps_per_second": 1.81, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "eval_accuracy": { | |
| "accuracy": 0.48161764705882354 | |
| }, | |
| "eval_logLoss": 1.3332045078277588, | |
| "eval_loss": 1.3332043886184692, | |
| "eval_runtime": 4.9941, | |
| "eval_samples_per_second": 54.464, | |
| "eval_steps_per_second": 1.802, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 1.616268515586853, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 1.2906, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.5036764705882353 | |
| }, | |
| "eval_logLoss": 1.2978487014770508, | |
| "eval_loss": 1.2978484630584717, | |
| "eval_runtime": 4.9213, | |
| "eval_samples_per_second": 55.27, | |
| "eval_steps_per_second": 1.829, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 1.5584542751312256, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.2371, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "eval_accuracy": { | |
| "accuracy": 0.5147058823529411 | |
| }, | |
| "eval_logLoss": 1.2702081203460693, | |
| "eval_loss": 1.2702082395553589, | |
| "eval_runtime": 5.014, | |
| "eval_samples_per_second": 54.248, | |
| "eval_steps_per_second": 1.795, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 1.5939627885818481, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.1856, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.5404411764705882 | |
| }, | |
| "eval_logLoss": 1.243437647819519, | |
| "eval_loss": 1.2434377670288086, | |
| "eval_runtime": 4.901, | |
| "eval_samples_per_second": 55.499, | |
| "eval_steps_per_second": 1.836, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 1.362315058708191, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 1.1506, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "eval_accuracy": { | |
| "accuracy": 0.5477941176470589 | |
| }, | |
| "eval_logLoss": 1.2299580574035645, | |
| "eval_loss": 1.2299582958221436, | |
| "eval_runtime": 4.9331, | |
| "eval_samples_per_second": 55.138, | |
| "eval_steps_per_second": 1.824, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 1.4996492862701416, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.0987, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.5588235294117647 | |
| }, | |
| "eval_logLoss": 1.2087745666503906, | |
| "eval_loss": 1.2087748050689697, | |
| "eval_runtime": 4.8571, | |
| "eval_samples_per_second": 56.0, | |
| "eval_steps_per_second": 1.853, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 1.7451958656311035, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 1.0758, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "eval_accuracy": { | |
| "accuracy": 0.5514705882352942 | |
| }, | |
| "eval_logLoss": 1.1948641538619995, | |
| "eval_loss": 1.19486403465271, | |
| "eval_runtime": 4.994, | |
| "eval_samples_per_second": 54.465, | |
| "eval_steps_per_second": 1.802, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.5588235294117647 | |
| }, | |
| "eval_logLoss": 1.1896252632141113, | |
| "eval_loss": 1.1896252632141113, | |
| "eval_runtime": 4.9288, | |
| "eval_samples_per_second": 55.186, | |
| "eval_steps_per_second": 1.826, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 14.117647058823529, | |
| "grad_norm": 1.9521229267120361, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 1.0483, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 14.941176470588236, | |
| "eval_accuracy": { | |
| "accuracy": 0.5698529411764706 | |
| }, | |
| "eval_logLoss": 1.177284598350525, | |
| "eval_loss": 1.177284598350525, | |
| "eval_runtime": 4.8123, | |
| "eval_samples_per_second": 56.521, | |
| "eval_steps_per_second": 1.87, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 15.294117647058824, | |
| "grad_norm": 1.6353868246078491, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 1.0346, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.5735294117647058 | |
| }, | |
| "eval_logLoss": 1.1718555688858032, | |
| "eval_loss": 1.1718555688858032, | |
| "eval_runtime": 4.8108, | |
| "eval_samples_per_second": 56.539, | |
| "eval_steps_per_second": 1.871, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 16.470588235294116, | |
| "grad_norm": 1.8729331493377686, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 1.0215, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 16.941176470588236, | |
| "eval_accuracy": { | |
| "accuracy": 0.5698529411764706 | |
| }, | |
| "eval_logLoss": 1.170174241065979, | |
| "eval_loss": 1.1701741218566895, | |
| "eval_runtime": 4.747, | |
| "eval_samples_per_second": 57.299, | |
| "eval_steps_per_second": 1.896, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 17.647058823529413, | |
| "grad_norm": 2.009471893310547, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 1.0177, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.5772058823529411 | |
| }, | |
| "eval_logLoss": 1.1665880680084229, | |
| "eval_loss": 1.1665880680084229, | |
| "eval_runtime": 4.8261, | |
| "eval_samples_per_second": 56.361, | |
| "eval_steps_per_second": 1.865, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 18.823529411764707, | |
| "grad_norm": 1.6420903205871582, | |
| "learning_rate": 0.0, | |
| "loss": 0.9956, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 18.823529411764707, | |
| "eval_accuracy": { | |
| "accuracy": 0.5808823529411765 | |
| }, | |
| "eval_logLoss": 1.1656935214996338, | |
| "eval_loss": 1.1656934022903442, | |
| "eval_runtime": 5.2789, | |
| "eval_samples_per_second": 51.526, | |
| "eval_steps_per_second": 1.705, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 18.823529411764707, | |
| "step": 160, | |
| "total_flos": 5.146567075115827e+17, | |
| "train_loss": 1.2247119784355163, | |
| "train_runtime": 1875.9294, | |
| "train_samples_per_second": 11.6, | |
| "train_steps_per_second": 0.085 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "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": 5.146567075115827e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |