| { | |
| "best_metric": 0.26321205496788025, | |
| "best_model_checkpoint": "autotrain-prj-image-classification-for-slides/checkpoint-48", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 48, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.8158, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.7927, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.8798, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.8946, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.735, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.5985, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.5549, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.3827, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5742, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.3724, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.4903, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.9232, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.75, | |
| "eval_auc": 0.6296296296296297, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5604451298713684, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.9668, | |
| "eval_samples_per_second": 24.824, | |
| "eval_steps_per_second": 2.069, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2256, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.9537037037037035e-05, | |
| "loss": 0.238, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 1.0486, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.2961, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.5506, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.2733, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.768518518518519e-05, | |
| "loss": 0.2415, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.1263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.675925925925926e-05, | |
| "loss": 0.1261, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.2731, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.1118, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.6111, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_auc": 0.8333333333333334, | |
| "eval_f1": 0.6, | |
| "eval_loss": 0.3809445798397064, | |
| "eval_precision": 0.75, | |
| "eval_recall": 0.5, | |
| "eval_runtime": 1.1816, | |
| "eval_samples_per_second": 20.311, | |
| "eval_steps_per_second": 1.693, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.490740740740741e-05, | |
| "loss": 0.293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0621, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.0873, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.0653, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.1292, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.1142, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.212962962962963e-05, | |
| "loss": 0.0272, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.0551, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.1203703703703705e-05, | |
| "loss": 0.1881, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.047, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.3178, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.4922, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.875, | |
| "eval_auc": 0.8148148148148148, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.4897962510585785, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.5, | |
| "eval_runtime": 0.91, | |
| "eval_samples_per_second": 26.373, | |
| "eval_steps_per_second": 2.198, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.0111, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0638, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.8425925925925924e-05, | |
| "loss": 0.0097, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.0402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0386, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1937, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 3.6574074074074076e-05, | |
| "loss": 0.5758, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.1015, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.564814814814815e-05, | |
| "loss": 0.0208, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.0489, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.0167, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.0876, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_auc": 0.9351851851851851, | |
| "eval_f1": 0.8333333333333334, | |
| "eval_loss": 0.26321205496788025, | |
| "eval_precision": 0.8333333333333334, | |
| "eval_recall": 0.8333333333333334, | |
| "eval_runtime": 0.8986, | |
| "eval_samples_per_second": 26.708, | |
| "eval_steps_per_second": 2.226, | |
| "step": 48 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 3.1148228745363456e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |