| { | |
| "best_metric": 0.4244471490383148, | |
| "best_model_checkpoint": "autotrain-wewh0-x81n8/checkpoint-60", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.6797, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6762, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6572, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.631, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5082, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.525, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8275862068965517, | |
| "eval_auc": 0.5322916666666666, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.4591643214225769, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.3931, | |
| "eval_samples_per_second": 295.124, | |
| "eval_steps_per_second": 20.353, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.4126, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3881, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.7125, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3655, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.4883, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.6153, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4142, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8275862068965517, | |
| "eval_auc": 0.6164062499999999, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.4668600261211395, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.4042, | |
| "eval_samples_per_second": 286.979, | |
| "eval_steps_per_second": 19.792, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.962962962962963e-05, | |
| "loss": 0.533, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.925925925925926e-05, | |
| "loss": 0.2934, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.5174, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.851851851851852e-05, | |
| "loss": 0.4464, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.4544, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.796296296296296e-05, | |
| "loss": 0.5618, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.759259259259259e-05, | |
| "loss": 0.4412, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8275862068965517, | |
| "eval_auc": 0.6213541666666668, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.49061912298202515, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.385, | |
| "eval_samples_per_second": 301.322, | |
| "eval_steps_per_second": 20.781, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.5116, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.685185185185185e-05, | |
| "loss": 0.4371, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 4.648148148148148e-05, | |
| "loss": 0.3013, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.1664, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 4.5740740740740745e-05, | |
| "loss": 0.2152, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.8311, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.3329, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.462962962962963e-05, | |
| "loss": 0.1868, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8275862068965517, | |
| "eval_auc": 0.7067708333333333, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.4244471490383148, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.3986, | |
| "eval_samples_per_second": 291.021, | |
| "eval_steps_per_second": 20.07, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 30520882421760.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |