| { | |
| "best_metric": 0.18809613585472107, | |
| "best_model_checkpoint": "autotrain-28eqp-t2e16/checkpoint-150", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.269129753112793, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.6984, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 4.074235916137695, | |
| "learning_rate": 4.962962962962963e-05, | |
| "loss": 0.6593, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 5.697342395782471, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.4673, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 5.995659351348877, | |
| "learning_rate": 4.3703703703703705e-05, | |
| "loss": 0.226, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 6.6095428466796875, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.1767, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.2729267477989197, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.4345, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8968481375358166, | |
| "eval_auc": 0.9792817679558011, | |
| "eval_f1": 0.8902439024390244, | |
| "eval_loss": 0.45533695816993713, | |
| "eval_precision": 0.9931972789115646, | |
| "eval_recall": 0.8066298342541437, | |
| "eval_runtime": 76.2971, | |
| "eval_samples_per_second": 4.574, | |
| "eval_steps_per_second": 0.288, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.21169081330299377, | |
| "learning_rate": 3.481481481481482e-05, | |
| "loss": 0.3073, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 8.168057441711426, | |
| "learning_rate": 3.185185185185185e-05, | |
| "loss": 0.1746, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.0985065698623657, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.118, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.13789577782154083, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.0233, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 1.7061790227890015, | |
| "learning_rate": 2.2962962962962965e-05, | |
| "loss": 0.2002, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 6.507961750030518, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0259, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9484240687679083, | |
| "eval_auc": 0.9819126545645883, | |
| "eval_f1": 0.9516129032258065, | |
| "eval_loss": 0.2552463114261627, | |
| "eval_precision": 0.9267015706806283, | |
| "eval_recall": 0.9779005524861878, | |
| "eval_runtime": 75.7963, | |
| "eval_samples_per_second": 4.604, | |
| "eval_steps_per_second": 0.29, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.1205369234085083, | |
| "learning_rate": 1.7037037037037038e-05, | |
| "loss": 0.0081, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.08243238925933838, | |
| "learning_rate": 1.4074074074074075e-05, | |
| "loss": 0.0458, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 54.06669998168945, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1301, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.08115862309932709, | |
| "learning_rate": 8.14814814814815e-06, | |
| "loss": 0.0053, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.06672395765781403, | |
| "learning_rate": 5.185185185185185e-06, | |
| "loss": 0.0075, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.0613614059984684, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0871, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9656160458452722, | |
| "eval_auc": 0.9890489344909235, | |
| "eval_f1": 0.967032967032967, | |
| "eval_loss": 0.18809613585472107, | |
| "eval_precision": 0.9617486338797814, | |
| "eval_recall": 0.9723756906077348, | |
| "eval_runtime": 75.8185, | |
| "eval_samples_per_second": 4.603, | |
| "eval_steps_per_second": 0.29, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 8, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 77750711202816.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |