| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 1875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7046678635547576, | |
| "eval_f1": 0.0, | |
| "eval_loss": 2.1335229873657227, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.4061, | |
| "eval_samples_per_second": 246.215, | |
| "eval_steps_per_second": 32.008, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7522441651705566, | |
| "eval_f1": 0.14012738853503184, | |
| "eval_loss": 2.0110883712768555, | |
| "eval_precision": 0.55, | |
| "eval_recall": 0.08029197080291971, | |
| "eval_runtime": 0.3251, | |
| "eval_samples_per_second": 307.591, | |
| "eval_steps_per_second": 39.987, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7630161579892281, | |
| "eval_f1": 0.19540229885057472, | |
| "eval_loss": 1.8779761791229248, | |
| "eval_precision": 0.4594594594594595, | |
| "eval_recall": 0.12408759124087591, | |
| "eval_runtime": 0.3807, | |
| "eval_samples_per_second": 262.671, | |
| "eval_steps_per_second": 34.147, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.3616102933883667, | |
| "learning_rate": 1.4666666666666666e-05, | |
| "loss": 2.0165, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8788150807899462, | |
| "eval_f1": 0.55, | |
| "eval_loss": 1.7138484716415405, | |
| "eval_precision": 0.6407766990291263, | |
| "eval_recall": 0.48175182481751827, | |
| "eval_runtime": 0.3747, | |
| "eval_samples_per_second": 266.905, | |
| "eval_steps_per_second": 34.698, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8940754039497307, | |
| "eval_f1": 0.6439393939393939, | |
| "eval_loss": 1.5681630373001099, | |
| "eval_precision": 0.6692913385826772, | |
| "eval_recall": 0.6204379562043796, | |
| "eval_runtime": 0.4653, | |
| "eval_samples_per_second": 214.902, | |
| "eval_steps_per_second": 27.937, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9371633752244165, | |
| "eval_f1": 0.7970479704797049, | |
| "eval_loss": 1.4361474514007568, | |
| "eval_precision": 0.8059701492537313, | |
| "eval_recall": 0.7883211678832117, | |
| "eval_runtime": 0.4338, | |
| "eval_samples_per_second": 230.535, | |
| "eval_steps_per_second": 29.97, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9488330341113106, | |
| "eval_f1": 0.8475836431226766, | |
| "eval_loss": 1.3189666271209717, | |
| "eval_precision": 0.8636363636363636, | |
| "eval_recall": 0.8321167883211679, | |
| "eval_runtime": 0.462, | |
| "eval_samples_per_second": 216.445, | |
| "eval_steps_per_second": 28.138, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.242187738418579, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 1.461, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9605026929982047, | |
| "eval_f1": 0.8623188405797102, | |
| "eval_loss": 1.2221076488494873, | |
| "eval_precision": 0.8561151079136691, | |
| "eval_recall": 0.8686131386861314, | |
| "eval_runtime": 0.4073, | |
| "eval_samples_per_second": 245.517, | |
| "eval_steps_per_second": 31.917, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.966786355475763, | |
| "eval_f1": 0.9051094890510949, | |
| "eval_loss": 1.1402738094329834, | |
| "eval_precision": 0.9051094890510949, | |
| "eval_recall": 0.9051094890510949, | |
| "eval_runtime": 0.4198, | |
| "eval_samples_per_second": 238.187, | |
| "eval_steps_per_second": 30.964, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.966786355475763, | |
| "eval_f1": 0.8864468864468864, | |
| "eval_loss": 1.0731350183486938, | |
| "eval_precision": 0.8897058823529411, | |
| "eval_recall": 0.8832116788321168, | |
| "eval_runtime": 0.3515, | |
| "eval_samples_per_second": 284.456, | |
| "eval_steps_per_second": 36.979, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9676840215439856, | |
| "eval_f1": 0.9025270758122744, | |
| "eval_loss": 1.0196468830108643, | |
| "eval_precision": 0.8928571428571429, | |
| "eval_recall": 0.9124087591240876, | |
| "eval_runtime": 0.414, | |
| "eval_samples_per_second": 241.566, | |
| "eval_steps_per_second": 31.404, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.1379125118255615, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0954, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9685816876122083, | |
| "eval_f1": 0.9057971014492754, | |
| "eval_loss": 0.9813730120658875, | |
| "eval_precision": 0.8992805755395683, | |
| "eval_recall": 0.9124087591240876, | |
| "eval_runtime": 0.3827, | |
| "eval_samples_per_second": 261.27, | |
| "eval_steps_per_second": 33.965, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9703770197486535, | |
| "eval_f1": 0.9057971014492754, | |
| "eval_loss": 0.955005943775177, | |
| "eval_precision": 0.8992805755395683, | |
| "eval_recall": 0.9124087591240876, | |
| "eval_runtime": 0.4058, | |
| "eval_samples_per_second": 246.447, | |
| "eval_steps_per_second": 32.038, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9694793536804309, | |
| "eval_f1": 0.9025270758122744, | |
| "eval_loss": 0.9408783912658691, | |
| "eval_precision": 0.8928571428571429, | |
| "eval_recall": 0.9124087591240876, | |
| "eval_runtime": 0.3995, | |
| "eval_samples_per_second": 250.335, | |
| "eval_steps_per_second": 32.544, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9703770197486535, | |
| "eval_f1": 0.9057971014492754, | |
| "eval_loss": 0.9354953169822693, | |
| "eval_precision": 0.8992805755395683, | |
| "eval_recall": 0.9124087591240876, | |
| "eval_runtime": 0.4049, | |
| "eval_samples_per_second": 246.945, | |
| "eval_steps_per_second": 32.103, | |
| "step": 1875 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1875, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "total_flos": 153789736715280.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |