| { | |
| "best_metric": 1.9435880184173584, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-9/checkpoint-198", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 198, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.012012012012012012, | |
| "eval_f1": 0.0031978072179077205, | |
| "eval_loss": 4.749619007110596, | |
| "eval_precision": 0.002532561505065123, | |
| "eval_recall": 0.004337050805452293, | |
| "eval_runtime": 0.3642, | |
| "eval_samples_per_second": 799.034, | |
| "eval_steps_per_second": 101.595, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.03333333333333333, | |
| "eval_f1": 0.003970223325062034, | |
| "eval_loss": 4.679495334625244, | |
| "eval_precision": 0.0033112582781456954, | |
| "eval_recall": 0.004956629491945477, | |
| "eval_runtime": 0.8425, | |
| "eval_samples_per_second": 345.396, | |
| "eval_steps_per_second": 43.916, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.05795795795795796, | |
| "eval_f1": 0.0071546505228398454, | |
| "eval_loss": 4.5262579917907715, | |
| "eval_precision": 0.006435643564356435, | |
| "eval_recall": 0.0080545229244114, | |
| "eval_runtime": 0.361, | |
| "eval_samples_per_second": 806.114, | |
| "eval_steps_per_second": 102.496, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.12612612612612611, | |
| "eval_f1": 0.023522129371711546, | |
| "eval_loss": 4.221945762634277, | |
| "eval_precision": 0.02350030921459493, | |
| "eval_recall": 0.023543990086741014, | |
| "eval_runtime": 0.3669, | |
| "eval_samples_per_second": 793.061, | |
| "eval_steps_per_second": 100.836, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.23153153153153153, | |
| "eval_f1": 0.057900244157656086, | |
| "eval_loss": 3.788745880126953, | |
| "eval_precision": 0.06624102154828412, | |
| "eval_recall": 0.051425030978934326, | |
| "eval_runtime": 0.3736, | |
| "eval_samples_per_second": 778.936, | |
| "eval_steps_per_second": 99.04, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.345045045045045, | |
| "eval_f1": 0.11658518239939826, | |
| "eval_loss": 3.2482411861419678, | |
| "eval_precision": 0.14832535885167464, | |
| "eval_recall": 0.09603469640644362, | |
| "eval_runtime": 0.3627, | |
| "eval_samples_per_second": 802.223, | |
| "eval_steps_per_second": 102.001, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.44114114114114117, | |
| "eval_f1": 0.18552200800291016, | |
| "eval_loss": 2.7049763202667236, | |
| "eval_precision": 0.22466960352422907, | |
| "eval_recall": 0.1579925650557621, | |
| "eval_runtime": 0.4418, | |
| "eval_samples_per_second": 658.601, | |
| "eval_steps_per_second": 83.74, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5042042042042042, | |
| "eval_f1": 0.23968705547652916, | |
| "eval_loss": 2.2730276584625244, | |
| "eval_precision": 0.28130217028380633, | |
| "eval_recall": 0.20879801734820322, | |
| "eval_runtime": 0.3655, | |
| "eval_samples_per_second": 796.135, | |
| "eval_steps_per_second": 101.227, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5591591591591591, | |
| "eval_f1": 0.3004824259131633, | |
| "eval_loss": 1.9435880184173584, | |
| "eval_precision": 0.3385093167701863, | |
| "eval_recall": 0.2701363073110285, | |
| "eval_runtime": 0.3718, | |
| "eval_samples_per_second": 782.782, | |
| "eval_steps_per_second": 99.529, | |
| "step": 198 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 264, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3.901404269366272e-05, | |
| "num_train_epochs": 12, | |
| "per_device_train_batch_size": 64, | |
| "warmup_steps": 368, | |
| "weight_decay": 0.16924253041207893 | |
| } | |
| } | |