| { | |
| "best_metric": 0.5396051449500585, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-3207", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 5345, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.883378108768492e-05, | |
| "loss": 0.5687, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.5858158684415064e-05, | |
| "loss": 0.4948, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4758210778236389, | |
| "eval_matthews_correlation": 0.43428613653509085, | |
| "eval_runtime": 0.7527, | |
| "eval_samples_per_second": 1385.607, | |
| "eval_steps_per_second": 87.68, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.2882536281145206e-05, | |
| "loss": 0.3622, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.9906913877875348e-05, | |
| "loss": 0.344, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6103293895721436, | |
| "eval_matthews_correlation": 0.5102489493078572, | |
| "eval_runtime": 0.8162, | |
| "eval_samples_per_second": 1277.866, | |
| "eval_steps_per_second": 80.862, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.693129147460549e-05, | |
| "loss": 0.2557, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.3955669071335632e-05, | |
| "loss": 0.2381, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.8707840442657471, | |
| "eval_matthews_correlation": 0.5396051449500585, | |
| "eval_runtime": 0.7552, | |
| "eval_samples_per_second": 1381.062, | |
| "eval_steps_per_second": 87.392, | |
| "step": 3207 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 1.0980046668065774e-05, | |
| "loss": 0.181, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 8.004424264795918e-06, | |
| "loss": 0.1475, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.1052277088165283, | |
| "eval_matthews_correlation": 0.47860504193113135, | |
| "eval_runtime": 0.7999, | |
| "eval_samples_per_second": 1303.971, | |
| "eval_steps_per_second": 82.514, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 5.028801861526059e-06, | |
| "loss": 0.1023, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.053179458256202e-06, | |
| "loss": 0.084, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.2291204929351807, | |
| "eval_matthews_correlation": 0.4917552463505288, | |
| "eval_runtime": 0.9511, | |
| "eval_samples_per_second": 1096.6, | |
| "eval_steps_per_second": 69.392, | |
| "step": 5345 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5345, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 188337593842272.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3.180940349095478e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 8, | |
| "seed": 22 | |
| } | |
| } | |