| { | |
| "best_metric": 0.8481262327416174, | |
| "best_model_checkpoint": "omarmomen/sf_babylm_1/finetune/sst2/checkpoint-1200", | |
| "epoch": 1.518987341772152, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.7775590419769287, | |
| "eval_f1": 0.7855787476280834, | |
| "eval_loss": 0.47054141759872437, | |
| "eval_mcc": 0.5571623075978556, | |
| "eval_runtime": 0.9009, | |
| "eval_samples_per_second": 563.86, | |
| "eval_steps_per_second": 71.037, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.7972440719604492, | |
| "eval_f1": 0.818342151675485, | |
| "eval_loss": 0.516063392162323, | |
| "eval_mcc": 0.6127643523723303, | |
| "eval_runtime": 0.8832, | |
| "eval_samples_per_second": 575.189, | |
| "eval_steps_per_second": 72.465, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.683544303797468e-05, | |
| "loss": 0.4417, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.7952755689620972, | |
| "eval_f1": 0.8022813688212928, | |
| "eval_loss": 0.4550493657588959, | |
| "eval_mcc": 0.5925102852024335, | |
| "eval_runtime": 0.9129, | |
| "eval_samples_per_second": 556.495, | |
| "eval_steps_per_second": 70.11, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.8208661675453186, | |
| "eval_f1": 0.8139059304703476, | |
| "eval_loss": 0.4225212037563324, | |
| "eval_mcc": 0.6430750513685719, | |
| "eval_runtime": 0.8829, | |
| "eval_samples_per_second": 575.39, | |
| "eval_steps_per_second": 72.49, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.367088607594937e-05, | |
| "loss": 0.2829, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.8287401795387268, | |
| "eval_f1": 0.8342857142857143, | |
| "eval_loss": 0.5139408707618713, | |
| "eval_mcc": 0.6594223100685462, | |
| "eval_runtime": 0.8789, | |
| "eval_samples_per_second": 578.009, | |
| "eval_steps_per_second": 72.82, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.8484252095222473, | |
| "eval_f1": 0.8481262327416174, | |
| "eval_loss": 0.43108150362968445, | |
| "eval_mcc": 0.6968557943649227, | |
| "eval_runtime": 0.8802, | |
| "eval_samples_per_second": 577.15, | |
| "eval_steps_per_second": 72.712, | |
| "step": 1200 | |
| } | |
| ], | |
| "max_steps": 7900, | |
| "num_train_epochs": 10, | |
| "total_flos": 1967293705076736.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |