| { | |
| "best_metric": 0.9934865429519479, | |
| "best_model_checkpoint": "omarmomen/sf_babylm_1/finetune/main_verb_control/checkpoint-600", | |
| "epoch": 10.0, | |
| "global_step": 1280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.9893577694892883, | |
| "eval_f1": 0.9893617021276596, | |
| "eval_loss": 0.05015372857451439, | |
| "eval_mcc": 0.9787174883729357, | |
| "eval_runtime": 27.4509, | |
| "eval_samples_per_second": 595.61, | |
| "eval_steps_per_second": 74.46, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.9921100735664368, | |
| "eval_f1": 0.9920678841542151, | |
| "eval_loss": 0.04251589626073837, | |
| "eval_mcc": 0.9842637485530025, | |
| "eval_runtime": 27.5753, | |
| "eval_samples_per_second": 592.922, | |
| "eval_steps_per_second": 74.124, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.0468750000000002e-05, | |
| "loss": 0.0781, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_accuracy": 0.9935168027877808, | |
| "eval_f1": 0.9934865429519479, | |
| "eval_loss": 0.042066145688295364, | |
| "eval_mcc": 0.9870657394565869, | |
| "eval_runtime": 27.392, | |
| "eval_samples_per_second": 596.89, | |
| "eval_steps_per_second": 74.62, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_accuracy": 0.9931498765945435, | |
| "eval_f1": 0.9931170108161259, | |
| "eval_loss": 0.04584728553891182, | |
| "eval_mcc": 0.9863337424620885, | |
| "eval_runtime": 27.5365, | |
| "eval_samples_per_second": 593.757, | |
| "eval_steps_per_second": 74.229, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 0.0003, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_accuracy": 0.9933333396911621, | |
| "eval_f1": 0.9933108315434183, | |
| "eval_loss": 0.04603412747383118, | |
| "eval_mcc": 0.986681565476627, | |
| "eval_runtime": 27.5008, | |
| "eval_samples_per_second": 594.529, | |
| "eval_steps_per_second": 74.325, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_accuracy": 0.9925382137298584, | |
| "eval_f1": 0.9925006147037128, | |
| "eval_loss": 0.04715948551893234, | |
| "eval_mcc": 0.9851145750966622, | |
| "eval_runtime": 27.359, | |
| "eval_samples_per_second": 597.609, | |
| "eval_steps_per_second": 74.71, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1280, | |
| "total_flos": 2092658450872320.0, | |
| "train_loss": 0.03072957310359925, | |
| "train_runtime": 433.9699, | |
| "train_samples_per_second": 188.17, | |
| "train_steps_per_second": 2.95 | |
| } | |
| ], | |
| "max_steps": 1280, | |
| "num_train_epochs": 10, | |
| "total_flos": 2092658450872320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |