| { | |
| "best_metric": 0.6674578901720911, | |
| "best_model_checkpoint": "omarmomen/sf_babylm_1/finetune/main_verb_lexical_content_the/checkpoint-400", | |
| "epoch": 10.0, | |
| "global_step": 1150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.74, | |
| "eval_accuracy": 0.673107385635376, | |
| "eval_f1": 0.6644370122630993, | |
| "eval_loss": 2.718010663986206, | |
| "eval_mcc": 0.34706224524049095, | |
| "eval_runtime": 37.1543, | |
| "eval_samples_per_second": 594.79, | |
| "eval_steps_per_second": 74.366, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_accuracy": 0.6703470945358276, | |
| "eval_f1": 0.6674578901720911, | |
| "eval_loss": 3.0592281818389893, | |
| "eval_mcc": 0.34089648488627655, | |
| "eval_runtime": 37.1714, | |
| "eval_samples_per_second": 594.516, | |
| "eval_steps_per_second": 74.331, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.826086956521739e-05, | |
| "loss": 0.0437, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_accuracy": 0.6721118688583374, | |
| "eval_f1": 0.6662982407663258, | |
| "eval_loss": 3.191685438156128, | |
| "eval_mcc": 0.344702333715234, | |
| "eval_runtime": 37.2337, | |
| "eval_samples_per_second": 593.522, | |
| "eval_steps_per_second": 74.207, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_accuracy": 0.6681750416755676, | |
| "eval_f1": 0.666211479812463, | |
| "eval_loss": 3.297962188720703, | |
| "eval_mcc": 0.3364860501633386, | |
| "eval_runtime": 37.0782, | |
| "eval_samples_per_second": 596.011, | |
| "eval_steps_per_second": 74.518, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 0.0003, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "eval_accuracy": 0.6701660752296448, | |
| "eval_f1": 0.6630610641150094, | |
| "eval_loss": 3.2882540225982666, | |
| "eval_mcc": 0.34095345354384726, | |
| "eval_runtime": 37.1786, | |
| "eval_samples_per_second": 594.401, | |
| "eval_steps_per_second": 74.317, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1150, | |
| "total_flos": 1872270712965120.0, | |
| "train_loss": 0.01914804144559995, | |
| "train_runtime": 426.9316, | |
| "train_samples_per_second": 171.128, | |
| "train_steps_per_second": 2.694 | |
| } | |
| ], | |
| "max_steps": 1150, | |
| "num_train_epochs": 10, | |
| "total_flos": 1872270712965120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |