| { | |
| "best_metric": 0.17771275341510773, | |
| "best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/convergence_french/random_sentence_french/checkpoint-4000", | |
| "epoch": 0.007233639316276412, | |
| "eval_steps": 2000, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003616819658138206, | |
| "grad_norm": 0.14744240045547485, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7697, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.003616819658138206, | |
| "eval_loss": 0.19154727458953857, | |
| "eval_runtime": 91.812, | |
| "eval_samples_per_second": 397.933, | |
| "eval_steps_per_second": 24.877, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.007233639316276412, | |
| "grad_norm": 0.1623348593711853, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1884, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.007233639316276412, | |
| "eval_loss": 0.17771275341510773, | |
| "eval_runtime": 99.0721, | |
| "eval_samples_per_second": 368.772, | |
| "eval_steps_per_second": 23.054, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 2000, | |
| "max_steps": 552972, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.001 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 77976305664000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |