| { | |
| "best_global_step": 50, | |
| "best_metric": 0.5, | |
| "best_model_checkpoint": "./models/punctuation/encoder_model/checkpoint-50", | |
| "epoch": 0.47058823529411764, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.2591496407985687, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0255, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.23840643465518951, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8799, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.2382705807685852, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8393, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.26509279012680054, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8444, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.26330241560935974, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8232, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "eval_loss": 0.8152285814285278, | |
| "eval_model_preparation_time": 0.0135, | |
| "eval_runtime": 4.0525, | |
| "eval_samples_per_second": 24.676, | |
| "eval_steps_per_second": 12.338, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 214, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7229174818203648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |