| { |
| "best_metric": 0.04859507828950882, |
| "best_model_checkpoint": "./xlam_3epoch_simple_long_text/checkpoint-48", |
| "epoch": 1.28, |
| "eval_steps": 12, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 0.17464148998260498, |
| "learning_rate": 2.4910586579272968e-05, |
| "loss": 0.1304, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_loss": 0.0760175809264183, |
| "eval_runtime": 10.6494, |
| "eval_samples_per_second": 3.944, |
| "eval_steps_per_second": 3.944, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.12056827545166016, |
| "learning_rate": 2.391931822053251e-05, |
| "loss": 0.1004, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_loss": 0.05837269127368927, |
| "eval_runtime": 10.6381, |
| "eval_samples_per_second": 3.948, |
| "eval_steps_per_second": 3.948, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.1074976772069931, |
| "learning_rate": 2.191339332504514e-05, |
| "loss": 0.0853, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 0.05101713165640831, |
| "eval_runtime": 10.7471, |
| "eval_samples_per_second": 3.908, |
| "eval_steps_per_second": 3.908, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.060621477663517, |
| "learning_rate": 1.907104712263131e-05, |
| "loss": 0.0699, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_loss": 0.04859507828950882, |
| "eval_runtime": 10.6758, |
| "eval_samples_per_second": 3.934, |
| "eval_steps_per_second": 3.934, |
| "step": 48 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 111, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 12, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.0 |
| }, |
| "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": 2.992523693113344e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
