| { |
| "best_metric": 3.606008291244507, |
| "best_model_checkpoint": "./youtube/dict/checkpoint-500", |
| "epoch": 2.5756600128783003, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6439150032195751, |
| "grad_norm": 3.328125, |
| "learning_rate": 4.452172417195941e-05, |
| "loss": 0.7536, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.6439150032195751, |
| "eval_accuracy": 0.45848246241947027, |
| "eval_loss": 3.606008291244507, |
| "eval_runtime": 3.6685, |
| "eval_samples_per_second": 95.953, |
| "eval_steps_per_second": 2.453, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.2878300064391501, |
| "grad_norm": 2.25, |
| "learning_rate": 3.0487817171685128e-05, |
| "loss": 0.3454, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.2878300064391501, |
| "eval_accuracy": 0.463157659269864, |
| "eval_loss": 3.908834934234619, |
| "eval_runtime": 2.2647, |
| "eval_samples_per_second": 155.431, |
| "eval_steps_per_second": 3.974, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.9317450096587252, |
| "grad_norm": 4.53125, |
| "learning_rate": 1.4048808078582942e-05, |
| "loss": 0.2247, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.9317450096587252, |
| "eval_accuracy": 0.45957856120257695, |
| "eval_loss": 3.9476664066314697, |
| "eval_runtime": 2.3811, |
| "eval_samples_per_second": 147.829, |
| "eval_steps_per_second": 3.78, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.5756600128783003, |
| "grad_norm": 2.59375, |
| "learning_rate": 2.409290984787371e-06, |
| "loss": 0.1506, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.5756600128783003, |
| "eval_accuracy": 0.45691660701503223, |
| "eval_loss": 4.0822529792785645, |
| "eval_runtime": 2.2552, |
| "eval_samples_per_second": 156.082, |
| "eval_steps_per_second": 3.991, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.5756600128783003, |
| "step": 2000, |
| "total_flos": 4.747627355386675e+16, |
| "train_loss": 0.36860907363891604, |
| "train_runtime": 2762.5839, |
| "train_samples_per_second": 3.373, |
| "train_steps_per_second": 0.843 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2328, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.747627355386675e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
