| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 50, |
| "global_step": 375, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "grad_norm": 2.5308005809783936, |
| "learning_rate": 1.99625729663483e-05, |
| "loss": 8.2688, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 2.6729016304016113, |
| "learning_rate": 1.95447296407255e-05, |
| "loss": 7.7962, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 7.424994945526123, |
| "eval_runtime": 36.7897, |
| "eval_samples_per_second": 8.154, |
| "eval_steps_per_second": 1.033, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 2.4165093898773193, |
| "learning_rate": 1.868180920098644e-05, |
| "loss": 7.272, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 3.073392152786255, |
| "learning_rate": 1.7414050203223092e-05, |
| "loss": 7.1306, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 6.984020233154297, |
| "eval_runtime": 37.416, |
| "eval_samples_per_second": 8.018, |
| "eval_steps_per_second": 1.016, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.286832332611084, |
| "learning_rate": 1.5800569095711983e-05, |
| "loss": 7.0359, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 2.9184694290161133, |
| "learning_rate": 1.3916603579471705e-05, |
| "loss": 6.9816, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_loss": 6.894983768463135, |
| "eval_runtime": 35.6543, |
| "eval_samples_per_second": 8.414, |
| "eval_steps_per_second": 1.066, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 3.036834478378296, |
| "learning_rate": 1.1850004224044315e-05, |
| "loss": 6.9832, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 2.8202149868011475, |
| "learning_rate": 9.697137936798635e-06, |
| "loss": 6.9095, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_loss": 6.850904941558838, |
| "eval_runtime": 36.7127, |
| "eval_samples_per_second": 8.172, |
| "eval_steps_per_second": 1.035, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 3.1002156734466553, |
| "learning_rate": 7.558394309716088e-06, |
| "loss": 6.8941, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 3.674051523208618, |
| "learning_rate": 5.533504385708024e-06, |
| "loss": 6.8801, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 6.828614711761475, |
| "eval_runtime": 37.0462, |
| "eval_samples_per_second": 8.098, |
| "eval_steps_per_second": 1.026, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 2.9793779850006104, |
| "learning_rate": 3.7168901335157313e-06, |
| "loss": 6.8425, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 3.072126865386963, |
| "learning_rate": 2.1932614882827196e-06, |
| "loss": 6.8726, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_loss": 6.8157854080200195, |
| "eval_runtime": 35.7147, |
| "eval_samples_per_second": 8.4, |
| "eval_steps_per_second": 1.064, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 2.8476767539978027, |
| "learning_rate": 1.0336662707363287e-06, |
| "loss": 6.9329, |
| "step": 325 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 3.1517913341522217, |
| "learning_rate": 2.921771798838069e-07, |
| "loss": 6.861, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.8, |
| "eval_loss": 6.814030170440674, |
| "eval_runtime": 36.1954, |
| "eval_samples_per_second": 8.288, |
| "eval_steps_per_second": 1.05, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 3.607140064239502, |
| "learning_rate": 3.3703469648760367e-09, |
| "loss": 6.8769, |
| "step": 375 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 375, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6930376445952000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
