| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 2000, |
| "global_step": 10704, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 9.342301943198804e-05, |
| "grad_norm": 6.934398651123047, |
| "learning_rate": 0.0, |
| "loss": 2.7298, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.18684603886397608, |
| "grad_norm": 3.9505438804626465, |
| "learning_rate": 5.603101934037186e-06, |
| "loss": 1.95, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.18684603886397608, |
| "eval_cosine_accuracy": 0.945648729801178, |
| "eval_loss": 0.6836262345314026, |
| "eval_runtime": 25.1378, |
| "eval_samples_per_second": 376.206, |
| "eval_steps_per_second": 1.472, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.37369207772795215, |
| "grad_norm": 3.8480846881866455, |
| "learning_rate": 1.1209006820517613e-05, |
| "loss": 1.3877, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.37369207772795215, |
| "eval_cosine_accuracy": 0.9498783946037292, |
| "eval_loss": 0.6531221866607666, |
| "eval_runtime": 28.1391, |
| "eval_samples_per_second": 336.081, |
| "eval_steps_per_second": 1.315, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.5605381165919282, |
| "grad_norm": 3.624490976333618, |
| "learning_rate": 1.681491170699804e-05, |
| "loss": 1.0715, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.5605381165919282, |
| "eval_cosine_accuracy": 0.9564343690872192, |
| "eval_loss": 0.6075382828712463, |
| "eval_runtime": 27.553, |
| "eval_samples_per_second": 343.229, |
| "eval_steps_per_second": 1.343, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.7473841554559043, |
| "grad_norm": 2.9945709705352783, |
| "learning_rate": 2.241521068859198e-05, |
| "loss": 0.8659, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.7473841554559043, |
| "eval_cosine_accuracy": 0.9581262469291687, |
| "eval_loss": 0.5895714163780212, |
| "eval_runtime": 27.1473, |
| "eval_samples_per_second": 348.359, |
| "eval_steps_per_second": 1.363, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.9342301943198804, |
| "grad_norm": 4.797957420349121, |
| "learning_rate": 2.801831262262917e-05, |
| "loss": 0.4948, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.9342301943198804, |
| "eval_cosine_accuracy": 0.9602410793304443, |
| "eval_loss": 0.5568962097167969, |
| "eval_runtime": 26.8641, |
| "eval_samples_per_second": 352.032, |
| "eval_steps_per_second": 1.377, |
| "step": 10000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 21408, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
