| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 1490, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5050505050505051, |
| "eval_loss": 2.2999494075775146, |
| "eval_runtime": 8.1743, |
| "eval_samples_per_second": 36.333, |
| "eval_steps_per_second": 4.649, |
| "step": 149 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6195286195286195, |
| "eval_loss": 1.9136502742767334, |
| "eval_runtime": 8.1758, |
| "eval_samples_per_second": 36.327, |
| "eval_steps_per_second": 4.648, |
| "step": 298 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6599326599326599, |
| "eval_loss": 1.7068243026733398, |
| "eval_runtime": 8.1915, |
| "eval_samples_per_second": 36.257, |
| "eval_steps_per_second": 4.639, |
| "step": 447 |
| }, |
| { |
| "epoch": 3.3557046979865772, |
| "grad_norm": 15.295294761657715, |
| "learning_rate": 3.3255033557046986e-05, |
| "loss": 2.0179, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6767676767676768, |
| "eval_loss": 1.5854746103286743, |
| "eval_runtime": 8.1951, |
| "eval_samples_per_second": 36.241, |
| "eval_steps_per_second": 4.637, |
| "step": 596 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6868686868686869, |
| "eval_loss": 1.5601825714111328, |
| "eval_runtime": 8.1968, |
| "eval_samples_per_second": 36.233, |
| "eval_steps_per_second": 4.636, |
| "step": 745 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.7037037037037037, |
| "eval_loss": 1.5054125785827637, |
| "eval_runtime": 8.1976, |
| "eval_samples_per_second": 36.23, |
| "eval_steps_per_second": 4.636, |
| "step": 894 |
| }, |
| { |
| "epoch": 6.7114093959731544, |
| "grad_norm": 7.224489212036133, |
| "learning_rate": 1.6476510067114094e-05, |
| "loss": 0.6927, |
| "step": 1000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.7070707070707071, |
| "eval_loss": 1.506157636642456, |
| "eval_runtime": 8.2414, |
| "eval_samples_per_second": 36.038, |
| "eval_steps_per_second": 4.611, |
| "step": 1043 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.7306397306397306, |
| "eval_loss": 1.4550477266311646, |
| "eval_runtime": 8.2258, |
| "eval_samples_per_second": 36.106, |
| "eval_steps_per_second": 4.62, |
| "step": 1192 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.7272727272727273, |
| "eval_loss": 1.4771537780761719, |
| "eval_runtime": 8.2112, |
| "eval_samples_per_second": 36.17, |
| "eval_steps_per_second": 4.628, |
| "step": 1341 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1490, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3129070999633920.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
