| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.6962053060531614, |
| "epoch": 0.3389830508474576, |
| "grad_norm": 5.6875, |
| "learning_rate": 1.9689373017815076e-05, |
| "loss": 2.622, |
| "mean_token_accuracy": 0.4749481610953808, |
| "num_tokens": 5419.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 2.698164188861847, |
| "epoch": 0.6779661016949152, |
| "grad_norm": 3.328125, |
| "learning_rate": 1.8214207751204917e-05, |
| "loss": 2.4606, |
| "mean_token_accuracy": 0.49576075151562693, |
| "num_tokens": 11175.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 2.676299622184352, |
| "epoch": 1.0, |
| "grad_norm": 2.640625, |
| "learning_rate": 1.5703226369349642e-05, |
| "loss": 2.3682, |
| "mean_token_accuracy": 0.49295464863902644, |
| "num_tokens": 16450.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 2.69452788233757, |
| "epoch": 1.3389830508474576, |
| "grad_norm": 1.8828125, |
| "learning_rate": 1.2473065005542155e-05, |
| "loss": 2.2639, |
| "mean_token_accuracy": 0.5272781491279602, |
| "num_tokens": 22083.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 2.6724473893642426, |
| "epoch": 1.6779661016949152, |
| "grad_norm": 2.046875, |
| "learning_rate": 8.931048784348875e-06, |
| "loss": 2.318, |
| "mean_token_accuracy": 0.5053238138556481, |
| "num_tokens": 27625.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 2.72734388552214, |
| "epoch": 2.0, |
| "grad_norm": 2.5625, |
| "learning_rate": 5.523827899372876e-06, |
| "loss": 2.3562, |
| "mean_token_accuracy": 0.5088289270275518, |
| "num_tokens": 32900.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 2.6972490429878233, |
| "epoch": 2.3389830508474576, |
| "grad_norm": 1.9609375, |
| "learning_rate": 2.681054778182748e-06, |
| "loss": 2.3019, |
| "mean_token_accuracy": 0.5131353832781315, |
| "num_tokens": 38497.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 2.6893122375011442, |
| "epoch": 2.6779661016949152, |
| "grad_norm": 1.984375, |
| "learning_rate": 7.612046748871327e-07, |
| "loss": 2.2939, |
| "mean_token_accuracy": 0.520061531662941, |
| "num_tokens": 44003.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 2.6991821401997615, |
| "epoch": 3.0, |
| "grad_norm": 2.875, |
| "learning_rate": 6.371743430082511e-09, |
| "loss": 2.2783, |
| "mean_token_accuracy": 0.5276820785120914, |
| "num_tokens": 49350.0, |
| "step": 90 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 90, |
| "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": 847960927833600.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
