| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.017069701280227598, |
| "eval_steps": 8, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0005689900426742532, |
| "eval_loss": 9.121294021606445, |
| "eval_runtime": 43.1024, |
| "eval_samples_per_second": 17.168, |
| "eval_steps_per_second": 8.584, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0017069701280227596, |
| "grad_norm": 16.72486686706543, |
| "learning_rate": 6e-05, |
| "loss": 8.6592, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0034139402560455193, |
| "grad_norm": 14.888457298278809, |
| "learning_rate": 0.00012, |
| "loss": 7.913, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.004551920341394026, |
| "eval_loss": 3.8307814598083496, |
| "eval_runtime": 42.5013, |
| "eval_samples_per_second": 17.411, |
| "eval_steps_per_second": 8.706, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.005120910384068279, |
| "grad_norm": 12.3302001953125, |
| "learning_rate": 0.00018, |
| "loss": 4.487, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0068278805120910386, |
| "grad_norm": 18.477922439575195, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 3.4117, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.008534850640113799, |
| "grad_norm": 13.56683349609375, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 2.1899, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.009103840682788052, |
| "eval_loss": 1.833335280418396, |
| "eval_runtime": 42.6016, |
| "eval_samples_per_second": 17.37, |
| "eval_steps_per_second": 8.685, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.010241820768136558, |
| "grad_norm": 18.128826141357422, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 1.728, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.011948790896159318, |
| "grad_norm": 15.941401481628418, |
| "learning_rate": 8.435655349597689e-05, |
| "loss": 1.4067, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.013655761024182077, |
| "grad_norm": 10.316154479980469, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 1.4947, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.013655761024182077, |
| "eval_loss": 1.5885289907455444, |
| "eval_runtime": 42.6387, |
| "eval_samples_per_second": 17.355, |
| "eval_steps_per_second": 8.678, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.015362731152204837, |
| "grad_norm": 5.8392181396484375, |
| "learning_rate": 1.0899347581163221e-05, |
| "loss": 1.4468, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.017069701280227598, |
| "grad_norm": 8.035550117492676, |
| "learning_rate": 0.0, |
| "loss": 1.823, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.112830925340672e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
