| { |
| "best_global_step": 1995, |
| "best_metric": 6.215089321136475, |
| "best_model_checkpoint": null, |
| "epoch": 5.012531328320802, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002506265664160401, |
| "grad_norm": 15.975584983825684, |
| "learning_rate": 0.0, |
| "loss": 10.3232, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.5802501440048218, |
| "learning_rate": 7.960000000000001e-05, |
| "loss": 7.3315, |
| "step": 399 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 6.782732009887695, |
| "eval_runtime": 20.1847, |
| "eval_samples_per_second": 1266.7, |
| "eval_steps_per_second": 4.954, |
| "step": 399 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.6263211965560913, |
| "learning_rate": 9.601876675603218e-05, |
| "loss": 6.5649, |
| "step": 798 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 6.505067348480225, |
| "eval_runtime": 20.2041, |
| "eval_samples_per_second": 1265.484, |
| "eval_steps_per_second": 4.949, |
| "step": 798 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.712126612663269, |
| "learning_rate": 9.067024128686328e-05, |
| "loss": 6.3596, |
| "step": 1197 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 6.374659061431885, |
| "eval_runtime": 20.1506, |
| "eval_samples_per_second": 1268.845, |
| "eval_steps_per_second": 4.963, |
| "step": 1197 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.8251084089279175, |
| "learning_rate": 8.532171581769438e-05, |
| "loss": 6.2374, |
| "step": 1596 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 6.283264636993408, |
| "eval_runtime": 20.2013, |
| "eval_samples_per_second": 1265.66, |
| "eval_steps_per_second": 4.95, |
| "step": 1596 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.9603049755096436, |
| "learning_rate": 7.997319034852548e-05, |
| "loss": 6.1394, |
| "step": 1995 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 6.215089321136475, |
| "eval_runtime": 20.1986, |
| "eval_samples_per_second": 1265.827, |
| "eval_steps_per_second": 4.951, |
| "step": 1995 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 7980, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 3.336568602624e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
