| { |
| "best_global_step": 3960, |
| "best_metric": 3.0727946758270264, |
| "best_model_checkpoint": null, |
| "epoch": 8.080808080808081, |
| "eval_steps": 500, |
| "global_step": 4000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00202020202020202, |
| "grad_norm": 30.443870544433594, |
| "learning_rate": 0.0, |
| "loss": 10.3392, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.3942521810531616, |
| "learning_rate": 9.88e-05, |
| "loss": 4.8272, |
| "step": 495 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.784661054611206, |
| "eval_runtime": 19.6467, |
| "eval_samples_per_second": 1618.086, |
| "eval_steps_per_second": 6.362, |
| "step": 495 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.0911511182785034, |
| "learning_rate": 9.478678038379531e-05, |
| "loss": 3.5402, |
| "step": 990 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 3.438631534576416, |
| "eval_runtime": 19.6741, |
| "eval_samples_per_second": 1615.83, |
| "eval_steps_per_second": 6.354, |
| "step": 990 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.0547674894332886, |
| "learning_rate": 8.950959488272922e-05, |
| "loss": 3.2821, |
| "step": 1485 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 3.2927286624908447, |
| "eval_runtime": 19.6268, |
| "eval_samples_per_second": 1619.722, |
| "eval_steps_per_second": 6.369, |
| "step": 1485 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.0422005653381348, |
| "learning_rate": 8.42324093816631e-05, |
| "loss": 3.137, |
| "step": 1980 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 3.211667537689209, |
| "eval_runtime": 19.8925, |
| "eval_samples_per_second": 1598.086, |
| "eval_steps_per_second": 6.284, |
| "step": 1980 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.0484884977340698, |
| "learning_rate": 7.895522388059702e-05, |
| "loss": 3.0348, |
| "step": 2475 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 3.154648780822754, |
| "eval_runtime": 19.6658, |
| "eval_samples_per_second": 1616.511, |
| "eval_steps_per_second": 6.356, |
| "step": 2475 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.0860364437103271, |
| "learning_rate": 7.367803837953093e-05, |
| "loss": 2.954, |
| "step": 2970 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 3.115788221359253, |
| "eval_runtime": 19.7596, |
| "eval_samples_per_second": 1608.836, |
| "eval_steps_per_second": 6.326, |
| "step": 2970 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 1.168921947479248, |
| "learning_rate": 6.840085287846483e-05, |
| "loss": 2.8855, |
| "step": 3465 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 3.09100341796875, |
| "eval_runtime": 19.6923, |
| "eval_samples_per_second": 1614.338, |
| "eval_steps_per_second": 6.348, |
| "step": 3465 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 1.189679741859436, |
| "learning_rate": 6.312366737739872e-05, |
| "loss": 2.825, |
| "step": 3960 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 3.0727946758270264, |
| "eval_runtime": 19.8838, |
| "eval_samples_per_second": 1598.79, |
| "eval_steps_per_second": 6.287, |
| "step": 3960 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 9900, |
| "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": 6.6813940334592e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
