| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 11.538461538461538, |
| "eval_steps": 50, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07692307692307693, |
| "eval_loss": 10.376392364501953, |
| "eval_runtime": 5.3202, |
| "eval_samples_per_second": 282.131, |
| "eval_steps_per_second": 4.511, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 0.09619140625, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 10.378, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 0.09716796875, |
| "learning_rate": 0.00013333333333333334, |
| "loss": 10.3754, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.11279296875, |
| "learning_rate": 0.0002, |
| "loss": 10.3683, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 0.201171875, |
| "learning_rate": 0.00019984815164333163, |
| "loss": 10.3522, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "grad_norm": 0.3203125, |
| "learning_rate": 0.00019939306773179497, |
| "loss": 10.3159, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "eval_loss": 10.285228729248047, |
| "eval_runtime": 5.2726, |
| "eval_samples_per_second": 284.681, |
| "eval_steps_per_second": 4.552, |
| "step": 50 |
| }, |
| { |
| "epoch": 4.615384615384615, |
| "grad_norm": 0.32421875, |
| "learning_rate": 0.00019863613034027224, |
| "loss": 10.2518, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.384615384615385, |
| "grad_norm": 0.326171875, |
| "learning_rate": 0.00019757963826274357, |
| "loss": 10.1828, |
| "step": 70 |
| }, |
| { |
| "epoch": 6.153846153846154, |
| "grad_norm": 0.330078125, |
| "learning_rate": 0.00019622680003092503, |
| "loss": 10.1177, |
| "step": 80 |
| }, |
| { |
| "epoch": 6.923076923076923, |
| "grad_norm": 0.33203125, |
| "learning_rate": 0.00019458172417006347, |
| "loss": 10.0565, |
| "step": 90 |
| }, |
| { |
| "epoch": 7.6923076923076925, |
| "grad_norm": 0.341796875, |
| "learning_rate": 0.00019264940672148018, |
| "loss": 9.998, |
| "step": 100 |
| }, |
| { |
| "epoch": 7.6923076923076925, |
| "eval_loss": 9.973793029785156, |
| "eval_runtime": 5.2822, |
| "eval_samples_per_second": 284.164, |
| "eval_steps_per_second": 4.544, |
| "step": 100 |
| }, |
| { |
| "epoch": 8.461538461538462, |
| "grad_norm": 0.345703125, |
| "learning_rate": 0.00019043571606975777, |
| "loss": 9.942, |
| "step": 110 |
| }, |
| { |
| "epoch": 9.23076923076923, |
| "grad_norm": 0.34765625, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 9.8887, |
| "step": 120 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.349609375, |
| "learning_rate": 0.00018519194088383273, |
| "loss": 9.836, |
| "step": 130 |
| }, |
| { |
| "epoch": 10.76923076923077, |
| "grad_norm": 0.357421875, |
| "learning_rate": 0.0001821777815225245, |
| "loss": 9.7845, |
| "step": 140 |
| }, |
| { |
| "epoch": 11.538461538461538, |
| "grad_norm": 0.361328125, |
| "learning_rate": 0.00017891405093963938, |
| "loss": 9.7359, |
| "step": 150 |
| }, |
| { |
| "epoch": 11.538461538461538, |
| "eval_loss": 9.719038963317871, |
| "eval_runtime": 5.2736, |
| "eval_samples_per_second": 284.626, |
| "eval_steps_per_second": 4.551, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 600, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 47, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 61373782425600.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
