| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 275, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 23.5, |
| "learning_rate": 1.9272727272727275e-05, |
| "loss": 7.128, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.482421875, |
| "learning_rate": 1.8545454545454545e-05, |
| "loss": 0.0809, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 0.76953125, |
| "learning_rate": 1.781818181818182e-05, |
| "loss": 0.0788, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.546875, |
| "learning_rate": 1.7090909090909092e-05, |
| "loss": 0.0481, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.447265625, |
| "learning_rate": 1.6363636363636366e-05, |
| "loss": 0.021, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.011722942814230919, |
| "eval_runtime": 3.0908, |
| "eval_samples_per_second": 15.853, |
| "eval_steps_per_second": 15.853, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.0909090909090908, |
| "grad_norm": 0.38671875, |
| "learning_rate": 1.563636363636364e-05, |
| "loss": 0.0264, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.2727272727272727, |
| "grad_norm": 0.482421875, |
| "learning_rate": 1.4909090909090911e-05, |
| "loss": 0.0185, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.4545454545454546, |
| "grad_norm": 0.318359375, |
| "learning_rate": 1.4181818181818183e-05, |
| "loss": 0.017, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.6363636363636362, |
| "grad_norm": 0.458984375, |
| "learning_rate": 1.3454545454545455e-05, |
| "loss": 0.0154, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 0.38671875, |
| "learning_rate": 1.2727272727272728e-05, |
| "loss": 0.0142, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.28515625, |
| "learning_rate": 1.2e-05, |
| "loss": 0.0112, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.005110493861138821, |
| "eval_runtime": 2.9869, |
| "eval_samples_per_second": 16.405, |
| "eval_steps_per_second": 16.405, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 0.3828125, |
| "learning_rate": 1.1272727272727272e-05, |
| "loss": 0.01, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 0.416015625, |
| "learning_rate": 1.0545454545454546e-05, |
| "loss": 0.0108, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 0.35546875, |
| "learning_rate": 9.81818181818182e-06, |
| "loss": 0.0086, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 0.458984375, |
| "learning_rate": 9.090909090909091e-06, |
| "loss": 0.0138, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 0.412109375, |
| "learning_rate": 8.363636363636365e-06, |
| "loss": 0.0123, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.004983998369425535, |
| "eval_runtime": 3.1294, |
| "eval_samples_per_second": 15.658, |
| "eval_steps_per_second": 15.658, |
| "step": 165 |
| }, |
| { |
| "epoch": 3.090909090909091, |
| "grad_norm": 0.263671875, |
| "learning_rate": 7.636363636363638e-06, |
| "loss": 0.0084, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.2727272727272725, |
| "grad_norm": 0.384765625, |
| "learning_rate": 6.90909090909091e-06, |
| "loss": 0.0117, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.4545454545454546, |
| "grad_norm": 0.54296875, |
| "learning_rate": 6.181818181818182e-06, |
| "loss": 0.0088, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.6363636363636362, |
| "grad_norm": 0.361328125, |
| "learning_rate": 5.4545454545454545e-06, |
| "loss": 0.0079, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.8181818181818183, |
| "grad_norm": 0.345703125, |
| "learning_rate": 4.727272727272728e-06, |
| "loss": 0.0095, |
| "step": 210 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.35546875, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0103, |
| "step": 220 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.0046064225025475025, |
| "eval_runtime": 3.0063, |
| "eval_samples_per_second": 16.299, |
| "eval_steps_per_second": 16.299, |
| "step": 220 |
| }, |
| { |
| "epoch": 4.181818181818182, |
| "grad_norm": 0.32421875, |
| "learning_rate": 3.272727272727273e-06, |
| "loss": 0.0103, |
| "step": 230 |
| }, |
| { |
| "epoch": 4.363636363636363, |
| "grad_norm": 0.341796875, |
| "learning_rate": 2.5454545454545456e-06, |
| "loss": 0.0091, |
| "step": 240 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 0.306640625, |
| "learning_rate": 1.8181818181818183e-06, |
| "loss": 0.0096, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.7272727272727275, |
| "grad_norm": 0.337890625, |
| "learning_rate": 1.090909090909091e-06, |
| "loss": 0.0092, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.909090909090909, |
| "grad_norm": 0.3046875, |
| "learning_rate": 3.6363636363636366e-07, |
| "loss": 0.0072, |
| "step": 270 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.004624366760253906, |
| "eval_runtime": 3.0994, |
| "eval_samples_per_second": 15.809, |
| "eval_steps_per_second": 15.809, |
| "step": 275 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 275, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.88519679000576e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
