| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.047619047619047616, |
| "grad_norm": 1.030305027961731, |
| "learning_rate": 0.0, |
| "loss": 2.7470703125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 1.1125051975250244, |
| "learning_rate": 1e-05, |
| "loss": 2.830078125, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 0.7187039852142334, |
| "learning_rate": 2e-05, |
| "loss": 2.2998046875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 1.1063803434371948, |
| "learning_rate": 1.9877251730624504e-05, |
| "loss": 3.041015625, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 0.6889466643333435, |
| "learning_rate": 1.9512355175305713e-05, |
| "loss": 2.1376953125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "eval_loss": 2.296875, |
| "eval_runtime": 5.3912, |
| "eval_samples_per_second": 0.371, |
| "eval_steps_per_second": 0.185, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.7164807319641113, |
| "learning_rate": 1.89152637608584e-05, |
| "loss": 2.130859375, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 1.202832579612732, |
| "learning_rate": 1.8102264584567543e-05, |
| "loss": 2.873046875, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.9575077295303345, |
| "learning_rate": 1.709553414463167e-05, |
| "loss": 2.392578125, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.8331758379936218, |
| "learning_rate": 1.5922533423101843e-05, |
| "loss": 2.23828125, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "eval_loss": 2.0, |
| "eval_runtime": 5.2865, |
| "eval_samples_per_second": 0.378, |
| "eval_steps_per_second": 0.189, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 0.7220287322998047, |
| "learning_rate": 1.4615258821876728e-05, |
| "loss": 1.9892578125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 0.8401488065719604, |
| "learning_rate": 1.3209369384267194e-05, |
| "loss": 2.3359375, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.8397203087806702, |
| "learning_rate": 1.1743214109250994e-05, |
| "loss": 2.4375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 0.7059556841850281, |
| "learning_rate": 1.0256785890749011e-05, |
| "loss": 2.181640625, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "eval_loss": 1.77734375, |
| "eval_runtime": 5.2751, |
| "eval_samples_per_second": 0.379, |
| "eval_steps_per_second": 0.19, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.665387749671936, |
| "learning_rate": 8.790630615732809e-06, |
| "loss": 2.12109375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.5787039399147034, |
| "learning_rate": 7.384741178123278e-06, |
| "loss": 1.9638671875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.5149873495101929, |
| "learning_rate": 6.077466576898161e-06, |
| "loss": 1.7607421875, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 0.5400381088256836, |
| "learning_rate": 4.904465855368333e-06, |
| "loss": 1.9052734375, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "eval_loss": 1.6875, |
| "eval_runtime": 5.2687, |
| "eval_samples_per_second": 0.38, |
| "eval_steps_per_second": 0.19, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 0.4548075795173645, |
| "learning_rate": 3.89773541543246e-06, |
| "loss": 1.66064453125, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 0.473891943693161, |
| "learning_rate": 3.0847362391415995e-06, |
| "loss": 1.677734375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.46464210748672485, |
| "learning_rate": 2.4876448246942884e-06, |
| "loss": 1.767578125, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5290471315383911, |
| "learning_rate": 2.1227482693754995e-06, |
| "loss": 2.05859375, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.65625, |
| "eval_runtime": 5.2649, |
| "eval_samples_per_second": 0.38, |
| "eval_steps_per_second": 0.19, |
| "step": 21 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 21, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.396989743899607e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
