| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 32, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0625, |
| "grad_norm": 0.0405812395222138, |
| "learning_rate": 1.25e-05, |
| "loss": 0.1831, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 0.04266307796780707, |
| "learning_rate": 2.5e-05, |
| "loss": 0.1798, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1875, |
| "grad_norm": 0.03931529137801882, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.1876, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.04450622538530822, |
| "learning_rate": 5e-05, |
| "loss": 0.1835, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.3125, |
| "grad_norm": 0.04469630327779733, |
| "learning_rate": 4.984280524733107e-05, |
| "loss": 0.1813, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 0.04907326921588077, |
| "learning_rate": 4.937319780454559e-05, |
| "loss": 0.167, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.4375, |
| "grad_norm": 0.04063536785408177, |
| "learning_rate": 4.8597083257709194e-05, |
| "loss": 0.1692, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.029628268241714627, |
| "learning_rate": 4.752422169756048e-05, |
| "loss": 0.1731, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.5625, |
| "grad_norm": 0.02885670095202559, |
| "learning_rate": 4.6168104980707107e-05, |
| "loss": 0.1605, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.03571279049752427, |
| "learning_rate": 4.454578706170075e-05, |
| "loss": 0.1533, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6875, |
| "grad_norm": 0.048775534324840226, |
| "learning_rate": 4.267766952966369e-05, |
| "loss": 0.1599, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.04440678150165617, |
| "learning_rate": 4.058724504646834e-05, |
| "loss": 0.1518, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.8125, |
| "grad_norm": 0.04145952387262748, |
| "learning_rate": 3.830080191288342e-05, |
| "loss": 0.156, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.875, |
| "grad_norm": 0.028884854532921472, |
| "learning_rate": 3.5847093477938956e-05, |
| "loss": 0.1515, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.9375, |
| "grad_norm": 0.023905265288016668, |
| "learning_rate": 3.3256976548879184e-05, |
| "loss": 0.1423, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.02330271438867509, |
| "learning_rate": 3.056302334890786e-05, |
| "loss": 0.1445, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.0625, |
| "grad_norm": 0.01765167150763442, |
| "learning_rate": 2.7799111902582696e-05, |
| "loss": 0.146, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.125, |
| "grad_norm": 0.018465045106513908, |
| "learning_rate": 2.5e-05, |
| "loss": 0.144, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.1875, |
| "grad_norm": 0.01791610056838167, |
| "learning_rate": 2.2200888097417307e-05, |
| "loss": 0.1265, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.02024006396567914, |
| "learning_rate": 1.9436976651092144e-05, |
| "loss": 0.1313, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.3125, |
| "grad_norm": 0.02055242205104592, |
| "learning_rate": 1.6743023451120832e-05, |
| "loss": 0.1276, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.375, |
| "grad_norm": 0.02620405124794344, |
| "learning_rate": 1.4152906522061048e-05, |
| "loss": 0.1295, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.4375, |
| "grad_norm": 0.02312683668569585, |
| "learning_rate": 1.1699198087116589e-05, |
| "loss": 0.1316, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.020663068542080693, |
| "learning_rate": 9.412754953531663e-06, |
| "loss": 0.134, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.5625, |
| "grad_norm": 0.02224169228928786, |
| "learning_rate": 7.3223304703363135e-06, |
| "loss": 0.1201, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.625, |
| "grad_norm": 0.020929932081834416, |
| "learning_rate": 5.454212938299255e-06, |
| "loss": 0.1293, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.6875, |
| "grad_norm": 0.019127606995202735, |
| "learning_rate": 3.831895019292897e-06, |
| "loss": 0.1398, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.75, |
| "grad_norm": 0.019156977344190494, |
| "learning_rate": 2.475778302439524e-06, |
| "loss": 0.1242, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.8125, |
| "grad_norm": 0.02123282757168043, |
| "learning_rate": 1.4029167422908107e-06, |
| "loss": 0.1173, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 0.01929242062693528, |
| "learning_rate": 6.268021954544096e-07, |
| "loss": 0.1326, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.9375, |
| "grad_norm": 0.0196613930735786, |
| "learning_rate": 1.571947526689349e-07, |
| "loss": 0.113, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.019793900466732767, |
| "learning_rate": 0.0, |
| "loss": 0.1429, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 32, |
| "total_flos": 598705943085056.0, |
| "train_loss": 0.14793596579693258, |
| "train_runtime": 1049.7373, |
| "train_samples_per_second": 0.476, |
| "train_steps_per_second": 0.03 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 598705943085056.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
