| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0, | |
| "loss": 3.1568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0, | |
| "loss": 2.0929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0, | |
| "loss": 1.8548, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0, | |
| "loss": 1.9561, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 31.57492020476853, | |
| "learning_rate": 0.0, | |
| "loss": 2.158, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 31.153859925878365, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1095, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 27.11565016529603, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9969, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 11.963172987739094, | |
| "learning_rate": 1.9393939393939395e-05, | |
| "loss": 1.8882, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 12.547776129299391, | |
| "learning_rate": 1.8787878787878792e-05, | |
| "loss": 2.2821, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 13.995949840524457, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.9093, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 32.10247036468728, | |
| "learning_rate": 1.7575757575757576e-05, | |
| "loss": 1.7738, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 12.920575409822058, | |
| "learning_rate": 1.6969696969696972e-05, | |
| "loss": 1.9714, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 12.06286747031755, | |
| "learning_rate": 1.6363636363636366e-05, | |
| "loss": 1.9296, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 8.907029074340802, | |
| "learning_rate": 1.575757575757576e-05, | |
| "loss": 1.8614, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 6.73971706849257, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 1.6771, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 17.60219359166014, | |
| "learning_rate": 1.4545454545454546e-05, | |
| "loss": 1.8053, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 16.964715579903814, | |
| "learning_rate": 1.3939393939393942e-05, | |
| "loss": 1.6802, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 17.69250115636477, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.7371, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": 15.007342258217257, | |
| "learning_rate": 1.2727272727272728e-05, | |
| "loss": 1.8895, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 12.014421697915866, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 1.74, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.420645268892007, | |
| "learning_rate": 1.1515151515151517e-05, | |
| "loss": 1.646, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 9.579171202930794, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 1.783, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.2857142857142856, | |
| "grad_norm": 9.480870311077393, | |
| "learning_rate": 1.0303030303030304e-05, | |
| "loss": 1.6975, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 11.085052433397502, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 1.5964, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.571428571428571, | |
| "grad_norm": 10.405891481014418, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.8499, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 7.19377512459299, | |
| "learning_rate": 8.484848484848486e-06, | |
| "loss": 1.9397, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.857142857142857, | |
| "grad_norm": 20.100305416386867, | |
| "learning_rate": 7.87878787878788e-06, | |
| "loss": 1.6575, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 6.598534461792029, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 1.8201, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 4.142857142857143, | |
| "grad_norm": 7.697231181333111, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.6547, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 5.6666359994095865, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 1.6578, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.428571428571429, | |
| "grad_norm": 9.64546505010074, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 1.5213, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 7.511399316368516, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 1.7394, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.714285714285714, | |
| "grad_norm": 11.799130579067045, | |
| "learning_rate": 4.242424242424243e-06, | |
| "loss": 1.7876, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 8.101541311297026, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 1.7558, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 11.45990563904692, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 1.8384, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |