| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002784658850283977, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.282196167613258e-05, | |
| "grad_norm": 0.014820126816630363, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9313, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.282196167613258e-05, | |
| "eval_loss": 11.928583145141602, | |
| "eval_runtime": 139.8719, | |
| "eval_samples_per_second": 129.726, | |
| "eval_steps_per_second": 64.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018564392335226516, | |
| "grad_norm": 0.01485100481659174, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9297, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002784658850283977, | |
| "grad_norm": 0.015872972086071968, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9286, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003712878467045303, | |
| "grad_norm": 0.01684979908168316, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9287, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00046410980838066285, | |
| "grad_norm": 0.01272808201611042, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9293, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005569317700567954, | |
| "grad_norm": 0.018846917897462845, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9299, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000649753731732928, | |
| "grad_norm": 0.013215523213148117, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9287, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007425756934090606, | |
| "grad_norm": 0.016623178496956825, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9304, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007425756934090606, | |
| "eval_loss": 11.928462982177734, | |
| "eval_runtime": 115.0141, | |
| "eval_samples_per_second": 157.763, | |
| "eval_steps_per_second": 78.886, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008353976550851931, | |
| "grad_norm": 0.012540486641228199, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9294, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009282196167613257, | |
| "grad_norm": 0.016163840889930725, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010210415784374584, | |
| "grad_norm": 0.018371539190411568, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 11.9273, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011138635401135909, | |
| "grad_norm": 0.016105543822050095, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.9294, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012066855017897234, | |
| "grad_norm": 0.012495412491261959, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 11.929, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001299507463465856, | |
| "grad_norm": 0.014130703173577785, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.9288, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0013923294251419885, | |
| "grad_norm": 0.011071882210671902, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9295, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014851513868181212, | |
| "grad_norm": 0.015319784171879292, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 11.93, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014851513868181212, | |
| "eval_loss": 11.928154945373535, | |
| "eval_runtime": 115.181, | |
| "eval_samples_per_second": 157.535, | |
| "eval_steps_per_second": 78.772, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015779733484942537, | |
| "grad_norm": 0.012164338491857052, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 11.9297, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0016707953101703862, | |
| "grad_norm": 0.017325541004538536, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.9274, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001763617271846519, | |
| "grad_norm": 0.01545996405184269, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 11.9279, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0018564392335226514, | |
| "grad_norm": 0.012894785962998867, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001949261195198784, | |
| "grad_norm": 0.01422932744026184, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 11.929, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002042083156874917, | |
| "grad_norm": 0.011517844162881374, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.9292, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002134905118551049, | |
| "grad_norm": 0.0101248100399971, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 11.9274, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0022277270802271818, | |
| "grad_norm": 0.015307254157960415, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 11.9269, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0022277270802271818, | |
| "eval_loss": 11.927979469299316, | |
| "eval_runtime": 115.0963, | |
| "eval_samples_per_second": 157.651, | |
| "eval_steps_per_second": 78.83, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0023205490419033145, | |
| "grad_norm": 0.011979633010923862, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9303, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0024133710035794467, | |
| "grad_norm": 0.011392545886337757, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.9293, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0025061929652555794, | |
| "grad_norm": 0.012941389344632626, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 11.9301, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002599014926931712, | |
| "grad_norm": 0.01663537509739399, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 11.9283, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002691836888607845, | |
| "grad_norm": 0.016010815277695656, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 11.929, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002784658850283977, | |
| "grad_norm": 0.01459334883838892, | |
| "learning_rate": 0.0, | |
| "loss": 11.9295, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 183994810368.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |