| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004083299305839118, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.166598611678236e-05, | |
| "grad_norm": 17.062883377075195, | |
| "learning_rate": 1e-05, | |
| "loss": 16.3788, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016333197223356472, | |
| "grad_norm": 16.815052032470703, | |
| "learning_rate": 2e-05, | |
| "loss": 17.0944, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002449979583503471, | |
| "grad_norm": 15.38818359375, | |
| "learning_rate": 3e-05, | |
| "loss": 15.4768, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00032666394446712944, | |
| "grad_norm": 17.041973114013672, | |
| "learning_rate": 4e-05, | |
| "loss": 17.3649, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004083299305839118, | |
| "grad_norm": 17.13035774230957, | |
| "learning_rate": 5e-05, | |
| "loss": 16.6489, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004899959167006942, | |
| "grad_norm": 13.58702564239502, | |
| "learning_rate": 6e-05, | |
| "loss": 14.0781, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005716619028174765, | |
| "grad_norm": 20.45118522644043, | |
| "learning_rate": 7e-05, | |
| "loss": 17.083, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006533278889342589, | |
| "grad_norm": 15.224943161010742, | |
| "learning_rate": 8e-05, | |
| "loss": 14.265, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007349938750510413, | |
| "grad_norm": 19.753936767578125, | |
| "learning_rate": 9e-05, | |
| "loss": 15.9611, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008166598611678236, | |
| "grad_norm": 14.75539779663086, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8529, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008983258472846059, | |
| "grad_norm": 17.792478561401367, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 12.8627, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0009799918334013884, | |
| "grad_norm": 21.60731315612793, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 13.4647, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010616578195181707, | |
| "grad_norm": 20.792444229125977, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 11.4533, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001143323805634953, | |
| "grad_norm": 23.68138885498047, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.5595, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012249897917517355, | |
| "grad_norm": 23.770912170410156, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.0865, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013066557778685177, | |
| "grad_norm": 21.059650421142578, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 7.6707, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013883217639853, | |
| "grad_norm": 19.416791915893555, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 7.7917, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0014699877501020825, | |
| "grad_norm": 20.199934005737305, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 6.7672, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015516537362188648, | |
| "grad_norm": 14.885459899902344, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 6.3004, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016333197223356473, | |
| "grad_norm": 13.609525680541992, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.3353, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017149857084524296, | |
| "grad_norm": 14.643861770629883, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 4.949, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0017966516945692118, | |
| "grad_norm": 14.1854887008667, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 5.4522, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0018783176806859943, | |
| "grad_norm": 17.34560203552246, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 5.9855, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001959983666802777, | |
| "grad_norm": 13.090412139892578, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 4.6431, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002041649652919559, | |
| "grad_norm": 15.996393203735352, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.3132, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0021233156390363414, | |
| "grad_norm": 10.16431999206543, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.8058, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0022049816251531237, | |
| "grad_norm": 10.617476463317871, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 4.1444, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002286647611269906, | |
| "grad_norm": 13.555794715881348, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 4.7664, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0023683135973866887, | |
| "grad_norm": 13.246901512145996, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 4.1173, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002449979583503471, | |
| "grad_norm": 10.543293952941895, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5346, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002531645569620253, | |
| "grad_norm": 10.046747207641602, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 3.517, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0026133115557370355, | |
| "grad_norm": 12.166019439697266, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 3.6236, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0026949775418538178, | |
| "grad_norm": 12.2982177734375, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 3.6672, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0027766435279706, | |
| "grad_norm": 12.674460411071777, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.7041, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0028583095140873828, | |
| "grad_norm": 12.634148597717285, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.8066, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.002939975500204165, | |
| "grad_norm": 11.344902992248535, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 3.2383, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0030216414863209473, | |
| "grad_norm": 10.499024391174316, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 3.3032, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0031033074724377296, | |
| "grad_norm": 11.4461030960083, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 3.1557, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.003184973458554512, | |
| "grad_norm": 9.176321983337402, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 2.606, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0032666394446712946, | |
| "grad_norm": 10.370387077331543, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.6242, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003348305430788077, | |
| "grad_norm": 9.519536018371582, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 3.5738, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003429971416904859, | |
| "grad_norm": 8.939133644104004, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.9957, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0035116374030216414, | |
| "grad_norm": 9.010765075683594, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 3.0591, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0035933033891384237, | |
| "grad_norm": 11.157018661499023, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 2.9803, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0036749693752552064, | |
| "grad_norm": 10.017087936401367, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8752, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0037566353613719887, | |
| "grad_norm": 11.067434310913086, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 3.2134, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.003838301347488771, | |
| "grad_norm": 8.755880355834961, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 3.1501, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.003919967333605554, | |
| "grad_norm": 9.387955665588379, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 2.8307, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0040016333197223355, | |
| "grad_norm": 7.871840476989746, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 2.7456, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.004083299305839118, | |
| "grad_norm": 8.828238487243652, | |
| "learning_rate": 0.0, | |
| "loss": 3.4735, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004083299305839118, | |
| "eval_loss": 0.9224815368652344, | |
| "eval_runtime": 0.2523, | |
| "eval_samples_per_second": 39.638, | |
| "eval_steps_per_second": 19.819, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2987656426291200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |