| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005264081417792595, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017546938059308652, | |
| "grad_norm": 0.021896077319979668, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017546938059308652, | |
| "eval_loss": 10.378170013427734, | |
| "eval_runtime": 20.1811, | |
| "eval_samples_per_second": 118.923, | |
| "eval_steps_per_second": 59.462, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035093876118617303, | |
| "grad_norm": 0.02895743027329445, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3799, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005264081417792595, | |
| "grad_norm": 0.03139834105968475, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3833, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007018775223723461, | |
| "grad_norm": 0.03180989623069763, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3725, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008773469029654326, | |
| "grad_norm": 0.04147100821137428, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3725, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001052816283558519, | |
| "grad_norm": 0.034542471170425415, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3629, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012282856641516056, | |
| "grad_norm": 0.030410971492528915, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3853, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014037550447446921, | |
| "grad_norm": 0.026322724297642708, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3725, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014037550447446921, | |
| "eval_loss": 10.377918243408203, | |
| "eval_runtime": 20.1636, | |
| "eval_samples_per_second": 119.026, | |
| "eval_steps_per_second": 59.513, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015792244253377786, | |
| "grad_norm": 0.023104362189769745, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3882, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001754693805930865, | |
| "grad_norm": 0.0319962278008461, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3865, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019301631865239516, | |
| "grad_norm": 0.031027458608150482, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 10.3821, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002105632567117038, | |
| "grad_norm": 0.04138890653848648, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3692, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022811019477101246, | |
| "grad_norm": 0.02614734135568142, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 10.3891, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0024565713283032113, | |
| "grad_norm": 0.02401694655418396, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.3821, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0026320407088962976, | |
| "grad_norm": 0.03232363983988762, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3736, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0028075100894893843, | |
| "grad_norm": 0.02802196890115738, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 10.3833, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028075100894893843, | |
| "eval_loss": 10.37726879119873, | |
| "eval_runtime": 20.1987, | |
| "eval_samples_per_second": 118.819, | |
| "eval_steps_per_second": 59.41, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0029829794700824705, | |
| "grad_norm": 0.032058119773864746, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 10.3759, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0031584488506755572, | |
| "grad_norm": 0.03021497279405594, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3804, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0033339182312686435, | |
| "grad_norm": 0.02468908578157425, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 10.3832, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00350938761186173, | |
| "grad_norm": 0.03662308305501938, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036848569924548165, | |
| "grad_norm": 0.031086675822734833, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3756, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003860326373047903, | |
| "grad_norm": 0.030318187549710274, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 10.372, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00403579575364099, | |
| "grad_norm": 0.03376461938023567, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 10.377, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004211265134234076, | |
| "grad_norm": 0.02785138599574566, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3689, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004211265134234076, | |
| "eval_loss": 10.376875877380371, | |
| "eval_runtime": 20.1626, | |
| "eval_samples_per_second": 119.032, | |
| "eval_steps_per_second": 59.516, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0043867345148271624, | |
| "grad_norm": 0.02769087813794613, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 10.374, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004562203895420249, | |
| "grad_norm": 0.03563356772065163, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 10.38, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004737673276013336, | |
| "grad_norm": 0.0283515527844429, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.379, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0049131426566064226, | |
| "grad_norm": 0.029156768694519997, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 10.3778, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005088612037199508, | |
| "grad_norm": 0.02999081462621689, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 10.377, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005264081417792595, | |
| "grad_norm": 0.031297340989112854, | |
| "learning_rate": 0.0, | |
| "loss": 10.3777, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1551708979200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |