| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 179, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.027932960893854747, |
| "grad_norm": 6.217156410217285, |
| "learning_rate": 2.3529411764705885e-06, |
| "loss": 0.4419, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.055865921787709494, |
| "grad_norm": 5.510581970214844, |
| "learning_rate": 5.294117647058824e-06, |
| "loss": 0.4127, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08379888268156424, |
| "grad_norm": 5.5799174308776855, |
| "learning_rate": 8.23529411764706e-06, |
| "loss": 0.4641, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.11173184357541899, |
| "grad_norm": 7.177088737487793, |
| "learning_rate": 9.999635004278054e-06, |
| "loss": 0.4635, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13966480446927373, |
| "grad_norm": 6.450545310974121, |
| "learning_rate": 9.995529414369582e-06, |
| "loss": 0.4839, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.16759776536312848, |
| "grad_norm": 5.527288913726807, |
| "learning_rate": 9.986865748457457e-06, |
| "loss": 0.4175, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.19553072625698323, |
| "grad_norm": 5.916306972503662, |
| "learning_rate": 9.973651911539209e-06, |
| "loss": 0.4671, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.22346368715083798, |
| "grad_norm": 5.527400493621826, |
| "learning_rate": 9.955899960329546e-06, |
| "loss": 0.4643, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.25139664804469275, |
| "grad_norm": 5.982852458953857, |
| "learning_rate": 9.933626092259439e-06, |
| "loss": 0.4754, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.27932960893854747, |
| "grad_norm": 5.4895710945129395, |
| "learning_rate": 9.906850630697068e-06, |
| "loss": 0.4728, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.30726256983240224, |
| "grad_norm": 6.2167463302612305, |
| "learning_rate": 9.875598006404164e-06, |
| "loss": 0.4711, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.33519553072625696, |
| "grad_norm": 5.332173824310303, |
| "learning_rate": 9.839896735244615e-06, |
| "loss": 0.4728, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.36312849162011174, |
| "grad_norm": 6.088379383087158, |
| "learning_rate": 9.799779392165716e-06, |
| "loss": 0.5057, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.39106145251396646, |
| "grad_norm": 6.17716121673584, |
| "learning_rate": 9.755282581475769e-06, |
| "loss": 0.4768, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.41899441340782123, |
| "grad_norm": 7.213939666748047, |
| "learning_rate": 9.706446903445179e-06, |
| "loss": 0.5043, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.44692737430167595, |
| "grad_norm": 5.0204691886901855, |
| "learning_rate": 9.653316917261511e-06, |
| "loss": 0.4568, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4748603351955307, |
| "grad_norm": 6.00094747543335, |
| "learning_rate": 9.595941100372301e-06, |
| "loss": 0.4883, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.5027932960893855, |
| "grad_norm": 5.573389530181885, |
| "learning_rate": 9.534371804252727e-06, |
| "loss": 0.489, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5307262569832403, |
| "grad_norm": 4.436511039733887, |
| "learning_rate": 9.46866520663851e-06, |
| "loss": 0.4552, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5586592178770949, |
| "grad_norm": 5.606967926025391, |
| "learning_rate": 9.398881260267589e-06, |
| "loss": 0.4961, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5865921787709497, |
| "grad_norm": 6.480439186096191, |
| "learning_rate": 9.325083638177401e-06, |
| "loss": 0.5207, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.6145251396648045, |
| "grad_norm": 5.892640590667725, |
| "learning_rate": 9.247339675607606e-06, |
| "loss": 0.4952, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6424581005586593, |
| "grad_norm": 5.1815314292907715, |
| "learning_rate": 9.165720308561347e-06, |
| "loss": 0.499, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.6703910614525139, |
| "grad_norm": 5.886406421661377, |
| "learning_rate": 9.080300009081025e-06, |
| "loss": 0.4907, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.6983240223463687, |
| "grad_norm": 5.219560146331787, |
| "learning_rate": 8.991156717297702e-06, |
| "loss": 0.4764, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.7262569832402235, |
| "grad_norm": 5.498112678527832, |
| "learning_rate": 8.898371770316113e-06, |
| "loss": 0.4684, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7541899441340782, |
| "grad_norm": 5.503330707550049, |
| "learning_rate": 8.802029828000157e-06, |
| "loss": 0.4854, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.7821229050279329, |
| "grad_norm": 5.640200614929199, |
| "learning_rate": 8.702218795726619e-06, |
| "loss": 0.5091, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8100558659217877, |
| "grad_norm": 5.910928726196289, |
| "learning_rate": 8.599029744177577e-06, |
| "loss": 0.4581, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.8379888268156425, |
| "grad_norm": 7.0951738357543945, |
| "learning_rate": 8.492556826244687e-06, |
| "loss": 0.4986, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8659217877094972, |
| "grad_norm": 4.941314697265625, |
| "learning_rate": 8.382897191121157e-06, |
| "loss": 0.4898, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.8938547486033519, |
| "grad_norm": 5.991004467010498, |
| "learning_rate": 8.270150895659824e-06, |
| "loss": 0.4634, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9217877094972067, |
| "grad_norm": 5.34398889541626, |
| "learning_rate": 8.154420813078155e-06, |
| "loss": 0.505, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.9497206703910615, |
| "grad_norm": 5.032632350921631, |
| "learning_rate": 8.035812539093557e-06, |
| "loss": 0.4554, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.9776536312849162, |
| "grad_norm": 5.789834022521973, |
| "learning_rate": 7.914434295574552e-06, |
| "loss": 0.4456, |
| "step": 175 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 537, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.422076336903291e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
