| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 50, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "grad_norm": 8.943879127502441, |
| "learning_rate": 1e-05, |
| "loss": 6.5078125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 7.270186424255371, |
| "learning_rate": 9.990133642141359e-06, |
| "loss": 6.3984375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 6.37836217880249, |
| "learning_rate": 9.960573506572391e-06, |
| "loss": 6.265625, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 7.293685436248779, |
| "learning_rate": 9.911436253643445e-06, |
| "loss": 6.4765625, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 6.509436130523682, |
| "learning_rate": 9.842915805643156e-06, |
| "loss": 5.94921875, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 6.362916946411133, |
| "learning_rate": 9.755282581475769e-06, |
| "loss": 5.4921875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 5.7927021980285645, |
| "learning_rate": 9.648882429441258e-06, |
| "loss": 4.72265625, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 5.231319427490234, |
| "learning_rate": 9.524135262330098e-06, |
| "loss": 4.4375, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 4.42698860168457, |
| "learning_rate": 9.381533400219319e-06, |
| "loss": 3.96484375, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 4.680422782897949, |
| "learning_rate": 9.221639627510076e-06, |
| "loss": 3.75390625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 4.277739524841309, |
| "learning_rate": 9.045084971874738e-06, |
| "loss": 3.55859375, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 2.7924997806549072, |
| "learning_rate": 8.852566213878947e-06, |
| "loss": 3.197265625, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 2.460587739944458, |
| "learning_rate": 8.644843137107058e-06, |
| "loss": 3.109375, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 2.5406017303466797, |
| "learning_rate": 8.422735529643445e-06, |
| "loss": 3.052734375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 1.7918001413345337, |
| "learning_rate": 8.18711994874345e-06, |
| "loss": 2.892578125, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 2.0637993812561035, |
| "learning_rate": 7.938926261462366e-06, |
| "loss": 2.85546875, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 1.8007744550704956, |
| "learning_rate": 7.679133974894984e-06, |
| "loss": 2.806640625, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 1.7077529430389404, |
| "learning_rate": 7.408768370508577e-06, |
| "loss": 2.73046875, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 1.1725691556930542, |
| "learning_rate": 7.128896457825364e-06, |
| "loss": 2.681640625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.0897101163864136, |
| "learning_rate": 6.840622763423391e-06, |
| "loss": 2.623046875, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.8132862448692322, |
| "learning_rate": 6.545084971874738e-06, |
| "loss": 2.544921875, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.8589746952056885, |
| "learning_rate": 6.243449435824276e-06, |
| "loss": 2.5234375, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.8374803066253662, |
| "learning_rate": 5.936906572928625e-06, |
| "loss": 2.5009765625, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.7755547165870667, |
| "learning_rate": 5.626666167821522e-06, |
| "loss": 2.49609375, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.6400609612464905, |
| "learning_rate": 5.3139525976465675e-06, |
| "loss": 2.44921875, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.6098289489746094, |
| "learning_rate": 5e-06, |
| "loss": 2.431640625, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.5200854539871216, |
| "learning_rate": 4.686047402353433e-06, |
| "loss": 2.345703125, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5618451833724976, |
| "learning_rate": 4.373333832178478e-06, |
| "loss": 2.369140625, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4647158980369568, |
| "learning_rate": 4.063093427071376e-06, |
| "loss": 2.3720703125, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.4867274761199951, |
| "learning_rate": 3.756550564175727e-06, |
| "loss": 2.3134765625, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.46214717626571655, |
| "learning_rate": 3.4549150281252635e-06, |
| "loss": 2.302734375, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4446595311164856, |
| "learning_rate": 3.1593772365766107e-06, |
| "loss": 2.3447265625, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4361993074417114, |
| "learning_rate": 2.871103542174637e-06, |
| "loss": 2.275390625, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4201323688030243, |
| "learning_rate": 2.5912316294914232e-06, |
| "loss": 2.2158203125, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.38919582962989807, |
| "learning_rate": 2.320866025105016e-06, |
| "loss": 2.310546875, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.37592536211013794, |
| "learning_rate": 2.061073738537635e-06, |
| "loss": 2.2421875, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.30617988109588623, |
| "learning_rate": 1.8128800512565514e-06, |
| "loss": 2.2490234375, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.35477542877197266, |
| "learning_rate": 1.5772644703565564e-06, |
| "loss": 2.2861328125, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.3512473404407501, |
| "learning_rate": 1.3551568628929434e-06, |
| "loss": 2.255859375, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.3029632866382599, |
| "learning_rate": 1.1474337861210543e-06, |
| "loss": 2.33984375, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.35100874304771423, |
| "learning_rate": 9.549150281252633e-07, |
| "loss": 2.228515625, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.3360106945037842, |
| "learning_rate": 7.783603724899258e-07, |
| "loss": 2.2626953125, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.3178384602069855, |
| "learning_rate": 6.184665997806832e-07, |
| "loss": 2.2880859375, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.30692294239997864, |
| "learning_rate": 4.758647376699033e-07, |
| "loss": 2.220703125, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.3297945559024811, |
| "learning_rate": 3.511175705587433e-07, |
| "loss": 2.236328125, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.2796439826488495, |
| "learning_rate": 2.447174185242324e-07, |
| "loss": 2.255859375, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.3400841951370239, |
| "learning_rate": 1.5708419435684463e-07, |
| "loss": 2.1943359375, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.2745136320590973, |
| "learning_rate": 8.856374635655696e-08, |
| "loss": 2.2314453125, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.34550172090530396, |
| "learning_rate": 3.9426493427611177e-08, |
| "loss": 2.2314453125, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.3090897500514984, |
| "learning_rate": 9.866357858642206e-09, |
| "loss": 2.2744140625, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.24609375, |
| "eval_runtime": 0.5137, |
| "eval_samples_per_second": 3.894, |
| "eval_steps_per_second": 1.947, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.10228947633963e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
