| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 11.48936170212766, | |
| "eval_steps": 500, | |
| "global_step": 2700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 0.7200157046318054, | |
| "learning_rate": 0.0001418439716312057, | |
| "loss": 1.039, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.5347419381141663, | |
| "learning_rate": 0.0002836879432624114, | |
| "loss": 0.6682, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 0.7219013571739197, | |
| "learning_rate": 0.000425531914893617, | |
| "loss": 0.5873, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 0.9977912306785583, | |
| "learning_rate": 0.0005673758865248228, | |
| "loss": 0.5932, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 0.946759819984436, | |
| "learning_rate": 0.0007092198581560284, | |
| "loss": 0.5843, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 0.9490156769752502, | |
| "learning_rate": 0.000851063829787234, | |
| "loss": 0.5616, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": 0.9529285430908203, | |
| "learning_rate": 0.0009929078014184398, | |
| "loss": 0.5976, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.404255319148936, | |
| "grad_norm": 1.0601491928100586, | |
| "learning_rate": 0.0009972024146827632, | |
| "loss": 0.5265, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.829787234042553, | |
| "grad_norm": 1.1251301765441895, | |
| "learning_rate": 0.0009882482608435923, | |
| "loss": 0.5463, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.25531914893617, | |
| "grad_norm": 1.0466716289520264, | |
| "learning_rate": 0.0009732407954960695, | |
| "loss": 0.4658, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.680851063829787, | |
| "grad_norm": 0.9589976072311401, | |
| "learning_rate": 0.0009523660814897424, | |
| "loss": 0.4432, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.1063829787234045, | |
| "grad_norm": 1.2019531726837158, | |
| "learning_rate": 0.0009258829239380381, | |
| "loss": 0.4233, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.531914893617021, | |
| "grad_norm": 0.7805734276771545, | |
| "learning_rate": 0.0008941196615473928, | |
| "loss": 0.3387, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.957446808510638, | |
| "grad_norm": 0.6454946994781494, | |
| "learning_rate": 0.0008574700958675344, | |
| "loss": 0.3554, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.382978723404255, | |
| "grad_norm": 0.8706166744232178, | |
| "learning_rate": 0.0008163886089321493, | |
| "loss": 0.2621, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.808510638297872, | |
| "grad_norm": 0.8278286457061768, | |
| "learning_rate": 0.0007713845298215226, | |
| "loss": 0.267, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 7.23404255319149, | |
| "grad_norm": 0.6279350519180298, | |
| "learning_rate": 0.0007230158199906162, | |
| "loss": 0.2148, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.659574468085106, | |
| "grad_norm": 0.5926242470741272, | |
| "learning_rate": 0.0006718821556520151, | |
| "loss": 0.1777, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 8.085106382978724, | |
| "grad_norm": 0.6583319306373596, | |
| "learning_rate": 0.0006186174929784868, | |
| "loss": 0.1703, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.51063829787234, | |
| "grad_norm": 0.6788440942764282, | |
| "learning_rate": 0.0005638822083019267, | |
| "loss": 0.1186, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.936170212765958, | |
| "grad_norm": 0.6308868527412415, | |
| "learning_rate": 0.0005083549107546504, | |
| "loss": 0.1129, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9.361702127659575, | |
| "grad_norm": 0.46226853132247925, | |
| "learning_rate": 0.000452724028860069, | |
| "loss": 0.0775, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9.787234042553191, | |
| "grad_norm": 0.5111752152442932, | |
| "learning_rate": 0.00039767927538236195, | |
| "loss": 0.0675, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 10.212765957446809, | |
| "grad_norm": 0.2776525020599365, | |
| "learning_rate": 0.00034390309625410685, | |
| "loss": 0.0573, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10.638297872340425, | |
| "grad_norm": 0.22762399911880493, | |
| "learning_rate": 0.00029206220959823183, | |
| "loss": 0.0432, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 11.063829787234043, | |
| "grad_norm": 0.11530320346355438, | |
| "learning_rate": 0.00024279933974365658, | |
| "loss": 0.0432, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 11.48936170212766, | |
| "grad_norm": 0.20928817987442017, | |
| "learning_rate": 0.0001967252487164663, | |
| "loss": 0.0325, | |
| "step": 2700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3525, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0806803429374771e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |