| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.032108913434369384, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003210891343436938, |
| "grad_norm": 8.177531242370605, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 2.2773, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006421782686873876, |
| "grad_norm": 0.6572615504264832, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.2291, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.009632674030310814, |
| "grad_norm": 0.6884369254112244, |
| "learning_rate": 1.2e-05, |
| "loss": 0.1612, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.012843565373747753, |
| "grad_norm": 0.32834213972091675, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.1469, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.016054456717184692, |
| "grad_norm": 0.3822823166847229, |
| "learning_rate": 2e-05, |
| "loss": 0.1699, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.019265348060621627, |
| "grad_norm": 0.3158350884914398, |
| "learning_rate": 1.9975640502598243e-05, |
| "loss": 0.1448, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.022476239404058566, |
| "grad_norm": 984.7891845703125, |
| "learning_rate": 1.9902680687415704e-05, |
| "loss": 0.1638, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.025687130747495505, |
| "grad_norm": 0.2283572256565094, |
| "learning_rate": 1.9781476007338058e-05, |
| "loss": 0.1346, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.028898022090932445, |
| "grad_norm": 0.24141617119312286, |
| "learning_rate": 1.961261695938319e-05, |
| "loss": 0.1347, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.032108913434369384, |
| "grad_norm": 0.2759339213371277, |
| "learning_rate": 1.9396926207859085e-05, |
| "loss": 0.1269, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 2500, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.299061445492736e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
