| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1175, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 3.7207822799682617, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 3.9659, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 6.125986576080322, | |
| "learning_rate": 4.1744680851063834e-05, | |
| "loss": 0.4412, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 2.0806655883789062, | |
| "learning_rate": 3.748936170212766e-05, | |
| "loss": 0.3628, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 2.888915538787842, | |
| "learning_rate": 3.3234042553191494e-05, | |
| "loss": 0.3836, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 2.3900370597839355, | |
| "learning_rate": 2.897872340425532e-05, | |
| "loss": 0.4249, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 11.082301139831543, | |
| "learning_rate": 2.4723404255319148e-05, | |
| "loss": 0.305, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 1.7785085439682007, | |
| "learning_rate": 2.046808510638298e-05, | |
| "loss": 0.3898, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 6.916086196899414, | |
| "learning_rate": 1.6212765957446808e-05, | |
| "loss": 0.3107, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 2.8340659141540527, | |
| "learning_rate": 1.1957446808510639e-05, | |
| "loss": 0.3754, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 1.609188199043274, | |
| "learning_rate": 7.702127659574469e-06, | |
| "loss": 0.4273, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 2.5411593914031982, | |
| "learning_rate": 3.446808510638298e-06, | |
| "loss": 0.403, | |
| "step": 1100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1175, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.71021067206656e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |