|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0001149410607782787, |
|
"eval_steps": 3, |
|
"global_step": 9, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.2771228975364299e-05, |
|
"grad_norm": 1.7874619960784912, |
|
"learning_rate": 2e-05, |
|
"loss": 12.8567, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 1.2771228975364299e-05, |
|
"eval_loss": 3.4389500617980957, |
|
"eval_runtime": 284.6198, |
|
"eval_samples_per_second": 115.835, |
|
"eval_steps_per_second": 57.919, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 2.5542457950728598e-05, |
|
"grad_norm": 1.8470408916473389, |
|
"learning_rate": 4e-05, |
|
"loss": 12.9693, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 3.8313686926092896e-05, |
|
"grad_norm": 1.853289008140564, |
|
"learning_rate": 6e-05, |
|
"loss": 14.4906, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 3.8313686926092896e-05, |
|
"eval_loss": 3.439675807952881, |
|
"eval_runtime": 283.588, |
|
"eval_samples_per_second": 116.257, |
|
"eval_steps_per_second": 58.13, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 5.1084915901457196e-05, |
|
"grad_norm": 1.82938814163208, |
|
"learning_rate": 8e-05, |
|
"loss": 13.5146, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 6.38561448768215e-05, |
|
"grad_norm": 1.9475919008255005, |
|
"learning_rate": 0.0001, |
|
"loss": 12.9003, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 7.662737385218579e-05, |
|
"grad_norm": 1.7962164878845215, |
|
"learning_rate": 0.00012, |
|
"loss": 13.3743, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 7.662737385218579e-05, |
|
"eval_loss": 3.4317994117736816, |
|
"eval_runtime": 283.8601, |
|
"eval_samples_per_second": 116.145, |
|
"eval_steps_per_second": 58.074, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 8.93986028275501e-05, |
|
"grad_norm": 1.9254177808761597, |
|
"learning_rate": 0.00014, |
|
"loss": 14.1191, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.00010216983180291439, |
|
"grad_norm": 1.966262936592102, |
|
"learning_rate": 0.00016, |
|
"loss": 13.6299, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0001149410607782787, |
|
"grad_norm": 2.2013680934906006, |
|
"learning_rate": 0.00018, |
|
"loss": 14.1981, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0001149410607782787, |
|
"eval_loss": 3.4004440307617188, |
|
"eval_runtime": 286.8421, |
|
"eval_samples_per_second": 114.938, |
|
"eval_steps_per_second": 57.471, |
|
"step": 9 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 19100445179904.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|