|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.3185840707964602, |
|
"eval_steps": 9, |
|
"global_step": 36, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.008849557522123894, |
|
"eval_loss": 7.850747108459473, |
|
"eval_runtime": 11.9245, |
|
"eval_samples_per_second": 7.967, |
|
"eval_steps_per_second": 2.013, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02654867256637168, |
|
"grad_norm": 23.30268096923828, |
|
"learning_rate": 3e-05, |
|
"loss": 32.3052, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.05309734513274336, |
|
"grad_norm": 24.82865333557129, |
|
"learning_rate": 6e-05, |
|
"loss": 26.7374, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.07964601769911504, |
|
"grad_norm": 16.411090850830078, |
|
"learning_rate": 9e-05, |
|
"loss": 15.0507, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.07964601769911504, |
|
"eval_loss": 1.889989972114563, |
|
"eval_runtime": 12.1586, |
|
"eval_samples_per_second": 7.813, |
|
"eval_steps_per_second": 1.974, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.10619469026548672, |
|
"grad_norm": 16.30251693725586, |
|
"learning_rate": 9.987820251299122e-05, |
|
"loss": 4.4943, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.13274336283185842, |
|
"grad_norm": 2.594444513320923, |
|
"learning_rate": 9.924038765061042e-05, |
|
"loss": 1.7033, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.1592920353982301, |
|
"grad_norm": 0.005044514779001474, |
|
"learning_rate": 9.806308479691595e-05, |
|
"loss": 0.0137, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.1592920353982301, |
|
"eval_loss": 0.0003469553776085377, |
|
"eval_runtime": 12.2289, |
|
"eval_samples_per_second": 7.769, |
|
"eval_steps_per_second": 1.963, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.18584070796460178, |
|
"grad_norm": 0.012934673577547073, |
|
"learning_rate": 9.635919272833938e-05, |
|
"loss": 0.0003, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.21238938053097345, |
|
"grad_norm": 0.00015438912669196725, |
|
"learning_rate": 9.414737964294636e-05, |
|
"loss": 0.0002, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.23893805309734514, |
|
"grad_norm": 0.0381203256547451, |
|
"learning_rate": 9.145187862775209e-05, |
|
"loss": 0.0001, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.23893805309734514, |
|
"eval_loss": 1.8848184026865056e-06, |
|
"eval_runtime": 12.2379, |
|
"eval_samples_per_second": 7.763, |
|
"eval_steps_per_second": 1.961, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.26548672566371684, |
|
"grad_norm": 0.005300083197653294, |
|
"learning_rate": 8.83022221559489e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.2920353982300885, |
|
"grad_norm": 0.0005808924324810505, |
|
"learning_rate": 8.473291852294987e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.3185840707964602, |
|
"grad_norm": 0.8387057185173035, |
|
"learning_rate": 8.07830737662829e-05, |
|
"loss": 0.0023, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.3185840707964602, |
|
"eval_loss": 2.120336603184114e-06, |
|
"eval_runtime": 12.2271, |
|
"eval_samples_per_second": 7.77, |
|
"eval_steps_per_second": 1.963, |
|
"step": 36 |
|
} |
|
], |
|
"logging_steps": 3, |
|
"max_steps": 100, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 9, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5.184295048052736e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|