|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0610079575596818, |
|
"eval_steps": 100, |
|
"global_step": 1200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08841732979664015, |
|
"eval_accuracy": 0.1989687629116883, |
|
"eval_loss": 4.78662633895874, |
|
"eval_runtime": 26.1083, |
|
"eval_samples_per_second": 16.7, |
|
"eval_steps_per_second": 0.536, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.1768346595932803, |
|
"eval_accuracy": 0.330860012697261, |
|
"eval_loss": 4.04963493347168, |
|
"eval_runtime": 26.2098, |
|
"eval_samples_per_second": 16.635, |
|
"eval_steps_per_second": 0.534, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.26525198938992045, |
|
"eval_accuracy": 0.37791993303243177, |
|
"eval_loss": 3.652527332305908, |
|
"eval_runtime": 26.1862, |
|
"eval_samples_per_second": 16.65, |
|
"eval_steps_per_second": 0.535, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.3536693191865606, |
|
"eval_accuracy": 0.42577323076228935, |
|
"eval_loss": 3.2409958839416504, |
|
"eval_runtime": 26.1526, |
|
"eval_samples_per_second": 16.671, |
|
"eval_steps_per_second": 0.535, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.4420866489832007, |
|
"grad_norm": 195.0, |
|
"learning_rate": 4.263188918361332e-05, |
|
"loss": 3.9116, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.4420866489832007, |
|
"eval_accuracy": 0.39117474036699323, |
|
"eval_loss": 3.6305172443389893, |
|
"eval_runtime": 26.2335, |
|
"eval_samples_per_second": 16.62, |
|
"eval_steps_per_second": 0.534, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.5305039787798409, |
|
"eval_accuracy": 0.4406458382696409, |
|
"eval_loss": 3.177022695541382, |
|
"eval_runtime": 26.2979, |
|
"eval_samples_per_second": 16.579, |
|
"eval_steps_per_second": 0.532, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.618921308576481, |
|
"eval_accuracy": 0.5199022247813888, |
|
"eval_loss": 2.4477944374084473, |
|
"eval_runtime": 26.2814, |
|
"eval_samples_per_second": 16.59, |
|
"eval_steps_per_second": 0.533, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.7073386383731212, |
|
"eval_accuracy": 0.5508474097348983, |
|
"eval_loss": 2.238290548324585, |
|
"eval_runtime": 26.1919, |
|
"eval_samples_per_second": 16.646, |
|
"eval_steps_per_second": 0.535, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.7957559681697612, |
|
"eval_accuracy": 0.5634974176979812, |
|
"eval_loss": 2.1547296047210693, |
|
"eval_runtime": 26.0445, |
|
"eval_samples_per_second": 16.741, |
|
"eval_steps_per_second": 0.538, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.8841732979664014, |
|
"grad_norm": 1.6484375, |
|
"learning_rate": 3.526377836722665e-05, |
|
"loss": 2.4568, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.8841732979664014, |
|
"eval_accuracy": 0.5759096753818043, |
|
"eval_loss": 2.086787223815918, |
|
"eval_runtime": 26.1107, |
|
"eval_samples_per_second": 16.698, |
|
"eval_steps_per_second": 0.536, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.9725906277630415, |
|
"eval_accuracy": 0.5819702172527925, |
|
"eval_loss": 2.0399203300476074, |
|
"eval_runtime": 26.206, |
|
"eval_samples_per_second": 16.637, |
|
"eval_steps_per_second": 0.534, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 1.0610079575596818, |
|
"eval_accuracy": 0.5872521470246358, |
|
"eval_loss": 2.0102362632751465, |
|
"eval_runtime": 26.1934, |
|
"eval_samples_per_second": 16.645, |
|
"eval_steps_per_second": 0.534, |
|
"step": 1200 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 3393, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 200, |
|
"total_flos": 6.109527025070899e+17, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|