|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0014114160031051153, |
|
"eval_steps": 5, |
|
"global_step": 30, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 4.704720010350384e-05, |
|
"eval_loss": 2.2353053092956543, |
|
"eval_runtime": 172.454, |
|
"eval_samples_per_second": 51.898, |
|
"eval_steps_per_second": 25.949, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00014114160031051152, |
|
"grad_norm": 1.6285557746887207, |
|
"learning_rate": 3e-05, |
|
"loss": 9.1049, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0002352360005175192, |
|
"eval_loss": 2.2215254306793213, |
|
"eval_runtime": 172.4694, |
|
"eval_samples_per_second": 51.893, |
|
"eval_steps_per_second": 25.947, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00028228320062102303, |
|
"grad_norm": 1.4452866315841675, |
|
"learning_rate": 6e-05, |
|
"loss": 8.538, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.00042342480093153457, |
|
"grad_norm": 1.5918633937835693, |
|
"learning_rate": 9e-05, |
|
"loss": 8.8431, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0004704720010350384, |
|
"eval_loss": 2.115410804748535, |
|
"eval_runtime": 172.4125, |
|
"eval_samples_per_second": 51.91, |
|
"eval_steps_per_second": 25.955, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0005645664012420461, |
|
"grad_norm": 1.854500412940979, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 8.4177, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0007057080015525577, |
|
"grad_norm": 2.6493282318115234, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 8.3907, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0007057080015525577, |
|
"eval_loss": 2.0367188453674316, |
|
"eval_runtime": 172.7142, |
|
"eval_samples_per_second": 51.82, |
|
"eval_steps_per_second": 25.91, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0008468496018630691, |
|
"grad_norm": 1.9623610973358154, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 8.0375, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0009409440020700768, |
|
"eval_loss": 1.9632492065429688, |
|
"eval_runtime": 172.4725, |
|
"eval_samples_per_second": 51.892, |
|
"eval_steps_per_second": 25.946, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0009879912021735807, |
|
"grad_norm": 1.8358335494995117, |
|
"learning_rate": 4.2178276747988446e-05, |
|
"loss": 7.643, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.0011291328024840921, |
|
"grad_norm": 1.6776705980300903, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 7.5998, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.001176180002587596, |
|
"eval_loss": 1.9313894510269165, |
|
"eval_runtime": 172.5931, |
|
"eval_samples_per_second": 51.856, |
|
"eval_steps_per_second": 25.928, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0012702744027946037, |
|
"grad_norm": 1.7137739658355713, |
|
"learning_rate": 5.449673790581611e-06, |
|
"loss": 7.4771, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.0014114160031051153, |
|
"grad_norm": 1.9183655977249146, |
|
"learning_rate": 0.0, |
|
"loss": 8.0373, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0014114160031051153, |
|
"eval_loss": 1.9244450330734253, |
|
"eval_runtime": 172.6698, |
|
"eval_samples_per_second": 51.833, |
|
"eval_steps_per_second": 25.917, |
|
"step": 30 |
|
} |
|
], |
|
"logging_steps": 3, |
|
"max_steps": 30, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 10, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2197632508231680.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|