|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.2328830926874709, |
|
"eval_steps": 100, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02328830926874709, |
|
"eval_accuracy": 0.6251894229623197, |
|
"eval_loss": 1.7397805452346802, |
|
"eval_runtime": 28.5721, |
|
"eval_samples_per_second": 20.335, |
|
"eval_steps_per_second": 0.35, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.04657661853749418, |
|
"eval_accuracy": 0.7068097781429745, |
|
"eval_loss": 1.3044862747192383, |
|
"eval_runtime": 28.3133, |
|
"eval_samples_per_second": 20.52, |
|
"eval_steps_per_second": 0.353, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.06986492780624126, |
|
"eval_accuracy": 0.7264728450848325, |
|
"eval_loss": 1.1957931518554688, |
|
"eval_runtime": 28.4954, |
|
"eval_samples_per_second": 20.389, |
|
"eval_steps_per_second": 0.351, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.09315323707498836, |
|
"eval_accuracy": 0.7365680716597873, |
|
"eval_loss": 1.1367889642715454, |
|
"eval_runtime": 28.5011, |
|
"eval_samples_per_second": 20.385, |
|
"eval_steps_per_second": 0.351, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.11644154634373545, |
|
"grad_norm": 1.4327788352966309, |
|
"learning_rate": 4.8059307560937745e-05, |
|
"loss": 1.6774, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.11644154634373545, |
|
"eval_accuracy": 0.7479708350529647, |
|
"eval_loss": 1.0806397199630737, |
|
"eval_runtime": 28.3151, |
|
"eval_samples_per_second": 20.519, |
|
"eval_steps_per_second": 0.353, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.13972985561248252, |
|
"eval_accuracy": 0.7532630012849124, |
|
"eval_loss": 1.0570966005325317, |
|
"eval_runtime": 28.5769, |
|
"eval_samples_per_second": 20.331, |
|
"eval_steps_per_second": 0.35, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.1630181648812296, |
|
"eval_accuracy": 0.7630408550249957, |
|
"eval_loss": 1.014039397239685, |
|
"eval_runtime": 28.2978, |
|
"eval_samples_per_second": 20.532, |
|
"eval_steps_per_second": 0.353, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.18630647414997673, |
|
"eval_accuracy": 0.7612289910578419, |
|
"eval_loss": 1.0060029029846191, |
|
"eval_runtime": 28.4993, |
|
"eval_samples_per_second": 20.386, |
|
"eval_steps_per_second": 0.351, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.2095947834187238, |
|
"eval_accuracy": 0.7636095789509747, |
|
"eval_loss": 1.0050908327102661, |
|
"eval_runtime": 28.3321, |
|
"eval_samples_per_second": 20.507, |
|
"eval_steps_per_second": 0.353, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.2328830926874709, |
|
"grad_norm": 1.2356228828430176, |
|
"learning_rate": 4.611861512187549e-05, |
|
"loss": 1.0452, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.2328830926874709, |
|
"eval_accuracy": 0.767719824719944, |
|
"eval_loss": 0.9805149435997009, |
|
"eval_runtime": 28.5332, |
|
"eval_samples_per_second": 20.362, |
|
"eval_steps_per_second": 0.35, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.2328830926874709, |
|
"step": 1000, |
|
"total_flos": 1.3069163715939533e+18, |
|
"train_loss": 1.361302978515625, |
|
"train_runtime": 10712.6155, |
|
"train_samples_per_second": 76.947, |
|
"train_steps_per_second": 1.203 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 12882, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 200, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.3069163715939533e+18, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|