|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.017292660994673862, |
|
"eval_steps": 100, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.001729266099467386, |
|
"eval_accuracy": 0.5147599845329504, |
|
"eval_loss": 2.3851237297058105, |
|
"eval_runtime": 162.2957, |
|
"eval_samples_per_second": 21.855, |
|
"eval_steps_per_second": 0.086, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.003458532198934772, |
|
"eval_accuracy": 0.664822956946066, |
|
"eval_loss": 1.5685330629348755, |
|
"eval_runtime": 160.1519, |
|
"eval_samples_per_second": 22.148, |
|
"eval_steps_per_second": 0.087, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.005187798298402158, |
|
"eval_accuracy": 0.6968067616966134, |
|
"eval_loss": 1.3908480405807495, |
|
"eval_runtime": 160.2009, |
|
"eval_samples_per_second": 22.141, |
|
"eval_steps_per_second": 0.087, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.006917064397869544, |
|
"eval_accuracy": 0.712278134986332, |
|
"eval_loss": 1.3142558336257935, |
|
"eval_runtime": 161.1937, |
|
"eval_samples_per_second": 22.005, |
|
"eval_steps_per_second": 0.087, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.008646330497336931, |
|
"grad_norm": 1.4352248907089233, |
|
"learning_rate": 4.985589449171105e-05, |
|
"loss": 2.1403, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.008646330497336931, |
|
"eval_accuracy": 0.7214570506536847, |
|
"eval_loss": 1.2621606588363647, |
|
"eval_runtime": 160.0804, |
|
"eval_samples_per_second": 22.158, |
|
"eval_steps_per_second": 0.087, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.010375596596804317, |
|
"eval_accuracy": 0.7294319423505166, |
|
"eval_loss": 1.2215678691864014, |
|
"eval_runtime": 161.111, |
|
"eval_samples_per_second": 22.016, |
|
"eval_steps_per_second": 0.087, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.012104862696271703, |
|
"eval_accuracy": 0.734985971027901, |
|
"eval_loss": 1.1908366680145264, |
|
"eval_runtime": 160.2095, |
|
"eval_samples_per_second": 22.14, |
|
"eval_steps_per_second": 0.087, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.013834128795739089, |
|
"eval_accuracy": 0.7399843258033025, |
|
"eval_loss": 1.1652381420135498, |
|
"eval_runtime": 161.2145, |
|
"eval_samples_per_second": 22.002, |
|
"eval_steps_per_second": 0.087, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.015563394895206474, |
|
"eval_accuracy": 0.7441422484377028, |
|
"eval_loss": 1.1482852697372437, |
|
"eval_runtime": 160.0254, |
|
"eval_samples_per_second": 22.165, |
|
"eval_steps_per_second": 0.087, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.017292660994673862, |
|
"grad_norm": 1.6683523654937744, |
|
"learning_rate": 4.9711788983422105e-05, |
|
"loss": 1.1733, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.017292660994673862, |
|
"eval_accuracy": 0.7479334730370067, |
|
"eval_loss": 1.1267001628875732, |
|
"eval_runtime": 160.2361, |
|
"eval_samples_per_second": 22.136, |
|
"eval_steps_per_second": 0.087, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.017292660994673862, |
|
"step": 1000, |
|
"total_flos": 1.3159164755627213e+18, |
|
"train_loss": 1.6568055419921874, |
|
"train_runtime": 12202.9628, |
|
"train_samples_per_second": 909.858, |
|
"train_steps_per_second": 14.217 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 173484, |
|
"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": 1.3159164755627213e+18, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|