|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.01824817518248175, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0018248175182481751, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0018248175182481751, |
|
"eval_loss": NaN, |
|
"eval_runtime": 111.6566, |
|
"eval_samples_per_second": 4.138, |
|
"eval_steps_per_second": 1.039, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0036496350364963502, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.005474452554744526, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.005474452554744526, |
|
"eval_loss": NaN, |
|
"eval_runtime": 111.5917, |
|
"eval_samples_per_second": 4.14, |
|
"eval_steps_per_second": 1.04, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0072992700729927005, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.009124087591240875, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.010948905109489052, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00012, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.010948905109489052, |
|
"eval_loss": NaN, |
|
"eval_runtime": 111.5362, |
|
"eval_samples_per_second": 4.142, |
|
"eval_steps_per_second": 1.04, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.012773722627737226, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00014, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.014598540145985401, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00016, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.016423357664233577, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00018, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.016423357664233577, |
|
"eval_loss": NaN, |
|
"eval_runtime": 111.6503, |
|
"eval_samples_per_second": 4.138, |
|
"eval_steps_per_second": 1.039, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.01824817518248175, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.812521215950848e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|