|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.173913043478261, |
|
"eval_steps": 500, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.17391304347826086, |
|
"grad_norm": 1.142800826395661, |
|
"learning_rate": 4.980286753286196e-06, |
|
"loss": 1.1348, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.8695652173913043, |
|
"grad_norm": 0.6947290849443474, |
|
"learning_rate": 4.522542485937369e-06, |
|
"loss": 0.6734, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 1.6956521739130435, |
|
"grad_norm": 0.23989161491744992, |
|
"learning_rate": 3.272542485937369e-06, |
|
"loss": 0.404, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 2.5217391304347827, |
|
"grad_norm": 0.06787620600314641, |
|
"learning_rate": 1.7274575140626318e-06, |
|
"loss": 0.3523, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 3.3478260869565215, |
|
"grad_norm": 0.05732556825499545, |
|
"learning_rate": 4.774575140626317e-07, |
|
"loss": 0.3453, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 4.173913043478261, |
|
"grad_norm": 0.051149405892957175, |
|
"learning_rate": 0.0, |
|
"loss": 0.3396, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 4.173913043478261, |
|
"step": 25, |
|
"total_flos": 1.4234593266971443e+17, |
|
"train_loss": 0.4413921880722046, |
|
"train_runtime": 499.0563, |
|
"train_samples_per_second": 7.364, |
|
"train_steps_per_second": 0.05 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 25, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": false, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.4234593266971443e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|