|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 16.0, |
|
"eval_steps": 500, |
|
"global_step": 100, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 2.3331761360168457, |
|
"learning_rate": 4.990486745229364e-10, |
|
"loss": 7.386, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"grad_norm": 2.494887351989746, |
|
"learning_rate": 4.962019382530521e-10, |
|
"loss": 6.7817, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"grad_norm": 2.389345407485962, |
|
"learning_rate": 4.914814565722671e-10, |
|
"loss": 7.1632, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"grad_norm": 2.437628984451294, |
|
"learning_rate": 4.849231551964771e-10, |
|
"loss": 7.0109, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"grad_norm": 3.2548422813415527, |
|
"learning_rate": 4.765769467591626e-10, |
|
"loss": 7.1004, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"grad_norm": 2.268507480621338, |
|
"learning_rate": 4.665063509461097e-10, |
|
"loss": 6.9577, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 5.6, |
|
"grad_norm": 2.739196300506592, |
|
"learning_rate": 4.54788011072248e-10, |
|
"loss": 7.1725, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 6.4, |
|
"grad_norm": 2.399449348449707, |
|
"learning_rate": 4.415111107797445e-10, |
|
"loss": 7.1535, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 7.2, |
|
"grad_norm": 2.798766613006592, |
|
"learning_rate": 4.267766952966369e-10, |
|
"loss": 6.9961, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"grad_norm": 2.742884635925293, |
|
"learning_rate": 4.106969024216348e-10, |
|
"loss": 7.1581, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 8.8, |
|
"grad_norm": 3.0411534309387207, |
|
"learning_rate": 3.933941090877615e-10, |
|
"loss": 7.3208, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 9.6, |
|
"grad_norm": 2.590532064437866, |
|
"learning_rate": 3.7500000000000005e-10, |
|
"loss": 6.7152, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 10.4, |
|
"grad_norm": 2.6501505374908447, |
|
"learning_rate": 3.556545654351749e-10, |
|
"loss": 7.1168, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 11.2, |
|
"grad_norm": 2.6842129230499268, |
|
"learning_rate": 3.3550503583141725e-10, |
|
"loss": 7.143, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"grad_norm": 2.7974400520324707, |
|
"learning_rate": 3.147047612756302e-10, |
|
"loss": 7.2724, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 12.8, |
|
"grad_norm": 2.68391489982605, |
|
"learning_rate": 2.9341204441673265e-10, |
|
"loss": 6.995, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 13.6, |
|
"grad_norm": 3.0854671001434326, |
|
"learning_rate": 2.717889356869146e-10, |
|
"loss": 7.1134, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 14.4, |
|
"grad_norm": 2.772061347961426, |
|
"learning_rate": 2.5e-10, |
|
"loss": 7.2029, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 15.2, |
|
"grad_norm": 2.6627767086029053, |
|
"learning_rate": 2.2821106431308546e-10, |
|
"loss": 7.4673, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"grad_norm": 2.7043120861053467, |
|
"learning_rate": 2.0658795558326743e-10, |
|
"loss": 6.8563, |
|
"step": 100 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 180, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 30, |
|
"save_steps": 100, |
|
"total_flos": 742939194654720.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|