|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.898876404494382, |
|
"eval_steps": 500, |
|
"global_step": 20, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0449438202247191, |
|
"grad_norm": 0.15547114610671997, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 0.9596, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0898876404494382, |
|
"grad_norm": 0.13959258794784546, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.9643, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.1348314606741573, |
|
"grad_norm": 0.14470240473747253, |
|
"learning_rate": 3e-06, |
|
"loss": 1.1562, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.1797752808988764, |
|
"grad_norm": 0.16597306728363037, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 1.1067, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.2247191011235955, |
|
"grad_norm": 0.14703088998794556, |
|
"learning_rate": 5e-06, |
|
"loss": 0.9694, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.2696629213483146, |
|
"grad_norm": 0.15088129043579102, |
|
"learning_rate": 6e-06, |
|
"loss": 1.0045, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.3146067415730337, |
|
"grad_norm": 0.16761414706707, |
|
"learning_rate": 7e-06, |
|
"loss": 0.9547, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.3595505617977528, |
|
"grad_norm": 0.14696507155895233, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 1.0284, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.4044943820224719, |
|
"grad_norm": 0.19629372656345367, |
|
"learning_rate": 9e-06, |
|
"loss": 0.9615, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.449438202247191, |
|
"grad_norm": 0.18038448691368103, |
|
"learning_rate": 1e-05, |
|
"loss": 1.0544, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.4943820224719101, |
|
"grad_norm": 0.22929255664348602, |
|
"learning_rate": 9.992134075089085e-06, |
|
"loss": 1.0329, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.5393258426966292, |
|
"grad_norm": 0.2177729308605194, |
|
"learning_rate": 9.968561049466214e-06, |
|
"loss": 0.9876, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.5842696629213483, |
|
"grad_norm": 0.2739273011684418, |
|
"learning_rate": 9.92935509259118e-06, |
|
"loss": 0.9326, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.6292134831460674, |
|
"grad_norm": 0.2714334726333618, |
|
"learning_rate": 9.874639560909118e-06, |
|
"loss": 1.0127, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.6741573033707865, |
|
"grad_norm": 0.318387508392334, |
|
"learning_rate": 9.804586609725499e-06, |
|
"loss": 1.1761, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.7191011235955056, |
|
"grad_norm": 0.2760864198207855, |
|
"learning_rate": 9.719416651541839e-06, |
|
"loss": 0.9729, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.7640449438202247, |
|
"grad_norm": 0.27431851625442505, |
|
"learning_rate": 9.619397662556434e-06, |
|
"loss": 0.9192, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.8089887640449438, |
|
"grad_norm": 0.24467918276786804, |
|
"learning_rate": 9.504844339512096e-06, |
|
"loss": 0.8674, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.8539325842696629, |
|
"grad_norm": 0.25415292382240295, |
|
"learning_rate": 9.376117109543769e-06, |
|
"loss": 0.9619, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.898876404494382, |
|
"grad_norm": 0.26627272367477417, |
|
"learning_rate": 9.233620996141421e-06, |
|
"loss": 0.8804, |
|
"step": 20 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 66, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 5, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.6786640876234342e+18, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|