|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.0, |
|
"eval_steps": 500, |
|
"global_step": 72, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000125, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000175, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000196875, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00019375000000000002, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000190625, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001875, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000184375, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00018125000000000001, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000178125, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000175, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00017187500000000002, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00016875, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000165625, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00016250000000000002, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000159375, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00015625, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000153125, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000146875, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00014375, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00014062500000000002, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001375, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000134375, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00013125000000000002, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000128125, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000125, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00012187500000000001, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00011875, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000115625, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00011250000000000001, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000109375, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00010625000000000001, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000103125, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"grad_norm": 0.0, |
|
"learning_rate": 9.687500000000001e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"grad_norm": 0.0, |
|
"learning_rate": 9.375e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"grad_norm": 0.0, |
|
"learning_rate": 9.062500000000001e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.75e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.4375e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.125000000000001e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.8125e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.1875e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"grad_norm": 0.0, |
|
"learning_rate": 6.875e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"grad_norm": 0.0, |
|
"learning_rate": 6.562500000000001e-05, |
|
"loss": 0.0, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"grad_norm": 0.0, |
|
"learning_rate": 6.25e-05, |
|
"loss": 0.0, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.9375e-05, |
|
"loss": 0.0, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.6250000000000005e-05, |
|
"loss": 0.0, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.3125000000000004e-05, |
|
"loss": 0.0, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"grad_norm": 0.0, |
|
"learning_rate": 4.6875e-05, |
|
"loss": 0.0, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"grad_norm": 0.0, |
|
"learning_rate": 4.375e-05, |
|
"loss": 0.0, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"grad_norm": 0.0, |
|
"learning_rate": 4.0625000000000005e-05, |
|
"loss": 0.0, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 0.0, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.4375e-05, |
|
"loss": 0.0, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.125e-05, |
|
"loss": 0.0, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.8125000000000003e-05, |
|
"loss": 0.0, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.0, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.1875e-05, |
|
"loss": 0.0, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.8750000000000002e-05, |
|
"loss": 0.0, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.5625e-05, |
|
"loss": 0.0, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.25e-05, |
|
"loss": 0.0, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"grad_norm": 0.0, |
|
"learning_rate": 9.375000000000001e-06, |
|
"loss": 0.0, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"grad_norm": 0.0, |
|
"learning_rate": 6.25e-06, |
|
"loss": 0.0, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.125e-06, |
|
"loss": 0.0, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 72 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 72, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 500, |
|
"total_flos": 1791530237952.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|