|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 238, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 8.333333333333333e-07, |
|
"loss": 4.1909, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.166666666666667e-06, |
|
"loss": 3.6566, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 8.333333333333334e-06, |
|
"loss": 2.263, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.25e-05, |
|
"loss": 1.5891, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 1.279, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.9998922457512608e-05, |
|
"loss": 1.1573, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.996123284790336e-05, |
|
"loss": 1.0848, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.9869898108633834e-05, |
|
"loss": 1.039, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.972541011294959e-05, |
|
"loss": 1.0085, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.952854698514318e-05, |
|
"loss": 0.9853, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.9280368910050943e-05, |
|
"loss": 0.97, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.898221242354353e-05, |
|
"loss": 0.9575, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.8635683214758213e-05, |
|
"loss": 0.9491, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.8242647478835717e-05, |
|
"loss": 0.9285, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.780522186673046e-05, |
|
"loss": 0.9286, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.7325762086218415e-05, |
|
"loss": 0.9181, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.680685021549063e-05, |
|
"loss": 0.9192, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.6251280797653606e-05, |
|
"loss": 0.9165, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.566204579102317e-05, |
|
"loss": 0.9042, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.5042318456260305e-05, |
|
"loss": 0.9056, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.4395436267123017e-05, |
|
"loss": 0.901, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.3724882936866596e-05, |
|
"loss": 0.895, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.3034269657086993e-05, |
|
"loss": 0.8956, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.2327315650043605e-05, |
|
"loss": 0.8878, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.1607828139194683e-05, |
|
"loss": 0.8908, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.0879681845811964e-05, |
|
"loss": 0.8854, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.0146798122093167e-05, |
|
"loss": 0.8826, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 9.41312383314878e-06, |
|
"loss": 0.8782, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 8.682610101591813e-06, |
|
"loss": 0.8836, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 7.95919102919926e-06, |
|
"loss": 0.8751, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 7.246762510237404e-06, |
|
"loss": 0.8808, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 6.549161250549474e-06, |
|
"loss": 0.8793, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 5.8701441053961185e-06, |
|
"loss": 0.8729, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 5.213367847322408e-06, |
|
"loss": 0.8726, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.58236947300939e-06, |
|
"loss": 0.8675, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 3.980547155165429e-06, |
|
"loss": 0.8663, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 3.4111419420388904e-06, |
|
"loss": 0.8727, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 2.877220303107373e-06, |
|
"loss": 0.8727, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 2.381657614941858e-06, |
|
"loss": 0.8613, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.927122676180756e-06, |
|
"loss": 0.8697, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.516063335006851e-06, |
|
"loss": 0.8652, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.1506933065287062e-06, |
|
"loss": 0.8623, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 8.329802510601559e-07, |
|
"loss": 0.8606, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 5.646351775009617e-07, |
|
"loss": 0.8685, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 3.471032288855869e-07, |
|
"loss": 0.8676, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.8155589972348453e-07, |
|
"loss": 0.8646, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 6.888472704359661e-08, |
|
"loss": 0.8628, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 9.696489119221942e-09, |
|
"loss": 0.8632, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.8563192486763, |
|
"eval_runtime": 482.3257, |
|
"eval_samples_per_second": 7.267, |
|
"eval_steps_per_second": 0.228, |
|
"step": 238 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 238, |
|
"total_flos": 397821345792000.0, |
|
"train_loss": 0.5069183211366669, |
|
"train_runtime": 9492.9381, |
|
"train_samples_per_second": 3.208, |
|
"train_steps_per_second": 0.025 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 238, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 397821345792000.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|