|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.6297229219143576, |
|
"eval_steps": 500, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.000196, |
|
"loss": 3.0544, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000192, |
|
"loss": 2.699, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.000188, |
|
"loss": 2.5306, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00018400000000000003, |
|
"loss": 2.4369, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00018, |
|
"loss": 2.2996, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00017600000000000002, |
|
"loss": 2.361, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.000172, |
|
"loss": 2.2129, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.000168, |
|
"loss": 2.1982, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.000164, |
|
"loss": 2.1275, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00016, |
|
"loss": 2.2264, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00015600000000000002, |
|
"loss": 2.2303, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.000152, |
|
"loss": 2.1791, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.000148, |
|
"loss": 2.1766, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.000144, |
|
"loss": 2.2172, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00014, |
|
"loss": 2.2492, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00013600000000000003, |
|
"loss": 2.0608, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.000132, |
|
"loss": 2.2299, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00012800000000000002, |
|
"loss": 2.1426, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.000124, |
|
"loss": 2.1903, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00012, |
|
"loss": 2.1713, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.000116, |
|
"loss": 2.1318, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00011200000000000001, |
|
"loss": 2.1589, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00010800000000000001, |
|
"loss": 1.9988, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00010400000000000001, |
|
"loss": 2.2181, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0001, |
|
"loss": 2.1888, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 9.6e-05, |
|
"loss": 2.1515, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 9.200000000000001e-05, |
|
"loss": 2.1827, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 8.800000000000001e-05, |
|
"loss": 2.0528, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 8.4e-05, |
|
"loss": 2.05, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 8e-05, |
|
"loss": 2.2682, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 7.6e-05, |
|
"loss": 2.036, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 7.2e-05, |
|
"loss": 2.1001, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 6.800000000000001e-05, |
|
"loss": 2.205, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 6.400000000000001e-05, |
|
"loss": 2.1086, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 6e-05, |
|
"loss": 2.0984, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 5.6000000000000006e-05, |
|
"loss": 2.1905, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 5.2000000000000004e-05, |
|
"loss": 2.1731, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.8e-05, |
|
"loss": 2.0839, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 2.0515, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 4e-05, |
|
"loss": 2.0287, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 3.6e-05, |
|
"loss": 2.1397, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 2.006, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 2.0506, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.4e-05, |
|
"loss": 1.9864, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2e-05, |
|
"loss": 2.1728, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 2.0661, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.2e-05, |
|
"loss": 2.0826, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 2.0811, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 2.1103, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0, |
|
"loss": 2.2032, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 500, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"total_flos": 3.377311103950848e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|