|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.912621359223301, |
|
"eval_steps": 500, |
|
"global_step": 75, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.038834951456310676, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.07766990291262135, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.11650485436893204, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.1553398058252427, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.1941747572815534, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000125, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.23300970873786409, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.27184466019417475, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.000175, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.3106796116504854, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.34951456310679613, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00019701492537313434, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.3883495145631068, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00019402985074626867, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.42718446601941745, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00019104477611940298, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.46601941747572817, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00018805970149253734, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.5048543689320388, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00018507462686567165, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.5436893203883495, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00018208955223880598, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.5825242718446602, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001791044776119403, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.6213592233009708, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00017611940298507464, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.6601941747572816, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00017313432835820895, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.6990291262135923, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00017014925373134328, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.7378640776699029, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00016716417910447761, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.7766990291262136, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00016417910447761195, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.8155339805825242, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00016119402985074628, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.8543689320388349, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00015820895522388059, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.8932038834951457, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00015522388059701495, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.9320388349514563, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00015223880597014925, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.970873786407767, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001492537313432836, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.0097087378640777, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00014626865671641792, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 1.0485436893203883, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00014328358208955225, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.087378640776699, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00014029850746268658, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 1.1262135922330097, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001373134328358209, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 1.1650485436893203, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00013432835820895525, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.203883495145631, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00013134328358208955, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 1.2427184466019416, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00012835820895522389, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 1.2815533980582523, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00012537313432835822, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 1.3203883495145632, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00012238805970149255, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.3592233009708738, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00011940298507462686, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.3980582524271845, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001164179104477612, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 1.4368932038834952, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00011343283582089552, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.4757281553398058, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00011044776119402987, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.5145631067961165, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00010746268656716419, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.5533980582524272, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0001044776119402985, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.5922330097087378, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.00010149253731343284, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.6310679611650487, |
|
"grad_norm": 0.0, |
|
"learning_rate": 9.850746268656717e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.6699029126213594, |
|
"grad_norm": 0.0, |
|
"learning_rate": 9.552238805970149e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.70873786407767, |
|
"grad_norm": 0.0, |
|
"learning_rate": 9.253731343283582e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.7475728155339807, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.955223880597016e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.7864077669902914, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.656716417910447e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.825242718446602, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.358208955223881e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.8640776699029127, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.059701492537314e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.9029126213592233, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.761194029850747e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.941747572815534, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.46268656716418e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.9805825242718447, |
|
"grad_norm": 0.0, |
|
"learning_rate": 7.164179104477612e-05, |
|
"loss": 0.0, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 2.0194174757281553, |
|
"grad_norm": 0.0, |
|
"learning_rate": 6.865671641791044e-05, |
|
"loss": 0.0, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 2.058252427184466, |
|
"grad_norm": 0.0, |
|
"learning_rate": 6.567164179104478e-05, |
|
"loss": 0.0, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 2.0970873786407767, |
|
"grad_norm": 0.0, |
|
"learning_rate": 6.268656716417911e-05, |
|
"loss": 0.0, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 2.1359223300970873, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.970149253731343e-05, |
|
"loss": 0.0, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 2.174757281553398, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.671641791044776e-05, |
|
"loss": 0.0, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 2.2135922330097086, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.373134328358209e-05, |
|
"loss": 0.0, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 2.2524271844660193, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.074626865671642e-05, |
|
"loss": 0.0, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 2.29126213592233, |
|
"grad_norm": 0.0, |
|
"learning_rate": 4.7761194029850745e-05, |
|
"loss": 0.0, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 2.3300970873786406, |
|
"grad_norm": 0.0, |
|
"learning_rate": 4.477611940298508e-05, |
|
"loss": 0.0, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.3689320388349513, |
|
"grad_norm": 0.0, |
|
"learning_rate": 4.1791044776119404e-05, |
|
"loss": 0.0, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 2.407766990291262, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.8805970149253736e-05, |
|
"loss": 0.0, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 2.4466019417475726, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.582089552238806e-05, |
|
"loss": 0.0, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 2.4854368932038833, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.283582089552239e-05, |
|
"loss": 0.0, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 2.524271844660194, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.9850746268656714e-05, |
|
"loss": 0.0, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 2.5631067961165046, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.6865671641791047e-05, |
|
"loss": 0.0, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 2.6019417475728153, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.3880597014925373e-05, |
|
"loss": 0.0, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 2.6407766990291264, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.0895522388059702e-05, |
|
"loss": 0.0, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 2.679611650485437, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.791044776119403e-05, |
|
"loss": 0.0, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 2.7184466019417477, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.4925373134328357e-05, |
|
"loss": 0.0, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 2.7572815533980584, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.1940298507462686e-05, |
|
"loss": 0.0, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 2.796116504854369, |
|
"grad_norm": 0.0, |
|
"learning_rate": 8.955223880597016e-06, |
|
"loss": 0.0, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 2.8349514563106797, |
|
"grad_norm": 0.0, |
|
"learning_rate": 5.970149253731343e-06, |
|
"loss": 0.0, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 2.8737864077669903, |
|
"grad_norm": 0.0, |
|
"learning_rate": 2.9850746268656716e-06, |
|
"loss": 0.0, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 2.912621359223301, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 75 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 75, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 2033753702400.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|