215 lines
6.0 KiB
JSON
215 lines
6.0 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 188,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 1.4603330492973328,
|
||
|
|
"epoch": 0.05319148936170213,
|
||
|
|
"grad_norm": 4.6854753494262695,
|
||
|
|
"learning_rate": 9.521276595744681e-06,
|
||
|
|
"loss": 1.741653823852539,
|
||
|
|
"mean_token_accuracy": 0.6400545597076416,
|
||
|
|
"num_tokens": 40889.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 1.0660340547561646,
|
||
|
|
"epoch": 0.10638297872340426,
|
||
|
|
"grad_norm": 3.8374905586242676,
|
||
|
|
"learning_rate": 8.98936170212766e-06,
|
||
|
|
"loss": 1.0968240737915038,
|
||
|
|
"mean_token_accuracy": 0.7254508972167969,
|
||
|
|
"num_tokens": 81626.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 1.0270070672035216,
|
||
|
|
"epoch": 0.1595744680851064,
|
||
|
|
"grad_norm": 3.7457542419433594,
|
||
|
|
"learning_rate": 8.457446808510638e-06,
|
||
|
|
"loss": 1.0470428466796875,
|
||
|
|
"mean_token_accuracy": 0.7316816687583924,
|
||
|
|
"num_tokens": 122202.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 1.021245890855789,
|
||
|
|
"epoch": 0.2127659574468085,
|
||
|
|
"grad_norm": 4.032021999359131,
|
||
|
|
"learning_rate": 7.925531914893617e-06,
|
||
|
|
"loss": 1.0314661979675293,
|
||
|
|
"mean_token_accuracy": 0.7340852200984955,
|
||
|
|
"num_tokens": 162462.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.9809991240501403,
|
||
|
|
"epoch": 0.26595744680851063,
|
||
|
|
"grad_norm": 4.68726921081543,
|
||
|
|
"learning_rate": 7.3936170212765965e-06,
|
||
|
|
"loss": 0.9869649887084961,
|
||
|
|
"mean_token_accuracy": 0.7414923906326294,
|
||
|
|
"num_tokens": 202934.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.9962253928184509,
|
||
|
|
"epoch": 0.3191489361702128,
|
||
|
|
"grad_norm": 7.180868148803711,
|
||
|
|
"learning_rate": 6.861702127659575e-06,
|
||
|
|
"loss": 0.9700075149536133,
|
||
|
|
"mean_token_accuracy": 0.7404910922050476,
|
||
|
|
"num_tokens": 243232.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.9725711524486542,
|
||
|
|
"epoch": 0.3723404255319149,
|
||
|
|
"grad_norm": 5.725026607513428,
|
||
|
|
"learning_rate": 6.329787234042554e-06,
|
||
|
|
"loss": 0.943790054321289,
|
||
|
|
"mean_token_accuracy": 0.7448513627052307,
|
||
|
|
"num_tokens": 283589.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.9446361184120178,
|
||
|
|
"epoch": 0.425531914893617,
|
||
|
|
"grad_norm": 3.3108112812042236,
|
||
|
|
"learning_rate": 5.7978723404255325e-06,
|
||
|
|
"loss": 0.909608268737793,
|
||
|
|
"mean_token_accuracy": 0.7471459031105041,
|
||
|
|
"num_tokens": 324131.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.89277583360672,
|
||
|
|
"epoch": 0.4787234042553192,
|
||
|
|
"grad_norm": 3.0306735038757324,
|
||
|
|
"learning_rate": 5.265957446808511e-06,
|
||
|
|
"loss": 0.893759822845459,
|
||
|
|
"mean_token_accuracy": 0.7512714087963104,
|
||
|
|
"num_tokens": 364978.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8922354459762574,
|
||
|
|
"epoch": 0.5319148936170213,
|
||
|
|
"grad_norm": 3.038768768310547,
|
||
|
|
"learning_rate": 4.73404255319149e-06,
|
||
|
|
"loss": 0.8918367385864258,
|
||
|
|
"mean_token_accuracy": 0.7505206227302551,
|
||
|
|
"num_tokens": 405852.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8864121615886689,
|
||
|
|
"epoch": 0.5851063829787234,
|
||
|
|
"grad_norm": 3.113696336746216,
|
||
|
|
"learning_rate": 4.202127659574468e-06,
|
||
|
|
"loss": 0.881045150756836,
|
||
|
|
"mean_token_accuracy": 0.7513486027717591,
|
||
|
|
"num_tokens": 446810.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8687325477600097,
|
||
|
|
"epoch": 0.6382978723404256,
|
||
|
|
"grad_norm": 2.933997392654419,
|
||
|
|
"learning_rate": 3.670212765957447e-06,
|
||
|
|
"loss": 0.8846899986267089,
|
||
|
|
"mean_token_accuracy": 0.7517411470413208,
|
||
|
|
"num_tokens": 487659.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8917729020118713,
|
||
|
|
"epoch": 0.6914893617021277,
|
||
|
|
"grad_norm": 3.022362232208252,
|
||
|
|
"learning_rate": 3.1382978723404255e-06,
|
||
|
|
"loss": 0.8868535995483399,
|
||
|
|
"mean_token_accuracy": 0.7494482934474945,
|
||
|
|
"num_tokens": 528601.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.874623042345047,
|
||
|
|
"epoch": 0.7446808510638298,
|
||
|
|
"grad_norm": 2.9119088649749756,
|
||
|
|
"learning_rate": 2.6063829787234047e-06,
|
||
|
|
"loss": 0.8700995445251465,
|
||
|
|
"mean_token_accuracy": 0.7555455088615417,
|
||
|
|
"num_tokens": 568921.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8479571878910065,
|
||
|
|
"epoch": 0.7978723404255319,
|
||
|
|
"grad_norm": 2.807938575744629,
|
||
|
|
"learning_rate": 2.074468085106383e-06,
|
||
|
|
"loss": 0.8540098190307617,
|
||
|
|
"mean_token_accuracy": 0.7577135026454925,
|
||
|
|
"num_tokens": 609706.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8550009965896607,
|
||
|
|
"epoch": 0.851063829787234,
|
||
|
|
"grad_norm": 2.8261220455169678,
|
||
|
|
"learning_rate": 1.5425531914893618e-06,
|
||
|
|
"loss": 0.8586338996887207,
|
||
|
|
"mean_token_accuracy": 0.7571197032928467,
|
||
|
|
"num_tokens": 650027.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8622809827327729,
|
||
|
|
"epoch": 0.9042553191489362,
|
||
|
|
"grad_norm": 2.9708003997802734,
|
||
|
|
"learning_rate": 1.0106382978723404e-06,
|
||
|
|
"loss": 0.8517495155334472,
|
||
|
|
"mean_token_accuracy": 0.7582991242408752,
|
||
|
|
"num_tokens": 690980.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8525941133499145,
|
||
|
|
"epoch": 0.9574468085106383,
|
||
|
|
"grad_norm": 2.8100616931915283,
|
||
|
|
"learning_rate": 4.787234042553192e-07,
|
||
|
|
"loss": 0.8452824592590332,
|
||
|
|
"mean_token_accuracy": 0.7601142942905426,
|
||
|
|
"num_tokens": 731534.0,
|
||
|
|
"step": 180
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 188,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 5548427590828032.0,
|
||
|
|
"train_batch_size": 32,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|