175 lines
4.0 KiB
JSON
175 lines
4.0 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.27968,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 2000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.064,
|
||
|
|
"grad_norm": 1.6644006967544556,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.552529907226562,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.128,
|
||
|
|
"grad_norm": 0.862553060054779,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.434567260742187,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.192,
|
||
|
|
"grad_norm": 0.9680566191673279,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 6.307720336914063,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.256,
|
||
|
|
"grad_norm": 1.0872560739517212,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 5.781602783203125,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.32,
|
||
|
|
"grad_norm": 0.8385273814201355,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 5.45978759765625,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.384,
|
||
|
|
"grad_norm": 0.9646134972572327,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 5.19693115234375,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.448,
|
||
|
|
"grad_norm": 0.9179049730300903,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 4.9500119018554685,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.512,
|
||
|
|
"grad_norm": 0.8189147710800171,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 4.757677612304687,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.576,
|
||
|
|
"grad_norm": 0.7599812746047974,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 4.617741394042969,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.64,
|
||
|
|
"grad_norm": 0.8522061109542847,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 4.509363403320313,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.704,
|
||
|
|
"grad_norm": 0.7664839029312134,
|
||
|
|
"learning_rate": 0.00048800565673641917,
|
||
|
|
"loss": 4.377576293945313,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.768,
|
||
|
|
"grad_norm": 0.7524094581604004,
|
||
|
|
"learning_rate": 0.00045271489520809337,
|
||
|
|
"loss": 4.273638916015625,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.832,
|
||
|
|
"grad_norm": 0.7883505821228027,
|
||
|
|
"learning_rate": 0.00039758098733907364,
|
||
|
|
"loss": 4.2021722412109375,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.896,
|
||
|
|
"grad_norm": 0.7538483142852783,
|
||
|
|
"learning_rate": 0.0003280008241721038,
|
||
|
|
"loss": 4.124585266113281,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.96,
|
||
|
|
"grad_norm": 0.7969692945480347,
|
||
|
|
"learning_rate": 0.0002507853968714699,
|
||
|
|
"loss": 4.049356994628906,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.02368,
|
||
|
|
"grad_norm": 0.7776799201965332,
|
||
|
|
"learning_rate": 0.00017349308945287484,
|
||
|
|
"loss": 3.9465155029296874,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.08768,
|
||
|
|
"grad_norm": 0.7725834846496582,
|
||
|
|
"learning_rate": 0.00010368981149362256,
|
||
|
|
"loss": 3.853138427734375,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.15168,
|
||
|
|
"grad_norm": 0.7704042792320251,
|
||
|
|
"learning_rate": 4.820839418839992e-05,
|
||
|
|
"loss": 3.818090515136719,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.21568,
|
||
|
|
"grad_norm": 0.7322491407394409,
|
||
|
|
"learning_rate": 1.2479745224807049e-05,
|
||
|
|
"loss": 3.7908795166015623,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.27968,
|
||
|
|
"grad_norm": 0.7623891830444336,
|
||
|
|
"learning_rate": 1.2336995354467196e-09,
|
||
|
|
"loss": 3.7930838012695314,
|
||
|
|
"step": 2000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 100,
|
||
|
|
"max_steps": 2000,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 2,
|
||
|
|
"save_steps": 200,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 8542818637185024.0,
|
||
|
|
"train_batch_size": 4,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|