|
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.365930599369085,
|
|
"eval_steps": 500,
|
|
"global_step": 1500,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.07886435331230283,
|
|
"grad_norm": 0.04835394397377968,
|
|
"learning_rate": 0.0002,
|
|
"loss": 0.66,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.15772870662460567,
|
|
"grad_norm": 0.0558183453977108,
|
|
"learning_rate": 0.0001996405260481014,
|
|
"loss": 0.4766,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.23659305993690852,
|
|
"grad_norm": 0.049051981419324875,
|
|
"learning_rate": 0.00019856468862284752,
|
|
"loss": 0.4494,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.31545741324921134,
|
|
"grad_norm": 0.05015840008854866,
|
|
"learning_rate": 0.00019678022243485544,
|
|
"loss": 0.4443,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.3943217665615142,
|
|
"grad_norm": 0.04640612378716469,
|
|
"learning_rate": 0.0001942999568663777,
|
|
"loss": 0.4342,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.47318611987381703,
|
|
"grad_norm": 0.046447452157735825,
|
|
"learning_rate": 0.00019114172373472754,
|
|
"loss": 0.4287,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.5520504731861199,
|
|
"grad_norm": 0.0452335923910141,
|
|
"learning_rate": 0.0001873282290908019,
|
|
"loss": 0.4267,
|
|
"step": 350
|
|
},
|
|
{
|
|
"epoch": 0.6309148264984227,
|
|
"grad_norm": 0.046432506293058395,
|
|
"learning_rate": 0.00018288688997440474,
|
|
"loss": 0.4235,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.7097791798107256,
|
|
"grad_norm": 0.5536419749259949,
|
|
"learning_rate": 0.00017784963730001395,
|
|
"loss": 0.4187,
|
|
"step": 450
|
|
},
|
|
{
|
|
"epoch": 0.7886435331230284,
|
|
"grad_norm": 0.05094370245933533,
|
|
"learning_rate": 0.00017225268629014097,
|
|
"loss": 0.4134,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.8675078864353313,
|
|
"grad_norm": 0.04656651243567467,
|
|
"learning_rate": 0.0001661362761067479,
|
|
"loss": 0.4123,
|
|
"step": 550
|
|
},
|
|
{
|
|
"epoch": 0.9463722397476341,
|
|
"grad_norm": 0.05060403794050217,
|
|
"learning_rate": 0.0001595443805526358,
|
|
"loss": 0.4106,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 1.025236593059937,
|
|
"grad_norm": 0.04831027239561081,
|
|
"learning_rate": 0.00015252439192271156,
|
|
"loss": 0.4029,
|
|
"step": 650
|
|
},
|
|
{
|
|
"epoch": 1.1041009463722398,
|
|
"grad_norm": 0.04964866116642952,
|
|
"learning_rate": 0.00014512678027807672,
|
|
"loss": 0.3935,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 1.1829652996845426,
|
|
"grad_norm": 0.04785332828760147,
|
|
"learning_rate": 0.00013740473059258154,
|
|
"loss": 0.3945,
|
|
"step": 750
|
|
},
|
|
{
|
|
"epoch": 1.2618296529968454,
|
|
"grad_norm": 0.04986065253615379,
|
|
"learning_rate": 0.00012941376038057,
|
|
"loss": 0.3911,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 1.3406940063091484,
|
|
"grad_norm": 0.05081675201654434,
|
|
"learning_rate": 0.00012121132055487441,
|
|
"loss": 0.3914,
|
|
"step": 850
|
|
},
|
|
{
|
|
"epoch": 1.4195583596214512,
|
|
"grad_norm": 0.04923517629504204,
|
|
"learning_rate": 0.00011285638238468185,
|
|
"loss": 0.3898,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 1.498422712933754,
|
|
"grad_norm": 0.051097236573696136,
|
|
"learning_rate": 0.0001044090135228305,
|
|
"loss": 0.3937,
|
|
"step": 950
|
|
},
|
|
{
|
|
"epoch": 1.5772870662460567,
|
|
"grad_norm": 0.04983523488044739,
|
|
"learning_rate": 9.59299461506786e-05,
|
|
"loss": 0.3867,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 1.6561514195583595,
|
|
"grad_norm": 0.050950683653354645,
|
|
"learning_rate": 8.748014034535983e-05,
|
|
"loss": 0.3868,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"epoch": 1.7350157728706623,
|
|
"grad_norm": 0.05136534571647644,
|
|
"learning_rate": 7.912034580858643e-05,
|
|
"loss": 0.3852,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"epoch": 1.8138801261829653,
|
|
"grad_norm": 0.05013886094093323,
|
|
"learning_rate": 7.091066510794224e-05,
|
|
"loss": 0.3834,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"epoch": 1.8927444794952681,
|
|
"grad_norm": 0.05132165551185608,
|
|
"learning_rate": 6.291012157073313e-05,
|
|
"loss": 0.382,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"epoch": 1.971608832807571,
|
|
"grad_norm": 0.053303513675928116,
|
|
"learning_rate": 5.517623493701213e-05,
|
|
"loss": 0.3853,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"epoch": 2.050473186119874,
|
|
"grad_norm": 0.05501561611890793,
|
|
"learning_rate": 4.776460782261445e-05,
|
|
"loss": 0.3727,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"epoch": 2.1293375394321767,
|
|
"grad_norm": 0.05665005370974541,
|
|
"learning_rate": 4.0728525965316324e-05,
|
|
"loss": 0.3693,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"epoch": 2.2082018927444795,
|
|
"grad_norm": 0.0542583093047142,
|
|
"learning_rate": 3.411857512814024e-05,
|
|
"loss": 0.3715,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"epoch": 2.2870662460567823,
|
|
"grad_norm": 0.05298887938261032,
|
|
"learning_rate": 2.79822774140721e-05,
|
|
"loss": 0.3704,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"epoch": 2.365930599369085,
|
|
"grad_norm": 0.058823250234127045,
|
|
"learning_rate": 2.2363749606897966e-05,
|
|
"loss": 0.3726,
|
|
"step": 1500
|
|
}
|
|
],
|
|
"logging_steps": 50,
|
|
"max_steps": 1902,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 4.2648056516050944e+17,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|
|
|