182 lines
4.7 KiB
JSON
182 lines
4.7 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 1076,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.04650622020695268,
|
||
|
|
"grad_norm": 0.14487601816654205,
|
||
|
|
"learning_rate": 4.9000000000000005e-05,
|
||
|
|
"loss": 9.355223999023437,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.09301244041390536,
|
||
|
|
"grad_norm": 0.07256779819726944,
|
||
|
|
"learning_rate": 9.900000000000001e-05,
|
||
|
|
"loss": 8.395075073242188,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.13951866062085805,
|
||
|
|
"grad_norm": 0.08071431517601013,
|
||
|
|
"learning_rate": 0.000149,
|
||
|
|
"loss": 7.945545043945312,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1860248808278107,
|
||
|
|
"grad_norm": 0.11445911228656769,
|
||
|
|
"learning_rate": 0.000199,
|
||
|
|
"loss": 7.699019775390625,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2325311010347634,
|
||
|
|
"grad_norm": 0.10978443920612335,
|
||
|
|
"learning_rate": 0.000249,
|
||
|
|
"loss": 7.29552734375,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2790373212417161,
|
||
|
|
"grad_norm": 0.11569751799106598,
|
||
|
|
"learning_rate": 0.000299,
|
||
|
|
"loss": 6.84951416015625,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.32554354144866876,
|
||
|
|
"grad_norm": 0.11708350479602814,
|
||
|
|
"learning_rate": 0.00034899999999999997,
|
||
|
|
"loss": 6.479200439453125,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3720497616556214,
|
||
|
|
"grad_norm": 0.10155152529478073,
|
||
|
|
"learning_rate": 0.00039900000000000005,
|
||
|
|
"loss": 6.209773559570312,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.41855598186257414,
|
||
|
|
"grad_norm": 0.11156516522169113,
|
||
|
|
"learning_rate": 0.000449,
|
||
|
|
"loss": 5.98971923828125,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4650622020695268,
|
||
|
|
"grad_norm": 0.10470128804445267,
|
||
|
|
"learning_rate": 0.000499,
|
||
|
|
"loss": 5.820839233398438,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5115684222764795,
|
||
|
|
"grad_norm": 0.0922137200832367,
|
||
|
|
"learning_rate": 0.0004911249568335938,
|
||
|
|
"loss": 5.658131103515625,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5580746424834322,
|
||
|
|
"grad_norm": 0.09017608314752579,
|
||
|
|
"learning_rate": 0.00046443215250006805,
|
||
|
|
"loss": 5.505938720703125,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6045808626903848,
|
||
|
|
"grad_norm": 0.10910492390394211,
|
||
|
|
"learning_rate": 0.00042189072640434186,
|
||
|
|
"loss": 5.364219970703125,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6510870828973375,
|
||
|
|
"grad_norm": 0.0955413430929184,
|
||
|
|
"learning_rate": 0.000366644903717664,
|
||
|
|
"loss": 5.2475146484375,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6975933031042902,
|
||
|
|
"grad_norm": 0.07590549439191818,
|
||
|
|
"learning_rate": 0.0003027778880897413,
|
||
|
|
"loss": 5.147374267578125,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7440995233112428,
|
||
|
|
"grad_norm": 0.07280214875936508,
|
||
|
|
"learning_rate": 0.00023501007318339978,
|
||
|
|
"loss": 5.035035705566406,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7906057435181956,
|
||
|
|
"grad_norm": 0.07863806188106537,
|
||
|
|
"learning_rate": 0.0001683501596695945,
|
||
|
|
"loss": 4.933069152832031,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8371119637251483,
|
||
|
|
"grad_norm": 0.08269604295492172,
|
||
|
|
"learning_rate": 0.00010772496353027538,
|
||
|
|
"loss": 4.838182983398437,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8836181839321009,
|
||
|
|
"grad_norm": 0.0789259672164917,
|
||
|
|
"learning_rate": 5.761527643622996e-05,
|
||
|
|
"loss": 4.838483276367188,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9301244041390536,
|
||
|
|
"grad_norm": 0.07977437973022461,
|
||
|
|
"learning_rate": 2.172469165981239e-05,
|
||
|
|
"loss": 4.8021307373046875,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9766306243460062,
|
||
|
|
"grad_norm": 0.09115710109472275,
|
||
|
|
"learning_rate": 2.7058725088047465e-06,
|
||
|
|
"loss": 4.787516784667969,
|
||
|
|
"step": 1050
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 50,
|
||
|
|
"max_steps": 1076,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 107,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1.11175261869312e+16,
|
||
|
|
"train_batch_size": 8,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|