Files
Photon-1.7B-Instruct-v1/checkpoint-146/trainer_state.json

133 lines
3.1 KiB
JSON
Raw Permalink Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 146,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.137221269296741,
"grad_norm": 1.8708672523498535,
"learning_rate": 1.9997408848413494e-05,
"loss": 2.1315,
"step": 10
},
{
"epoch": 0.274442538593482,
"grad_norm": 0.6868349313735962,
"learning_rate": 1.9688092181649065e-05,
"loss": 1.723,
"step": 20
},
{
"epoch": 0.411663807890223,
"grad_norm": 0.6329067349433899,
"learning_rate": 1.8878852184023754e-05,
"loss": 1.5232,
"step": 30
},
{
"epoch": 0.548885077186964,
"grad_norm": 0.5874230265617371,
"learning_rate": 1.761144712408965e-05,
"loss": 1.3021,
"step": 40
},
{
"epoch": 0.6861063464837049,
"grad_norm": 0.5230386853218079,
"learning_rate": 1.59512774281879e-05,
"loss": 1.1852,
"step": 50
},
{
"epoch": 0.823327615780446,
"grad_norm": 0.47135353088378906,
"learning_rate": 1.3984010898462417e-05,
"loss": 1.1621,
"step": 60
},
{
"epoch": 0.9605488850771869,
"grad_norm": 0.4249146580696106,
"learning_rate": 1.1811162097098559e-05,
"loss": 1.1451,
"step": 70
},
{
"epoch": 1.0960548885077186,
"grad_norm": 0.3795073926448822,
"learning_rate": 9.544854008670366e-06,
"loss": 1.0693,
"step": 80
},
{
"epoch": 1.2332761578044598,
"grad_norm": 0.5233401656150818,
"learning_rate": 7.3020322884297565e-06,
"loss": 1.1261,
"step": 90
},
{
"epoch": 1.3704974271012007,
"grad_norm": 0.45651111006736755,
"learning_rate": 5.198430651940846e-06,
"loss": 1.0958,
"step": 100
},
{
"epoch": 1.5077186963979416,
"grad_norm": 0.36210718750953674,
"learning_rate": 3.342598803025595e-06,
"loss": 1.0381,
"step": 110
},
{
"epoch": 1.6449399656946828,
"grad_norm": 0.4071405529975891,
"learning_rate": 1.8303010698955803e-06,
"loss": 1.1037,
"step": 120
},
{
"epoch": 1.7821612349914235,
"grad_norm": 0.39132291078567505,
"learning_rate": 7.395747901219474e-07,
"loss": 0.9461,
"step": 130
},
{
"epoch": 1.9193825042881647,
"grad_norm": 0.49480199813842773,
"learning_rate": 1.2670344084530384e-07,
"loss": 1.0119,
"step": 140
}
],
"logging_steps": 10,
"max_steps": 146,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 8.477135587403366e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}