File size: 1,437 Bytes
4265a6a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 401,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.24937655860349128,
"grad_norm": 0.9138969779014587,
"learning_rate": 0.00015012468827930176,
"loss": 1.6682,
"step": 100
},
{
"epoch": 0.49875311720698257,
"grad_norm": 0.9227935075759888,
"learning_rate": 0.0001002493765586035,
"loss": 1.4274,
"step": 200
},
{
"epoch": 0.7481296758104738,
"grad_norm": 0.9506911039352417,
"learning_rate": 5.037406483790524e-05,
"loss": 1.4323,
"step": 300
},
{
"epoch": 0.9975062344139651,
"grad_norm": 0.7986575961112976,
"learning_rate": 4.987531172069825e-07,
"loss": 1.3683,
"step": 400
}
],
"logging_steps": 100,
"max_steps": 401,
"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": 3402058752614400.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|