File size: 1,407 Bytes
7a0c502 | 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 63 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 20.0,
"eval_steps": 500,
"global_step": 20,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 5.0,
"grad_norm": 0.7897256016731262,
"learning_rate": 0.00019994755690455152,
"loss": 1.18,
"step": 5
},
{
"epoch": 10.0,
"grad_norm": 0.3124788701534271,
"learning_rate": 0.0001981178176898239,
"loss": 0.5251,
"step": 10
},
{
"epoch": 15.0,
"grad_norm": 0.0885872170329094,
"learning_rate": 0.00019372067050063438,
"loss": 0.3762,
"step": 15
},
{
"epoch": 20.0,
"grad_norm": 0.05624234303832054,
"learning_rate": 0.00018687117365181512,
"loss": 0.3055,
"step": 20
}
],
"logging_steps": 5,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 20,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.912612368790323e+17,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|