File size: 1,536 Bytes
82fe113 |
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 64 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3574620196604111,
"eval_steps": 200,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.17873100983020554,
"grad_norm": 0.5410762429237366,
"learning_rate": 9.999142157322298e-05,
"loss": 0.5394,
"step": 200
},
{
"epoch": 0.17873100983020554,
"eval_loss": 0.2514195740222931,
"eval_runtime": 56.7459,
"eval_samples_per_second": 3.19,
"eval_steps_per_second": 1.604,
"step": 200
},
{
"epoch": 0.3574620196604111,
"grad_norm": 0.3244825303554535,
"learning_rate": 9.95497608932715e-05,
"loss": 0.2114,
"step": 400
},
{
"epoch": 0.3574620196604111,
"eval_loss": 0.19941778481006622,
"eval_runtime": 56.7365,
"eval_samples_per_second": 3.19,
"eval_steps_per_second": 1.604,
"step": 400
}
],
"logging_steps": 200,
"max_steps": 5595,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.454947034284032e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|