File size: 1,326 Bytes
5d1d6db |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.03577817531305903,
"eval_steps": 5,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007155635062611807,
"eval_loss": 8.003866195678711,
"eval_runtime": 21.074,
"eval_samples_per_second": 11.199,
"eval_steps_per_second": 1.424,
"step": 1
},
{
"epoch": 0.02146690518783542,
"grad_norm": 36.30503845214844,
"learning_rate": 3e-05,
"loss": 29.32,
"step": 3
},
{
"epoch": 0.03577817531305903,
"eval_loss": 6.45150899887085,
"eval_runtime": 21.281,
"eval_samples_per_second": 11.09,
"eval_steps_per_second": 1.41,
"step": 5
}
],
"logging_steps": 3,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6652543295815680.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|