File size: 1,598 Bytes
2a5048b |
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 65 66 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 87,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.9,
"eval_loss": 0.2707670331001282,
"eval_runtime": 19.5658,
"eval_samples_per_second": 2.044,
"eval_steps_per_second": 0.256,
"step": 29
},
{
"epoch": 1.0344827586206897,
"grad_norm": 4.015429496765137,
"learning_rate": 3.275862068965517e-05,
"loss": 0.7211,
"step": 30
},
{
"epoch": 2.0,
"eval_accuracy": 0.9,
"eval_loss": 0.34923750162124634,
"eval_runtime": 19.9116,
"eval_samples_per_second": 2.009,
"eval_steps_per_second": 0.251,
"step": 58
},
{
"epoch": 2.0689655172413794,
"grad_norm": 0.996155321598053,
"learning_rate": 1.5517241379310346e-05,
"loss": 0.1894,
"step": 60
}
],
"logging_steps": 30,
"max_steps": 87,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 90210298484736.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|