File size: 2,082 Bytes
9eb10cb | 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 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | {
"best_metric": 0.020941253751516342,
"best_model_checkpoint": "/content/donut_finetuned/checkpoint-25",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 9.464871406555176,
"eval_runtime": 4.0077,
"eval_samples_per_second": 3.743,
"eval_steps_per_second": 1.996,
"step": 5
},
{
"epoch": 2.0,
"grad_norm": 46.585044860839844,
"learning_rate": 2.4e-05,
"loss": 10.4972,
"step": 10
},
{
"epoch": 2.0,
"eval_loss": 6.029897689819336,
"eval_runtime": 3.4276,
"eval_samples_per_second": 4.376,
"eval_steps_per_second": 2.334,
"step": 10
},
{
"epoch": 3.0,
"eval_loss": 2.0910725593566895,
"eval_runtime": 3.4674,
"eval_samples_per_second": 4.326,
"eval_steps_per_second": 2.307,
"step": 15
},
{
"epoch": 4.0,
"grad_norm": 11.026430130004883,
"learning_rate": 2.9418925439074784e-05,
"loss": 3.1451,
"step": 20
},
{
"epoch": 4.0,
"eval_loss": 0.37007761001586914,
"eval_runtime": 4.5507,
"eval_samples_per_second": 3.296,
"eval_steps_per_second": 1.758,
"step": 20
},
{
"epoch": 5.0,
"eval_loss": 0.020941253751516342,
"eval_runtime": 3.4626,
"eval_samples_per_second": 4.332,
"eval_steps_per_second": 2.31,
"step": 25
}
],
"logging_steps": 10,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.25076466040832e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|