File size: 2,105 Bytes
9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca 0829b32 9af20ca |
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 |
{
"best_metric": 0.8163265306122449,
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-2200",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 2200,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.91,
"learning_rate": 7.123150895957912e-06,
"loss": 2.1151,
"step": 500
},
{
"epoch": 1.0,
"eval_accuracy": 0.6326530612244898,
"eval_loss": 1.7264677286148071,
"eval_runtime": 1.125,
"eval_samples_per_second": 217.778,
"eval_steps_per_second": 14.222,
"step": 550
},
{
"epoch": 1.82,
"learning_rate": 5.540228474633931e-06,
"loss": 1.5823,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.7755102040816326,
"eval_loss": 1.2948896884918213,
"eval_runtime": 1.575,
"eval_samples_per_second": 155.555,
"eval_steps_per_second": 10.159,
"step": 1100
},
{
"epoch": 2.73,
"learning_rate": 3.9573060533099506e-06,
"loss": 1.2756,
"step": 1500
},
{
"epoch": 3.0,
"eval_accuracy": 0.8,
"eval_loss": 1.0647388696670532,
"eval_runtime": 2.6287,
"eval_samples_per_second": 93.202,
"eval_steps_per_second": 6.087,
"step": 1650
},
{
"epoch": 3.64,
"learning_rate": 2.37438363198597e-06,
"loss": 1.0916,
"step": 2000
},
{
"epoch": 4.0,
"eval_accuracy": 0.8163265306122449,
"eval_loss": 0.9502941966056824,
"eval_runtime": 1.215,
"eval_samples_per_second": 201.646,
"eval_steps_per_second": 13.169,
"step": 2200
}
],
"logging_steps": 500,
"max_steps": 2750,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 3864466200000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"learning_rate": 8.706073317281892e-06,
"num_train_epochs": 5,
"per_device_train_batch_size": 4,
"seed": 1
}
}
|