Spaces:
Sleeping
Sleeping
File size: 3,128 Bytes
7769f4e |
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 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
{
"best_metric": 0.08877604454755783,
"best_model_checkpoint": "/content/drive/MyDrive/chatbot_info/models/bert_ner/checkpoint-4796",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 4796,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2085070892410342,
"grad_norm": 1.3864336013793945,
"learning_rate": 1.8609952738393106e-05,
"loss": 0.217,
"step": 500
},
{
"epoch": 0.4170141784820684,
"grad_norm": 0.8502457737922668,
"learning_rate": 1.721990547678621e-05,
"loss": 0.1147,
"step": 1000
},
{
"epoch": 0.6255212677231026,
"grad_norm": 1.1136561632156372,
"learning_rate": 1.5829858215179316e-05,
"loss": 0.1029,
"step": 1500
},
{
"epoch": 0.8340283569641368,
"grad_norm": 0.9568729400634766,
"learning_rate": 1.4439810953572422e-05,
"loss": 0.1039,
"step": 2000
},
{
"epoch": 1.0,
"eval_accuracy": 0.9708774583963692,
"eval_f1": 0.8271461197438539,
"eval_loss": 0.09369628131389618,
"eval_precision": 0.8277762839472976,
"eval_recall": 0.8265169142652586,
"eval_runtime": 32.2988,
"eval_samples_per_second": 296.915,
"eval_steps_per_second": 18.577,
"step": 2398
},
{
"epoch": 1.042535446205171,
"grad_norm": 1.206861972808838,
"learning_rate": 1.3049763691965527e-05,
"loss": 0.093,
"step": 2500
},
{
"epoch": 1.2510425354462051,
"grad_norm": 0.7828037142753601,
"learning_rate": 1.1659716430358635e-05,
"loss": 0.0807,
"step": 3000
},
{
"epoch": 1.4595496246872393,
"grad_norm": 0.5838351845741272,
"learning_rate": 1.026966916875174e-05,
"loss": 0.0777,
"step": 3500
},
{
"epoch": 1.6680567139282736,
"grad_norm": 0.8385056853294373,
"learning_rate": 8.879621907144844e-06,
"loss": 0.0758,
"step": 4000
},
{
"epoch": 1.8765638031693077,
"grad_norm": 0.9494819045066833,
"learning_rate": 7.4895746455379494e-06,
"loss": 0.076,
"step": 4500
},
{
"epoch": 2.0,
"eval_accuracy": 0.9721030659338555,
"eval_f1": 0.83379981340797,
"eval_loss": 0.08877604454755783,
"eval_precision": 0.8278782531980591,
"eval_recall": 0.8398066941113299,
"eval_runtime": 31.2589,
"eval_samples_per_second": 306.793,
"eval_steps_per_second": 19.195,
"step": 4796
}
],
"logging_steps": 500,
"max_steps": 7194,
"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": false
},
"attributes": {}
}
},
"total_flos": 1797436693363512.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|