Commit
·
f169e4a
1
Parent(s):
76bc7aa
Upload 11 files
Browse files- config.json +44 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +337 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "indolem/indobertweet-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_ids": 0,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Bintang 1",
|
| 16 |
+
"1": "Bintang 2",
|
| 17 |
+
"2": "Bintang 3",
|
| 18 |
+
"3": "Bintang 4",
|
| 19 |
+
"4": "Bintang 5"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"Bintang 1": 0,
|
| 25 |
+
"Bintang 2": 1,
|
| 26 |
+
"Bintang 3": 2,
|
| 27 |
+
"Bintang 4": 3,
|
| 28 |
+
"Bintang 5": 4
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"max_position_embeddings": 512,
|
| 32 |
+
"model_type": "bert",
|
| 33 |
+
"num_attention_heads": 12,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"output_past": true,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "multi_label_classification",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.32.0",
|
| 41 |
+
"type_vocab_size": 2,
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 31923
|
| 44 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715908a4b9ff716429fa0576972c829fc810817c0f9e0f5d424e961c59a5c115
|
| 3 |
+
size 884664069
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd5894498fb85c08107b7978fd7b58d109ef92dcc76d7b0b390bfe479726123d
|
| 3 |
+
size 442316593
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f4ff69ce3a867fc6c92d51f98704f57a1baefeadbf478fa8dc3e04a96a1937f
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0c7d3ee4508404640122d0b540ef9f7b79c50f752e4177f6a40eaa4ce2e4108
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.49511729307051994,
|
| 3 |
+
"best_model_checkpoint": "./indobertweet-review-rating/checkpoint-14300",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 21450,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14,
|
| 13 |
+
"learning_rate": 1.9813519813519816e-05,
|
| 14 |
+
"loss": 0.4207,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.28,
|
| 19 |
+
"learning_rate": 1.962703962703963e-05,
|
| 20 |
+
"loss": 0.3879,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.42,
|
| 25 |
+
"learning_rate": 1.944055944055944e-05,
|
| 26 |
+
"loss": 0.3832,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.56,
|
| 31 |
+
"learning_rate": 1.9254079254079257e-05,
|
| 32 |
+
"loss": 0.3796,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.7,
|
| 37 |
+
"learning_rate": 1.906759906759907e-05,
|
| 38 |
+
"loss": 0.3764,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.84,
|
| 43 |
+
"learning_rate": 1.888111888111888e-05,
|
| 44 |
+
"loss": 0.3732,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.98,
|
| 49 |
+
"learning_rate": 1.8694638694638696e-05,
|
| 50 |
+
"loss": 0.3715,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"eval_akurasi": 0.304635761589404,
|
| 56 |
+
"eval_f1": 0.41270686365854736,
|
| 57 |
+
"eval_loss": 0.36894935369491577,
|
| 58 |
+
"eval_roc_auc": 0.6308684676414661,
|
| 59 |
+
"eval_runtime": 132.2279,
|
| 60 |
+
"eval_samples_per_second": 115.339,
|
| 61 |
+
"eval_steps_per_second": 7.215,
|
| 62 |
+
"step": 3575
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.12,
|
| 66 |
+
"learning_rate": 1.850815850815851e-05,
|
| 67 |
+
"loss": 0.3592,
|
| 68 |
+
"step": 4000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.26,
|
| 72 |
+
"learning_rate": 1.8321678321678323e-05,
|
| 73 |
+
"loss": 0.3515,
|
| 74 |
+
"step": 4500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.4,
|
| 78 |
+
"learning_rate": 1.8135198135198137e-05,
|
| 79 |
+
"loss": 0.3529,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.54,
|
| 84 |
+
"learning_rate": 1.794871794871795e-05,
|
| 85 |
+
"loss": 0.3497,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.68,
|
| 90 |
+
"learning_rate": 1.7762237762237765e-05,
|
| 91 |
+
"loss": 0.3489,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.82,
|
| 96 |
+
"learning_rate": 1.7575757575757576e-05,
|
| 97 |
+
"loss": 0.3511,
|
| 98 |
+
"step": 6500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.96,
|
| 102 |
+
"learning_rate": 1.738927738927739e-05,
|
| 103 |
+
"loss": 0.3494,
|
| 104 |
+
"step": 7000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.0,
|
| 108 |
+
"eval_akurasi": 0.36633663366336633,
|
| 109 |
+
"eval_f1": 0.4571545380212592,
|
| 110 |
+
"eval_loss": 0.36878135800361633,
|
| 111 |
+
"eval_roc_auc": 0.653645662579503,
|
| 112 |
+
"eval_runtime": 132.2013,
|
| 113 |
+
"eval_samples_per_second": 115.362,
|
| 114 |
+
"eval_steps_per_second": 7.216,
|
| 115 |
+
"step": 7150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 2.1,
|
| 119 |
+
"learning_rate": 1.7202797202797203e-05,
|
| 120 |
+
"loss": 0.327,
|
| 121 |
+
"step": 7500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.24,
|
| 125 |
+
"learning_rate": 1.7016317016317017e-05,
|
| 126 |
+
"loss": 0.3207,
|
| 127 |
+
"step": 8000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.38,
|
| 131 |
+
"learning_rate": 1.682983682983683e-05,
|
| 132 |
+
"loss": 0.3178,
|
| 133 |
+
"step": 8500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.52,
|
| 137 |
+
"learning_rate": 1.6643356643356645e-05,
|
| 138 |
+
"loss": 0.3141,
|
| 139 |
+
"step": 9000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.66,
|
| 143 |
+
"learning_rate": 1.645687645687646e-05,
|
| 144 |
+
"loss": 0.3183,
|
| 145 |
+
"step": 9500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.8,
|
| 149 |
+
"learning_rate": 1.6270396270396273e-05,
|
| 150 |
+
"loss": 0.3226,
|
| 151 |
+
"step": 10000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.94,
|
| 155 |
+
"learning_rate": 1.6083916083916083e-05,
|
| 156 |
+
"loss": 0.322,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 3.0,
|
| 161 |
+
"eval_akurasi": 0.4225296701855616,
|
| 162 |
+
"eval_f1": 0.4886535552193646,
|
| 163 |
+
"eval_loss": 0.3799174726009369,
|
| 164 |
+
"eval_roc_auc": 0.6730296374008262,
|
| 165 |
+
"eval_runtime": 132.2733,
|
| 166 |
+
"eval_samples_per_second": 115.299,
|
| 167 |
+
"eval_steps_per_second": 7.212,
|
| 168 |
+
"step": 10725
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.08,
|
| 172 |
+
"learning_rate": 1.5897435897435897e-05,
|
| 173 |
+
"loss": 0.2957,
|
| 174 |
+
"step": 11000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.22,
|
| 178 |
+
"learning_rate": 1.5710955710955715e-05,
|
| 179 |
+
"loss": 0.2751,
|
| 180 |
+
"step": 11500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.36,
|
| 184 |
+
"learning_rate": 1.5524475524475525e-05,
|
| 185 |
+
"loss": 0.2724,
|
| 186 |
+
"step": 12000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 3.5,
|
| 190 |
+
"learning_rate": 1.533799533799534e-05,
|
| 191 |
+
"loss": 0.2827,
|
| 192 |
+
"step": 12500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.64,
|
| 196 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 197 |
+
"loss": 0.2846,
|
| 198 |
+
"step": 13000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.78,
|
| 202 |
+
"learning_rate": 1.4965034965034965e-05,
|
| 203 |
+
"loss": 0.2826,
|
| 204 |
+
"step": 13500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.92,
|
| 208 |
+
"learning_rate": 1.4778554778554779e-05,
|
| 209 |
+
"loss": 0.2863,
|
| 210 |
+
"step": 14000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 4.0,
|
| 214 |
+
"eval_akurasi": 0.448101763818766,
|
| 215 |
+
"eval_f1": 0.49511729307051994,
|
| 216 |
+
"eval_loss": 0.412160724401474,
|
| 217 |
+
"eval_roc_auc": 0.6790866172709985,
|
| 218 |
+
"eval_runtime": 132.2949,
|
| 219 |
+
"eval_samples_per_second": 115.28,
|
| 220 |
+
"eval_steps_per_second": 7.211,
|
| 221 |
+
"step": 14300
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.06,
|
| 225 |
+
"learning_rate": 1.4592074592074595e-05,
|
| 226 |
+
"loss": 0.2652,
|
| 227 |
+
"step": 14500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.2,
|
| 231 |
+
"learning_rate": 1.4405594405594407e-05,
|
| 232 |
+
"loss": 0.2333,
|
| 233 |
+
"step": 15000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 4.34,
|
| 237 |
+
"learning_rate": 1.421911421911422e-05,
|
| 238 |
+
"loss": 0.2457,
|
| 239 |
+
"step": 15500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 4.48,
|
| 243 |
+
"learning_rate": 1.4032634032634035e-05,
|
| 244 |
+
"loss": 0.244,
|
| 245 |
+
"step": 16000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 4.62,
|
| 249 |
+
"learning_rate": 1.3846153846153847e-05,
|
| 250 |
+
"loss": 0.2438,
|
| 251 |
+
"step": 16500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 4.76,
|
| 255 |
+
"learning_rate": 1.365967365967366e-05,
|
| 256 |
+
"loss": 0.2448,
|
| 257 |
+
"step": 17000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 4.9,
|
| 261 |
+
"learning_rate": 1.3473193473193473e-05,
|
| 262 |
+
"loss": 0.2484,
|
| 263 |
+
"step": 17500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.0,
|
| 267 |
+
"eval_akurasi": 0.45597010032129043,
|
| 268 |
+
"eval_f1": 0.48838265609168097,
|
| 269 |
+
"eval_loss": 0.4510646164417267,
|
| 270 |
+
"eval_roc_auc": 0.6768326667103797,
|
| 271 |
+
"eval_runtime": 132.311,
|
| 272 |
+
"eval_samples_per_second": 115.266,
|
| 273 |
+
"eval_steps_per_second": 7.21,
|
| 274 |
+
"step": 17875
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 5.03,
|
| 278 |
+
"learning_rate": 1.3286713286713288e-05,
|
| 279 |
+
"loss": 0.2364,
|
| 280 |
+
"step": 18000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.17,
|
| 284 |
+
"learning_rate": 1.3100233100233102e-05,
|
| 285 |
+
"loss": 0.2016,
|
| 286 |
+
"step": 18500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 5.31,
|
| 290 |
+
"learning_rate": 1.2913752913752915e-05,
|
| 291 |
+
"loss": 0.2034,
|
| 292 |
+
"step": 19000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 5.45,
|
| 296 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 297 |
+
"loss": 0.2131,
|
| 298 |
+
"step": 19500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 5.59,
|
| 302 |
+
"learning_rate": 1.254079254079254e-05,
|
| 303 |
+
"loss": 0.2076,
|
| 304 |
+
"step": 20000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 5.73,
|
| 308 |
+
"learning_rate": 1.2354312354312355e-05,
|
| 309 |
+
"loss": 0.2032,
|
| 310 |
+
"step": 20500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 5.87,
|
| 314 |
+
"learning_rate": 1.216783216783217e-05,
|
| 315 |
+
"loss": 0.2134,
|
| 316 |
+
"step": 21000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.0,
|
| 320 |
+
"eval_akurasi": 0.462986033702708,
|
| 321 |
+
"eval_f1": 0.4940430572005852,
|
| 322 |
+
"eval_loss": 0.4969989061355591,
|
| 323 |
+
"eval_roc_auc": 0.680316044849518,
|
| 324 |
+
"eval_runtime": 132.3664,
|
| 325 |
+
"eval_samples_per_second": 115.218,
|
| 326 |
+
"eval_steps_per_second": 7.207,
|
| 327 |
+
"step": 21450
|
| 328 |
+
}
|
| 329 |
+
],
|
| 330 |
+
"logging_steps": 500,
|
| 331 |
+
"max_steps": 53625,
|
| 332 |
+
"num_train_epochs": 15,
|
| 333 |
+
"save_steps": 500,
|
| 334 |
+
"total_flos": 4.514475841140326e+16,
|
| 335 |
+
"trial_name": null,
|
| 336 |
+
"trial_params": null
|
| 337 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75cfa005ff68f329bd629346f5624f4aab8e968cc9ff3ad03c353bfa81cddb41
|
| 3 |
+
size 4091
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|