apriandito
commited on
Commit
•
3290870
1
Parent(s):
b441de4
Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-160/config.json +38 -0
- checkpoint-160/model.safetensors +3 -0
- checkpoint-160/optimizer.pt +3 -0
- checkpoint-160/rng_state.pth +3 -0
- checkpoint-160/scheduler.pt +3 -0
- checkpoint-160/trainer_state.json +209 -0
- checkpoint-160/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/Aug03_17-14-23_r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t/events.out.tfevents.1722705264.r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t.83.0 +2 -2
- runs/Aug03_17-14-23_r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t/events.out.tfevents.1722705325.r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t.83.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: indolem/indobert-base-uncased
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.24004296958446503
|
17 |
+
|
18 |
+
f1: 0.912621359223301
|
19 |
+
|
20 |
+
precision: 0.94
|
21 |
+
|
22 |
+
recall: 0.8867924528301887
|
23 |
+
|
24 |
+
auc: 0.9688286163522013
|
25 |
+
|
26 |
+
accuracy: 0.9153605015673981
|
checkpoint-160/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_ids": 0,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "Relevan",
|
16 |
+
"1": "Tidak Relevan"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"Relevan": 0,
|
22 |
+
"Tidak Relevan": 1
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"output_past": true,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.43.1",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 31923
|
38 |
+
}
|
checkpoint-160/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8abc02f49b2c3ad504aa6e5c05cce2946596205fb5707cfafc42c90e597f5164
|
3 |
+
size 442262520
|
checkpoint-160/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e655d27ba82c3b4183c23df563d0ec4da1089694742e8775f11092ff3aa332eb
|
3 |
+
size 884646138
|
checkpoint-160/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8d340e0e0954c402b990f22cd5f9a8b683acafd696e9f7e54bba76d106ebb00
|
3 |
+
size 14244
|
checkpoint-160/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dbdadc911e25d2854a46ed369aac3da762f40ea0ab90fb2acda60d72e451a38
|
3 |
+
size 1064
|
checkpoint-160/trainer_state.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.24004296958446503,
|
3 |
+
"best_model_checkpoint": "relevancy-desk-1/checkpoint-160",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 160,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04375,
|
13 |
+
"grad_norm": 16.161113739013672,
|
14 |
+
"learning_rate": 5.208333333333334e-06,
|
15 |
+
"loss": 0.7405,
|
16 |
+
"step": 7
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0875,
|
20 |
+
"grad_norm": 18.8027400970459,
|
21 |
+
"learning_rate": 1.25e-05,
|
22 |
+
"loss": 0.7231,
|
23 |
+
"step": 14
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.13125,
|
27 |
+
"grad_norm": 7.321622848510742,
|
28 |
+
"learning_rate": 1.8750000000000002e-05,
|
29 |
+
"loss": 0.7016,
|
30 |
+
"step": 21
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.175,
|
34 |
+
"grad_norm": 16.223827362060547,
|
35 |
+
"learning_rate": 2.604166666666667e-05,
|
36 |
+
"loss": 0.6902,
|
37 |
+
"step": 28
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.21875,
|
41 |
+
"grad_norm": 10.89142894744873,
|
42 |
+
"learning_rate": 3.3333333333333335e-05,
|
43 |
+
"loss": 0.6941,
|
44 |
+
"step": 35
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2625,
|
48 |
+
"grad_norm": 11.153426170349121,
|
49 |
+
"learning_rate": 4.0625000000000005e-05,
|
50 |
+
"loss": 0.6313,
|
51 |
+
"step": 42
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.30625,
|
55 |
+
"grad_norm": 12.487936019897461,
|
56 |
+
"learning_rate": 4.6875e-05,
|
57 |
+
"loss": 0.5933,
|
58 |
+
"step": 49
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.35,
|
62 |
+
"grad_norm": 21.75290298461914,
|
63 |
+
"learning_rate": 4.9537037037037035e-05,
|
64 |
+
"loss": 0.5932,
|
65 |
+
"step": 56
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.39375,
|
69 |
+
"grad_norm": 57.575801849365234,
|
70 |
+
"learning_rate": 4.8726851851851855e-05,
|
71 |
+
"loss": 0.5077,
|
72 |
+
"step": 63
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4375,
|
76 |
+
"grad_norm": 23.81184196472168,
|
77 |
+
"learning_rate": 4.791666666666667e-05,
|
78 |
+
"loss": 0.4552,
|
79 |
+
"step": 70
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.48125,
|
83 |
+
"grad_norm": 19.651561737060547,
|
84 |
+
"learning_rate": 4.722222222222222e-05,
|
85 |
+
"loss": 0.8497,
|
86 |
+
"step": 77
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.525,
|
90 |
+
"grad_norm": 45.1554069519043,
|
91 |
+
"learning_rate": 4.6412037037037034e-05,
|
92 |
+
"loss": 0.5609,
|
93 |
+
"step": 84
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.56875,
|
97 |
+
"grad_norm": 124.0260009765625,
|
98 |
+
"learning_rate": 4.5601851851851854e-05,
|
99 |
+
"loss": 0.4622,
|
100 |
+
"step": 91
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6125,
|
104 |
+
"grad_norm": 8.57412338256836,
|
105 |
+
"learning_rate": 4.4791666666666673e-05,
|
106 |
+
"loss": 0.3109,
|
107 |
+
"step": 98
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.65625,
|
111 |
+
"grad_norm": 7.455972194671631,
|
112 |
+
"learning_rate": 4.3981481481481486e-05,
|
113 |
+
"loss": 0.3433,
|
114 |
+
"step": 105
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7,
|
118 |
+
"grad_norm": 23.886850357055664,
|
119 |
+
"learning_rate": 4.31712962962963e-05,
|
120 |
+
"loss": 0.3481,
|
121 |
+
"step": 112
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.74375,
|
125 |
+
"grad_norm": 15.515789985656738,
|
126 |
+
"learning_rate": 4.236111111111111e-05,
|
127 |
+
"loss": 0.333,
|
128 |
+
"step": 119
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7875,
|
132 |
+
"grad_norm": 20.180509567260742,
|
133 |
+
"learning_rate": 4.1550925925925925e-05,
|
134 |
+
"loss": 0.3546,
|
135 |
+
"step": 126
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.83125,
|
139 |
+
"grad_norm": 39.38922882080078,
|
140 |
+
"learning_rate": 4.074074074074074e-05,
|
141 |
+
"loss": 0.1842,
|
142 |
+
"step": 133
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.875,
|
146 |
+
"grad_norm": 50.90278244018555,
|
147 |
+
"learning_rate": 3.993055555555556e-05,
|
148 |
+
"loss": 0.2997,
|
149 |
+
"step": 140
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.91875,
|
153 |
+
"grad_norm": 56.43859100341797,
|
154 |
+
"learning_rate": 3.912037037037037e-05,
|
155 |
+
"loss": 0.4073,
|
156 |
+
"step": 147
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9625,
|
160 |
+
"grad_norm": 29.69350814819336,
|
161 |
+
"learning_rate": 3.831018518518519e-05,
|
162 |
+
"loss": 0.2362,
|
163 |
+
"step": 154
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.0,
|
167 |
+
"eval_accuracy": 0.9153605015673981,
|
168 |
+
"eval_auc": 0.9688286163522013,
|
169 |
+
"eval_f1": 0.912621359223301,
|
170 |
+
"eval_loss": 0.24004296958446503,
|
171 |
+
"eval_precision": 0.94,
|
172 |
+
"eval_recall": 0.8867924528301887,
|
173 |
+
"eval_runtime": 0.6665,
|
174 |
+
"eval_samples_per_second": 478.602,
|
175 |
+
"eval_steps_per_second": 30.006,
|
176 |
+
"step": 160
|
177 |
+
}
|
178 |
+
],
|
179 |
+
"logging_steps": 7,
|
180 |
+
"max_steps": 480,
|
181 |
+
"num_input_tokens_seen": 0,
|
182 |
+
"num_train_epochs": 3,
|
183 |
+
"save_steps": 500,
|
184 |
+
"stateful_callbacks": {
|
185 |
+
"EarlyStoppingCallback": {
|
186 |
+
"args": {
|
187 |
+
"early_stopping_patience": 5,
|
188 |
+
"early_stopping_threshold": 0.01
|
189 |
+
},
|
190 |
+
"attributes": {
|
191 |
+
"early_stopping_patience_counter": 0
|
192 |
+
}
|
193 |
+
},
|
194 |
+
"TrainerControl": {
|
195 |
+
"args": {
|
196 |
+
"should_epoch_stop": false,
|
197 |
+
"should_evaluate": false,
|
198 |
+
"should_log": false,
|
199 |
+
"should_save": true,
|
200 |
+
"should_training_stop": false
|
201 |
+
},
|
202 |
+
"attributes": {}
|
203 |
+
}
|
204 |
+
},
|
205 |
+
"total_flos": 83735093368320.0,
|
206 |
+
"train_batch_size": 8,
|
207 |
+
"trial_name": null,
|
208 |
+
"trial_params": null
|
209 |
+
}
|
checkpoint-160/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76d7fe33abfc87c575e8b8804cbfa3093eed22b554904c0e1695e40196f9bde5
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_ids": 0,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "Relevan",
|
16 |
+
"1": "Tidak Relevan"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"Relevan": 0,
|
22 |
+
"Tidak Relevan": 1
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"output_past": true,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.43.1",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 31923
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8abc02f49b2c3ad504aa6e5c05cce2946596205fb5707cfafc42c90e597f5164
|
3 |
+
size 442262520
|
runs/Aug03_17-14-23_r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t/events.out.tfevents.1722705264.r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t.83.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17aa6ef2c9bfa0482657ae3403e7e48e311fa98fc75bb2640eeb29d1c334b27b
|
3 |
+
size 21303
|
runs/Aug03_17-14-23_r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t/events.out.tfevents.1722705325.r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t.83.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0357834158d2b66b7cc15c4b697ed0bb4a855923fce6aa799df79dcef2c3520
|
3 |
+
size 607
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[MASK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[SEP]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76d7fe33abfc87c575e8b8804cbfa3093eed22b554904c0e1695e40196f9bde5
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "relevancy-desk-1/autotrain-data",
|
3 |
+
"model": "indolem/indobert-base-uncased",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "relevancy-desk-1",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "apriandito",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|