apriandito
commited on
Commit
•
c4674f4
1
Parent(s):
23146d2
Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-72/config.json +42 -0
- checkpoint-72/model.safetensors +3 -0
- checkpoint-72/optimizer.pt +3 -0
- checkpoint-72/rng_state.pth +3 -0
- checkpoint-72/scheduler.pt +3 -0
- checkpoint-72/trainer_state.json +582 -0
- checkpoint-72/training_args.bin +3 -0
- config.json +42 -0
- model.safetensors +3 -0
- runs/Aug05_17-25-27_r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy/events.out.tfevents.1722878728.r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy.82.0 +2 -2
- runs/Aug05_17-25-27_r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy/events.out.tfevents.1722878766.r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy.82.1 +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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 1.0960981845855713
|
17 |
+
|
18 |
+
f1_macro: 0.45793362717137664
|
19 |
+
|
20 |
+
f1_micro: 0.4722222222222222
|
21 |
+
|
22 |
+
f1_weighted: 0.45793362717137676
|
23 |
+
|
24 |
+
precision_macro: 0.6229166666666666
|
25 |
+
|
26 |
+
precision_micro: 0.4722222222222222
|
27 |
+
|
28 |
+
precision_weighted: 0.6229166666666667
|
29 |
+
|
30 |
+
recall_macro: 0.47222222222222227
|
31 |
+
|
32 |
+
recall_micro: 0.4722222222222222
|
33 |
+
|
34 |
+
recall_weighted: 0.4722222222222222
|
35 |
+
|
36 |
+
accuracy: 0.4722222222222222
|
checkpoint-72/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
+
"_num_labels": 4,
|
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": "Action",
|
16 |
+
"1": "Attention",
|
17 |
+
"2": "Desire",
|
18 |
+
"3": "Interest"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Action": 0,
|
24 |
+
"Attention": 1,
|
25 |
+
"Desire": 2,
|
26 |
+
"Interest": 3
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"output_past": true,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.43.1",
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 31923
|
42 |
+
}
|
checkpoint-72/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1aa85aa535f0dd9fa7b57ed5ec25e0de8e2c84fb8250650300c483721b2fef4
|
3 |
+
size 442268672
|
checkpoint-72/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc42bb916ea459a060753cd4cacba43b50df4215058117facd797793dd4037df
|
3 |
+
size 884658426
|
checkpoint-72/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e46a0b9576318c3cb909658a7777f7b980c2492296bfebd42c87020423c27c2
|
3 |
+
size 14244
|
checkpoint-72/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4776a1d290829eebe7cad027e643c943020df65dc3ad504950dd6659e9e061e8
|
3 |
+
size 1064
|
checkpoint-72/trainer_state.json
ADDED
@@ -0,0 +1,582 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0960981845855713,
|
3 |
+
"best_model_checkpoint": "autotrain-kly27-cj2jm/checkpoint-72",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 72,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.027777777777777776,
|
13 |
+
"grad_norm": 12.897777557373047,
|
14 |
+
"learning_rate": 1.388888888888889e-06,
|
15 |
+
"loss": 1.3688,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.05555555555555555,
|
20 |
+
"grad_norm": 12.80229377746582,
|
21 |
+
"learning_rate": 2.777777777777778e-06,
|
22 |
+
"loss": 1.3042,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.08333333333333333,
|
27 |
+
"grad_norm": 13.397868156433105,
|
28 |
+
"learning_rate": 4.166666666666667e-06,
|
29 |
+
"loss": 1.4323,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1111111111111111,
|
34 |
+
"grad_norm": Infinity,
|
35 |
+
"learning_rate": 4.166666666666667e-06,
|
36 |
+
"loss": 1.2959,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.1388888888888889,
|
41 |
+
"grad_norm": 13.320487976074219,
|
42 |
+
"learning_rate": 5.555555555555556e-06,
|
43 |
+
"loss": 1.3689,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.16666666666666666,
|
48 |
+
"grad_norm": 11.328529357910156,
|
49 |
+
"learning_rate": 6.944444444444445e-06,
|
50 |
+
"loss": 1.4755,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.19444444444444445,
|
55 |
+
"grad_norm": 13.40771770477295,
|
56 |
+
"learning_rate": 8.333333333333334e-06,
|
57 |
+
"loss": 1.4,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2222222222222222,
|
62 |
+
"grad_norm": 13.415596008300781,
|
63 |
+
"learning_rate": 9.722222222222223e-06,
|
64 |
+
"loss": 1.3943,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.25,
|
69 |
+
"grad_norm": 14.173083305358887,
|
70 |
+
"learning_rate": 1.1111111111111112e-05,
|
71 |
+
"loss": 1.5555,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.2777777777777778,
|
76 |
+
"grad_norm": NaN,
|
77 |
+
"learning_rate": 1.1111111111111112e-05,
|
78 |
+
"loss": 1.3157,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3055555555555556,
|
83 |
+
"grad_norm": 18.251338958740234,
|
84 |
+
"learning_rate": 1.25e-05,
|
85 |
+
"loss": 1.4651,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.3333333333333333,
|
90 |
+
"grad_norm": 13.927824974060059,
|
91 |
+
"learning_rate": 1.388888888888889e-05,
|
92 |
+
"loss": 1.3839,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.3611111111111111,
|
97 |
+
"grad_norm": 21.421586990356445,
|
98 |
+
"learning_rate": 1.527777777777778e-05,
|
99 |
+
"loss": 1.3521,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3888888888888889,
|
104 |
+
"grad_norm": 19.138628005981445,
|
105 |
+
"learning_rate": 1.6666666666666667e-05,
|
106 |
+
"loss": 1.4547,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.4166666666666667,
|
111 |
+
"grad_norm": 11.62378215789795,
|
112 |
+
"learning_rate": 1.8055555555555555e-05,
|
113 |
+
"loss": 1.4541,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.4444444444444444,
|
118 |
+
"grad_norm": 30.170297622680664,
|
119 |
+
"learning_rate": 1.9444444444444445e-05,
|
120 |
+
"loss": 1.5448,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.4722222222222222,
|
125 |
+
"grad_norm": Infinity,
|
126 |
+
"learning_rate": 1.9444444444444445e-05,
|
127 |
+
"loss": 1.3871,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.5,
|
132 |
+
"grad_norm": 11.596631050109863,
|
133 |
+
"learning_rate": 2.0833333333333336e-05,
|
134 |
+
"loss": 1.4873,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.5277777777777778,
|
139 |
+
"grad_norm": Infinity,
|
140 |
+
"learning_rate": 2.0833333333333336e-05,
|
141 |
+
"loss": 1.4276,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.5555555555555556,
|
146 |
+
"grad_norm": 31.894027709960938,
|
147 |
+
"learning_rate": 2.2222222222222223e-05,
|
148 |
+
"loss": 1.5219,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.5833333333333334,
|
153 |
+
"grad_norm": 12.369022369384766,
|
154 |
+
"learning_rate": 2.361111111111111e-05,
|
155 |
+
"loss": 1.4709,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.6111111111111112,
|
160 |
+
"grad_norm": 12.697649002075195,
|
161 |
+
"learning_rate": 2.5e-05,
|
162 |
+
"loss": 1.328,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.6388888888888888,
|
167 |
+
"grad_norm": 31.784717559814453,
|
168 |
+
"learning_rate": 2.6388888888888892e-05,
|
169 |
+
"loss": 1.3354,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.6666666666666666,
|
174 |
+
"grad_norm": 19.375490188598633,
|
175 |
+
"learning_rate": 2.777777777777778e-05,
|
176 |
+
"loss": 1.3274,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.6944444444444444,
|
181 |
+
"grad_norm": 25.336938858032227,
|
182 |
+
"learning_rate": 2.916666666666667e-05,
|
183 |
+
"loss": 1.3849,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.7222222222222222,
|
188 |
+
"grad_norm": 11.820061683654785,
|
189 |
+
"learning_rate": 3.055555555555556e-05,
|
190 |
+
"loss": 1.4387,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.75,
|
195 |
+
"grad_norm": 10.392581939697266,
|
196 |
+
"learning_rate": 3.194444444444444e-05,
|
197 |
+
"loss": 1.3236,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.7777777777777778,
|
202 |
+
"grad_norm": 7.693061828613281,
|
203 |
+
"learning_rate": 3.3333333333333335e-05,
|
204 |
+
"loss": 1.3445,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.8055555555555556,
|
209 |
+
"grad_norm": 13.216531753540039,
|
210 |
+
"learning_rate": 3.472222222222222e-05,
|
211 |
+
"loss": 1.576,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.8333333333333334,
|
216 |
+
"grad_norm": 12.331393241882324,
|
217 |
+
"learning_rate": 3.611111111111111e-05,
|
218 |
+
"loss": 1.5475,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.8611111111111112,
|
223 |
+
"grad_norm": 9.119909286499023,
|
224 |
+
"learning_rate": 3.7500000000000003e-05,
|
225 |
+
"loss": 1.3323,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.8888888888888888,
|
230 |
+
"grad_norm": 12.2987699508667,
|
231 |
+
"learning_rate": 3.888888888888889e-05,
|
232 |
+
"loss": 1.5143,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.9166666666666666,
|
237 |
+
"grad_norm": 8.577352523803711,
|
238 |
+
"learning_rate": 4.027777777777778e-05,
|
239 |
+
"loss": 1.33,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.9444444444444444,
|
244 |
+
"grad_norm": 13.695905685424805,
|
245 |
+
"learning_rate": 4.166666666666667e-05,
|
246 |
+
"loss": 1.4465,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.9722222222222222,
|
251 |
+
"grad_norm": 8.713174819946289,
|
252 |
+
"learning_rate": 4.305555555555556e-05,
|
253 |
+
"loss": 1.4567,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.0,
|
258 |
+
"grad_norm": 7.167442798614502,
|
259 |
+
"learning_rate": 4.4444444444444447e-05,
|
260 |
+
"loss": 1.1802,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.0,
|
265 |
+
"eval_accuracy": 0.4305555555555556,
|
266 |
+
"eval_f1_macro": 0.3679068360556564,
|
267 |
+
"eval_f1_micro": 0.4305555555555556,
|
268 |
+
"eval_f1_weighted": 0.36790683605565644,
|
269 |
+
"eval_loss": 1.2675509452819824,
|
270 |
+
"eval_precision_macro": 0.36041666666666666,
|
271 |
+
"eval_precision_micro": 0.4305555555555556,
|
272 |
+
"eval_precision_weighted": 0.36041666666666666,
|
273 |
+
"eval_recall_macro": 0.4305555555555556,
|
274 |
+
"eval_recall_micro": 0.4305555555555556,
|
275 |
+
"eval_recall_weighted": 0.4305555555555556,
|
276 |
+
"eval_runtime": 0.1633,
|
277 |
+
"eval_samples_per_second": 440.845,
|
278 |
+
"eval_steps_per_second": 30.614,
|
279 |
+
"step": 36
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.0277777777777777,
|
283 |
+
"grad_norm": 8.469690322875977,
|
284 |
+
"learning_rate": 4.5833333333333334e-05,
|
285 |
+
"loss": 1.2082,
|
286 |
+
"step": 37
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.0555555555555556,
|
290 |
+
"grad_norm": 10.915877342224121,
|
291 |
+
"learning_rate": 4.722222222222222e-05,
|
292 |
+
"loss": 1.4532,
|
293 |
+
"step": 38
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.0833333333333333,
|
297 |
+
"grad_norm": 14.45482349395752,
|
298 |
+
"learning_rate": 4.8611111111111115e-05,
|
299 |
+
"loss": 1.5985,
|
300 |
+
"step": 39
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.1111111111111112,
|
304 |
+
"grad_norm": 9.392463684082031,
|
305 |
+
"learning_rate": 5e-05,
|
306 |
+
"loss": 1.0948,
|
307 |
+
"step": 40
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.1388888888888888,
|
311 |
+
"grad_norm": 10.35122013092041,
|
312 |
+
"learning_rate": 4.984567901234568e-05,
|
313 |
+
"loss": 1.3086,
|
314 |
+
"step": 41
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.1666666666666667,
|
318 |
+
"grad_norm": 11.031954765319824,
|
319 |
+
"learning_rate": 4.969135802469136e-05,
|
320 |
+
"loss": 1.2919,
|
321 |
+
"step": 42
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.1944444444444444,
|
325 |
+
"grad_norm": 12.27844524383545,
|
326 |
+
"learning_rate": 4.9537037037037035e-05,
|
327 |
+
"loss": 1.5781,
|
328 |
+
"step": 43
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.2222222222222223,
|
332 |
+
"grad_norm": 8.939851760864258,
|
333 |
+
"learning_rate": 4.938271604938271e-05,
|
334 |
+
"loss": 1.2585,
|
335 |
+
"step": 44
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.25,
|
339 |
+
"grad_norm": 11.441798210144043,
|
340 |
+
"learning_rate": 4.92283950617284e-05,
|
341 |
+
"loss": 1.4658,
|
342 |
+
"step": 45
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.2777777777777777,
|
346 |
+
"grad_norm": 43.12884521484375,
|
347 |
+
"learning_rate": 4.9074074074074075e-05,
|
348 |
+
"loss": 1.2574,
|
349 |
+
"step": 46
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.3055555555555556,
|
353 |
+
"grad_norm": 8.0072021484375,
|
354 |
+
"learning_rate": 4.891975308641975e-05,
|
355 |
+
"loss": 1.1718,
|
356 |
+
"step": 47
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.3333333333333333,
|
360 |
+
"grad_norm": 8.759527206420898,
|
361 |
+
"learning_rate": 4.876543209876544e-05,
|
362 |
+
"loss": 1.3,
|
363 |
+
"step": 48
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.3611111111111112,
|
367 |
+
"grad_norm": 22.927743911743164,
|
368 |
+
"learning_rate": 4.8611111111111115e-05,
|
369 |
+
"loss": 1.1322,
|
370 |
+
"step": 49
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.3888888888888888,
|
374 |
+
"grad_norm": 8.5543794631958,
|
375 |
+
"learning_rate": 4.845679012345679e-05,
|
376 |
+
"loss": 0.9913,
|
377 |
+
"step": 50
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.4166666666666667,
|
381 |
+
"grad_norm": 10.449179649353027,
|
382 |
+
"learning_rate": 4.830246913580247e-05,
|
383 |
+
"loss": 1.2861,
|
384 |
+
"step": 51
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.4444444444444444,
|
388 |
+
"grad_norm": 10.111722946166992,
|
389 |
+
"learning_rate": 4.814814814814815e-05,
|
390 |
+
"loss": 1.1513,
|
391 |
+
"step": 52
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 1.4722222222222223,
|
395 |
+
"grad_norm": 7.970386981964111,
|
396 |
+
"learning_rate": 4.799382716049383e-05,
|
397 |
+
"loss": 0.8262,
|
398 |
+
"step": 53
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.5,
|
402 |
+
"grad_norm": 9.8405179977417,
|
403 |
+
"learning_rate": 4.783950617283951e-05,
|
404 |
+
"loss": 1.2034,
|
405 |
+
"step": 54
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.5277777777777777,
|
409 |
+
"grad_norm": 11.818384170532227,
|
410 |
+
"learning_rate": 4.768518518518519e-05,
|
411 |
+
"loss": 1.1393,
|
412 |
+
"step": 55
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.5555555555555556,
|
416 |
+
"grad_norm": 11.990804672241211,
|
417 |
+
"learning_rate": 4.7530864197530866e-05,
|
418 |
+
"loss": 1.4407,
|
419 |
+
"step": 56
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.5833333333333335,
|
423 |
+
"grad_norm": 8.206277847290039,
|
424 |
+
"learning_rate": 4.7376543209876543e-05,
|
425 |
+
"loss": 1.0123,
|
426 |
+
"step": 57
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.6111111111111112,
|
430 |
+
"grad_norm": 9.01528263092041,
|
431 |
+
"learning_rate": 4.722222222222222e-05,
|
432 |
+
"loss": 1.0687,
|
433 |
+
"step": 58
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 1.6388888888888888,
|
437 |
+
"grad_norm": 16.894432067871094,
|
438 |
+
"learning_rate": 4.70679012345679e-05,
|
439 |
+
"loss": 1.5649,
|
440 |
+
"step": 59
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.6666666666666665,
|
444 |
+
"grad_norm": 10.745332717895508,
|
445 |
+
"learning_rate": 4.691358024691358e-05,
|
446 |
+
"loss": 1.3554,
|
447 |
+
"step": 60
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.6944444444444444,
|
451 |
+
"grad_norm": 58.126827239990234,
|
452 |
+
"learning_rate": 4.675925925925926e-05,
|
453 |
+
"loss": 0.7321,
|
454 |
+
"step": 61
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 1.7222222222222223,
|
458 |
+
"grad_norm": 9.566184043884277,
|
459 |
+
"learning_rate": 4.6604938271604945e-05,
|
460 |
+
"loss": 1.2133,
|
461 |
+
"step": 62
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.75,
|
465 |
+
"grad_norm": 13.502289772033691,
|
466 |
+
"learning_rate": 4.645061728395062e-05,
|
467 |
+
"loss": 1.5203,
|
468 |
+
"step": 63
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 1.7777777777777777,
|
472 |
+
"grad_norm": 20.97662353515625,
|
473 |
+
"learning_rate": 4.62962962962963e-05,
|
474 |
+
"loss": 2.1095,
|
475 |
+
"step": 64
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 1.8055555555555556,
|
479 |
+
"grad_norm": 13.869538307189941,
|
480 |
+
"learning_rate": 4.614197530864198e-05,
|
481 |
+
"loss": 0.9453,
|
482 |
+
"step": 65
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.8333333333333335,
|
486 |
+
"grad_norm": 8.554522514343262,
|
487 |
+
"learning_rate": 4.5987654320987656e-05,
|
488 |
+
"loss": 1.0372,
|
489 |
+
"step": 66
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.8611111111111112,
|
493 |
+
"grad_norm": 8.473492622375488,
|
494 |
+
"learning_rate": 4.5833333333333334e-05,
|
495 |
+
"loss": 1.1877,
|
496 |
+
"step": 67
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.8888888888888888,
|
500 |
+
"grad_norm": 16.97106170654297,
|
501 |
+
"learning_rate": 4.567901234567901e-05,
|
502 |
+
"loss": 1.0579,
|
503 |
+
"step": 68
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.9166666666666665,
|
507 |
+
"grad_norm": 13.524179458618164,
|
508 |
+
"learning_rate": 4.5524691358024696e-05,
|
509 |
+
"loss": 1.448,
|
510 |
+
"step": 69
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 1.9444444444444444,
|
514 |
+
"grad_norm": 17.190797805786133,
|
515 |
+
"learning_rate": 4.5370370370370374e-05,
|
516 |
+
"loss": 1.0511,
|
517 |
+
"step": 70
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 1.9722222222222223,
|
521 |
+
"grad_norm": 11.905118942260742,
|
522 |
+
"learning_rate": 4.521604938271605e-05,
|
523 |
+
"loss": 1.1331,
|
524 |
+
"step": 71
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 2.0,
|
528 |
+
"grad_norm": 9.310904502868652,
|
529 |
+
"learning_rate": 4.506172839506173e-05,
|
530 |
+
"loss": 0.9219,
|
531 |
+
"step": 72
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 2.0,
|
535 |
+
"eval_accuracy": 0.4722222222222222,
|
536 |
+
"eval_f1_macro": 0.45793362717137664,
|
537 |
+
"eval_f1_micro": 0.4722222222222222,
|
538 |
+
"eval_f1_weighted": 0.45793362717137676,
|
539 |
+
"eval_loss": 1.0960981845855713,
|
540 |
+
"eval_precision_macro": 0.6229166666666666,
|
541 |
+
"eval_precision_micro": 0.4722222222222222,
|
542 |
+
"eval_precision_weighted": 0.6229166666666667,
|
543 |
+
"eval_recall_macro": 0.47222222222222227,
|
544 |
+
"eval_recall_micro": 0.4722222222222222,
|
545 |
+
"eval_recall_weighted": 0.4722222222222222,
|
546 |
+
"eval_runtime": 0.1626,
|
547 |
+
"eval_samples_per_second": 442.909,
|
548 |
+
"eval_steps_per_second": 30.758,
|
549 |
+
"step": 72
|
550 |
+
}
|
551 |
+
],
|
552 |
+
"logging_steps": 1,
|
553 |
+
"max_steps": 360,
|
554 |
+
"num_input_tokens_seen": 0,
|
555 |
+
"num_train_epochs": 10,
|
556 |
+
"save_steps": 500,
|
557 |
+
"stateful_callbacks": {
|
558 |
+
"EarlyStoppingCallback": {
|
559 |
+
"args": {
|
560 |
+
"early_stopping_patience": 5,
|
561 |
+
"early_stopping_threshold": 0.01
|
562 |
+
},
|
563 |
+
"attributes": {
|
564 |
+
"early_stopping_patience_counter": 0
|
565 |
+
}
|
566 |
+
},
|
567 |
+
"TrainerControl": {
|
568 |
+
"args": {
|
569 |
+
"should_epoch_stop": false,
|
570 |
+
"should_evaluate": false,
|
571 |
+
"should_log": false,
|
572 |
+
"should_save": true,
|
573 |
+
"should_training_stop": false
|
574 |
+
},
|
575 |
+
"attributes": {}
|
576 |
+
}
|
577 |
+
},
|
578 |
+
"total_flos": 37888672333824.0,
|
579 |
+
"train_batch_size": 8,
|
580 |
+
"trial_name": null,
|
581 |
+
"trial_params": null
|
582 |
+
}
|
checkpoint-72/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90e8701d17b5e169413d92462ffc3abc16f4af789b44a78416b8756c3a9ab664
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
+
"_num_labels": 4,
|
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": "Action",
|
16 |
+
"1": "Attention",
|
17 |
+
"2": "Desire",
|
18 |
+
"3": "Interest"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Action": 0,
|
24 |
+
"Attention": 1,
|
25 |
+
"Desire": 2,
|
26 |
+
"Interest": 3
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"output_past": true,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.43.1",
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 31923
|
42 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1aa85aa535f0dd9fa7b57ed5ec25e0de8e2c84fb8250650300c483721b2fef4
|
3 |
+
size 442268672
|
runs/Aug05_17-25-27_r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy/events.out.tfevents.1722878728.r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy.82.0
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:d80bbf642d58ec62149ba118d1282a23c3e29ebe198907f8e6c31b8832b869ed
|
3 |
+
size 64002
|
runs/Aug05_17-25-27_r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy/events.out.tfevents.1722878766.r-apriandito-autotrain-gpu-dm9xesp7-a4686-6r7xy.82.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36990bdd04dfd05691e6e4c8658dd3f2a263c852636ea0d58e456aa4bb1d183c
|
3 |
+
size 921
|
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 sha256:90e8701d17b5e169413d92462ffc3abc16f4af789b44a78416b8756c3a9ab664
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-kly27-cj2jm/autotrain-data",
|
3 |
+
"model": "indolem/indobert-base-uncased",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 10,
|
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": "autotrain-kly27-cj2jm",
|
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
|
|