apriandito
commited on
Commit
•
6f10081
1
Parent(s):
f4f5400
Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-588/config.json +42 -0
- checkpoint-588/model.safetensors +3 -0
- checkpoint-588/optimizer.pt +3 -0
- checkpoint-588/rng_state.pth +3 -0
- checkpoint-588/scheduler.pt +3 -0
- checkpoint-588/trainer_state.json +551 -0
- checkpoint-588/training_args.bin +3 -0
- config.json +42 -0
- model.safetensors +3 -0
- runs/Aug05_22-45-28_r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc/events.out.tfevents.1722897929.r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc.131.0 +2 -2
- runs/Aug05_22-45-28_r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc/events.out.tfevents.1722898001.r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc.131.1 +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: 0.877387523651123
|
17 |
+
|
18 |
+
f1_macro: 0.693991401598852
|
19 |
+
|
20 |
+
f1_micro: 0.6938775510204082
|
21 |
+
|
22 |
+
f1_weighted: 0.6939914015988521
|
23 |
+
|
24 |
+
precision_macro: 0.6961606483158189
|
25 |
+
|
26 |
+
precision_micro: 0.6938775510204082
|
27 |
+
|
28 |
+
precision_weighted: 0.6961606483158188
|
29 |
+
|
30 |
+
recall_macro: 0.6938775510204082
|
31 |
+
|
32 |
+
recall_micro: 0.6938775510204082
|
33 |
+
|
34 |
+
recall_weighted: 0.6938775510204082
|
35 |
+
|
36 |
+
accuracy: 0.6938775510204082
|
checkpoint-588/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-588/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3b6195fccb5468983f303c71c51a42ebaf7fcd5da18f4fc64b2d12b73b5aa0
|
3 |
+
size 442268672
|
checkpoint-588/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ca5e826530c2a4af3302c532524fb46d16b5d0b7187ab6f2a2a2f04ac21590f
|
3 |
+
size 884658426
|
checkpoint-588/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eefc4af11579c2b15e7e970bf1963147004f12f661654a1e1dadbb79e20ede4
|
3 |
+
size 14244
|
checkpoint-588/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e1f3092ecc0aead253a8e833747adae2ea06c261721f1ce0e78acea20e1e430
|
3 |
+
size 1064
|
checkpoint-588/trainer_state.json
ADDED
@@ -0,0 +1,551 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.877387523651123,
|
3 |
+
"best_model_checkpoint": "autotrain-8c1y5-lsgog/checkpoint-588",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 588,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04591836734693878,
|
13 |
+
"grad_norm": 13.273290634155273,
|
14 |
+
"learning_rate": 5.932203389830509e-06,
|
15 |
+
"loss": 1.3557,
|
16 |
+
"step": 9
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09183673469387756,
|
20 |
+
"grad_norm": Infinity,
|
21 |
+
"learning_rate": 1.2711864406779661e-05,
|
22 |
+
"loss": 1.4241,
|
23 |
+
"step": 18
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1377551020408163,
|
27 |
+
"grad_norm": 16.573213577270508,
|
28 |
+
"learning_rate": 2.033898305084746e-05,
|
29 |
+
"loss": 1.3423,
|
30 |
+
"step": 27
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1836734693877551,
|
34 |
+
"grad_norm": 11.559469223022461,
|
35 |
+
"learning_rate": 2.7966101694915255e-05,
|
36 |
+
"loss": 1.3488,
|
37 |
+
"step": 36
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.22959183673469388,
|
41 |
+
"grad_norm": 13.121813774108887,
|
42 |
+
"learning_rate": 3.474576271186441e-05,
|
43 |
+
"loss": 1.2955,
|
44 |
+
"step": 45
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2755102040816326,
|
48 |
+
"grad_norm": 19.90020179748535,
|
49 |
+
"learning_rate": 4.152542372881356e-05,
|
50 |
+
"loss": 1.3652,
|
51 |
+
"step": 54
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.32142857142857145,
|
55 |
+
"grad_norm": 42.38658142089844,
|
56 |
+
"learning_rate": 4.915254237288136e-05,
|
57 |
+
"loss": 1.3228,
|
58 |
+
"step": 63
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3673469387755102,
|
62 |
+
"grad_norm": 16.879314422607422,
|
63 |
+
"learning_rate": 4.9243856332703216e-05,
|
64 |
+
"loss": 1.4373,
|
65 |
+
"step": 72
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.413265306122449,
|
69 |
+
"grad_norm": 10.268380165100098,
|
70 |
+
"learning_rate": 4.839319470699433e-05,
|
71 |
+
"loss": 1.4207,
|
72 |
+
"step": 81
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.45918367346938777,
|
76 |
+
"grad_norm": 49.17950439453125,
|
77 |
+
"learning_rate": 4.754253308128545e-05,
|
78 |
+
"loss": 1.3291,
|
79 |
+
"step": 90
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.5051020408163265,
|
83 |
+
"grad_norm": 10.70398235321045,
|
84 |
+
"learning_rate": 4.669187145557656e-05,
|
85 |
+
"loss": 1.2806,
|
86 |
+
"step": 99
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5510204081632653,
|
90 |
+
"grad_norm": 14.200324058532715,
|
91 |
+
"learning_rate": 4.584120982986768e-05,
|
92 |
+
"loss": 1.5323,
|
93 |
+
"step": 108
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5969387755102041,
|
97 |
+
"grad_norm": 13.224357604980469,
|
98 |
+
"learning_rate": 4.499054820415879e-05,
|
99 |
+
"loss": 1.3381,
|
100 |
+
"step": 117
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6428571428571429,
|
104 |
+
"grad_norm": 12.96914291381836,
|
105 |
+
"learning_rate": 4.413988657844991e-05,
|
106 |
+
"loss": 1.3752,
|
107 |
+
"step": 126
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6887755102040817,
|
111 |
+
"grad_norm": 9.912948608398438,
|
112 |
+
"learning_rate": 4.3289224952741024e-05,
|
113 |
+
"loss": 1.2576,
|
114 |
+
"step": 135
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7346938775510204,
|
118 |
+
"grad_norm": 8.655780792236328,
|
119 |
+
"learning_rate": 4.243856332703214e-05,
|
120 |
+
"loss": 1.1475,
|
121 |
+
"step": 144
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.7806122448979592,
|
125 |
+
"grad_norm": 6.818447113037109,
|
126 |
+
"learning_rate": 4.158790170132325e-05,
|
127 |
+
"loss": 1.1608,
|
128 |
+
"step": 153
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.826530612244898,
|
132 |
+
"grad_norm": 36.97886276245117,
|
133 |
+
"learning_rate": 4.073724007561437e-05,
|
134 |
+
"loss": 1.0747,
|
135 |
+
"step": 162
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.8724489795918368,
|
139 |
+
"grad_norm": 18.22942543029785,
|
140 |
+
"learning_rate": 3.988657844990548e-05,
|
141 |
+
"loss": 1.0558,
|
142 |
+
"step": 171
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.9183673469387755,
|
146 |
+
"grad_norm": 14.418513298034668,
|
147 |
+
"learning_rate": 3.90359168241966e-05,
|
148 |
+
"loss": 1.1605,
|
149 |
+
"step": 180
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.9642857142857143,
|
153 |
+
"grad_norm": 17.860261917114258,
|
154 |
+
"learning_rate": 3.8185255198487716e-05,
|
155 |
+
"loss": 1.236,
|
156 |
+
"step": 189
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.0,
|
160 |
+
"eval_accuracy": 0.5357142857142857,
|
161 |
+
"eval_f1_macro": 0.5169015312293899,
|
162 |
+
"eval_f1_micro": 0.5357142857142857,
|
163 |
+
"eval_f1_weighted": 0.5169015312293898,
|
164 |
+
"eval_loss": 1.0397837162017822,
|
165 |
+
"eval_precision_macro": 0.6040472568054893,
|
166 |
+
"eval_precision_micro": 0.5357142857142857,
|
167 |
+
"eval_precision_weighted": 0.6040472568054893,
|
168 |
+
"eval_recall_macro": 0.5357142857142857,
|
169 |
+
"eval_recall_micro": 0.5357142857142857,
|
170 |
+
"eval_recall_weighted": 0.5357142857142857,
|
171 |
+
"eval_runtime": 0.8403,
|
172 |
+
"eval_samples_per_second": 466.478,
|
173 |
+
"eval_steps_per_second": 29.75,
|
174 |
+
"step": 196
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.010204081632653,
|
178 |
+
"grad_norm": 10.591184616088867,
|
179 |
+
"learning_rate": 3.733459357277883e-05,
|
180 |
+
"loss": 1.0559,
|
181 |
+
"step": 198
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.0561224489795917,
|
185 |
+
"grad_norm": 20.194005966186523,
|
186 |
+
"learning_rate": 3.648393194706995e-05,
|
187 |
+
"loss": 1.0911,
|
188 |
+
"step": 207
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.1020408163265305,
|
192 |
+
"grad_norm": 11.607887268066406,
|
193 |
+
"learning_rate": 3.563327032136106e-05,
|
194 |
+
"loss": 0.9098,
|
195 |
+
"step": 216
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.1479591836734695,
|
199 |
+
"grad_norm": 29.328445434570312,
|
200 |
+
"learning_rate": 3.478260869565218e-05,
|
201 |
+
"loss": 0.9996,
|
202 |
+
"step": 225
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.193877551020408,
|
206 |
+
"grad_norm": 12.970704078674316,
|
207 |
+
"learning_rate": 3.393194706994329e-05,
|
208 |
+
"loss": 0.8921,
|
209 |
+
"step": 234
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.239795918367347,
|
213 |
+
"grad_norm": 11.346271514892578,
|
214 |
+
"learning_rate": 3.308128544423441e-05,
|
215 |
+
"loss": 0.7828,
|
216 |
+
"step": 243
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.2857142857142856,
|
220 |
+
"grad_norm": 26.86040687561035,
|
221 |
+
"learning_rate": 3.2230623818525524e-05,
|
222 |
+
"loss": 0.9659,
|
223 |
+
"step": 252
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.3316326530612246,
|
227 |
+
"grad_norm": 54.28874969482422,
|
228 |
+
"learning_rate": 3.137996219281664e-05,
|
229 |
+
"loss": 0.8242,
|
230 |
+
"step": 261
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.3775510204081631,
|
234 |
+
"grad_norm": 23.010454177856445,
|
235 |
+
"learning_rate": 3.052930056710775e-05,
|
236 |
+
"loss": 0.9375,
|
237 |
+
"step": 270
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.4234693877551021,
|
241 |
+
"grad_norm": 35.56595230102539,
|
242 |
+
"learning_rate": 2.9678638941398867e-05,
|
243 |
+
"loss": 0.8834,
|
244 |
+
"step": 279
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.469387755102041,
|
248 |
+
"grad_norm": 20.237417221069336,
|
249 |
+
"learning_rate": 2.882797731568998e-05,
|
250 |
+
"loss": 1.2205,
|
251 |
+
"step": 288
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.5153061224489797,
|
255 |
+
"grad_norm": 17.17922019958496,
|
256 |
+
"learning_rate": 2.7977315689981097e-05,
|
257 |
+
"loss": 1.1868,
|
258 |
+
"step": 297
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.5612244897959182,
|
262 |
+
"grad_norm": 36.083892822265625,
|
263 |
+
"learning_rate": 2.7126654064272213e-05,
|
264 |
+
"loss": 0.7935,
|
265 |
+
"step": 306
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.6071428571428572,
|
269 |
+
"grad_norm": 12.143678665161133,
|
270 |
+
"learning_rate": 2.6275992438563328e-05,
|
271 |
+
"loss": 0.8405,
|
272 |
+
"step": 315
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.6530612244897958,
|
276 |
+
"grad_norm": 17.92725944519043,
|
277 |
+
"learning_rate": 2.5425330812854444e-05,
|
278 |
+
"loss": 0.9103,
|
279 |
+
"step": 324
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.6989795918367347,
|
283 |
+
"grad_norm": 8.833161354064941,
|
284 |
+
"learning_rate": 2.457466918714556e-05,
|
285 |
+
"loss": 0.8916,
|
286 |
+
"step": 333
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.7448979591836735,
|
290 |
+
"grad_norm": 16.942583084106445,
|
291 |
+
"learning_rate": 2.3724007561436674e-05,
|
292 |
+
"loss": 0.8364,
|
293 |
+
"step": 342
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.7908163265306123,
|
297 |
+
"grad_norm": 52.1734733581543,
|
298 |
+
"learning_rate": 2.287334593572779e-05,
|
299 |
+
"loss": 1.0671,
|
300 |
+
"step": 351
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.836734693877551,
|
304 |
+
"grad_norm": 17.128494262695312,
|
305 |
+
"learning_rate": 2.2022684310018905e-05,
|
306 |
+
"loss": 0.7792,
|
307 |
+
"step": 360
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.8826530612244898,
|
311 |
+
"grad_norm": 11.736278533935547,
|
312 |
+
"learning_rate": 2.117202268431002e-05,
|
313 |
+
"loss": 0.7889,
|
314 |
+
"step": 369
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.9285714285714286,
|
318 |
+
"grad_norm": 22.40500831604004,
|
319 |
+
"learning_rate": 2.0321361058601136e-05,
|
320 |
+
"loss": 0.8719,
|
321 |
+
"step": 378
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.9744897959183674,
|
325 |
+
"grad_norm": 7.382483959197998,
|
326 |
+
"learning_rate": 1.947069943289225e-05,
|
327 |
+
"loss": 0.7411,
|
328 |
+
"step": 387
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 2.0,
|
332 |
+
"eval_accuracy": 0.6454081632653061,
|
333 |
+
"eval_f1_macro": 0.6383598362124523,
|
334 |
+
"eval_f1_micro": 0.6454081632653061,
|
335 |
+
"eval_f1_weighted": 0.6383598362124524,
|
336 |
+
"eval_loss": 0.9568982720375061,
|
337 |
+
"eval_precision_macro": 0.6613340870548332,
|
338 |
+
"eval_precision_micro": 0.6454081632653061,
|
339 |
+
"eval_precision_weighted": 0.6613340870548333,
|
340 |
+
"eval_recall_macro": 0.6454081632653061,
|
341 |
+
"eval_recall_micro": 0.6454081632653061,
|
342 |
+
"eval_recall_weighted": 0.6454081632653061,
|
343 |
+
"eval_runtime": 0.8449,
|
344 |
+
"eval_samples_per_second": 463.965,
|
345 |
+
"eval_steps_per_second": 29.59,
|
346 |
+
"step": 392
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 2.020408163265306,
|
350 |
+
"grad_norm": 12.731431007385254,
|
351 |
+
"learning_rate": 1.8714555765595465e-05,
|
352 |
+
"loss": 0.6781,
|
353 |
+
"step": 396
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 2.066326530612245,
|
357 |
+
"grad_norm": 20.548770904541016,
|
358 |
+
"learning_rate": 1.786389413988658e-05,
|
359 |
+
"loss": 0.4761,
|
360 |
+
"step": 405
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.1122448979591835,
|
364 |
+
"grad_norm": 22.985334396362305,
|
365 |
+
"learning_rate": 1.7013232514177692e-05,
|
366 |
+
"loss": 0.6752,
|
367 |
+
"step": 414
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 2.1581632653061225,
|
371 |
+
"grad_norm": 22.62578010559082,
|
372 |
+
"learning_rate": 1.6162570888468808e-05,
|
373 |
+
"loss": 0.5669,
|
374 |
+
"step": 423
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.204081632653061,
|
378 |
+
"grad_norm": 11.662425994873047,
|
379 |
+
"learning_rate": 1.5311909262759923e-05,
|
380 |
+
"loss": 0.4492,
|
381 |
+
"step": 432
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.25,
|
385 |
+
"grad_norm": 22.092039108276367,
|
386 |
+
"learning_rate": 1.446124763705104e-05,
|
387 |
+
"loss": 0.6171,
|
388 |
+
"step": 441
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 2.295918367346939,
|
392 |
+
"grad_norm": 18.506088256835938,
|
393 |
+
"learning_rate": 1.3610586011342156e-05,
|
394 |
+
"loss": 0.516,
|
395 |
+
"step": 450
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.3418367346938775,
|
399 |
+
"grad_norm": 50.34038543701172,
|
400 |
+
"learning_rate": 1.2759924385633271e-05,
|
401 |
+
"loss": 0.8574,
|
402 |
+
"step": 459
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.387755102040816,
|
406 |
+
"grad_norm": 17.631423950195312,
|
407 |
+
"learning_rate": 1.1909262759924386e-05,
|
408 |
+
"loss": 0.5258,
|
409 |
+
"step": 468
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 2.433673469387755,
|
413 |
+
"grad_norm": 14.761687278747559,
|
414 |
+
"learning_rate": 1.1058601134215502e-05,
|
415 |
+
"loss": 0.697,
|
416 |
+
"step": 477
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.479591836734694,
|
420 |
+
"grad_norm": 15.371265411376953,
|
421 |
+
"learning_rate": 1.0207939508506617e-05,
|
422 |
+
"loss": 0.6966,
|
423 |
+
"step": 486
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 2.5255102040816326,
|
427 |
+
"grad_norm": 11.90428638458252,
|
428 |
+
"learning_rate": 9.357277882797732e-06,
|
429 |
+
"loss": 0.4714,
|
430 |
+
"step": 495
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 2.571428571428571,
|
434 |
+
"grad_norm": 20.273618698120117,
|
435 |
+
"learning_rate": 8.506616257088846e-06,
|
436 |
+
"loss": 0.4554,
|
437 |
+
"step": 504
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 2.61734693877551,
|
441 |
+
"grad_norm": 16.07473373413086,
|
442 |
+
"learning_rate": 7.655954631379962e-06,
|
443 |
+
"loss": 0.5895,
|
444 |
+
"step": 513
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.663265306122449,
|
448 |
+
"grad_norm": 13.280965805053711,
|
449 |
+
"learning_rate": 6.805293005671078e-06,
|
450 |
+
"loss": 0.5932,
|
451 |
+
"step": 522
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 2.7091836734693877,
|
455 |
+
"grad_norm": 14.767223358154297,
|
456 |
+
"learning_rate": 5.954631379962193e-06,
|
457 |
+
"loss": 0.4047,
|
458 |
+
"step": 531
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.7551020408163263,
|
462 |
+
"grad_norm": 12.252891540527344,
|
463 |
+
"learning_rate": 5.1039697542533085e-06,
|
464 |
+
"loss": 0.544,
|
465 |
+
"step": 540
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.8010204081632653,
|
469 |
+
"grad_norm": 17.47493553161621,
|
470 |
+
"learning_rate": 4.253308128544423e-06,
|
471 |
+
"loss": 0.535,
|
472 |
+
"step": 549
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 2.8469387755102042,
|
476 |
+
"grad_norm": 12.823530197143555,
|
477 |
+
"learning_rate": 3.402646502835539e-06,
|
478 |
+
"loss": 0.5172,
|
479 |
+
"step": 558
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 2.892857142857143,
|
483 |
+
"grad_norm": 12.597037315368652,
|
484 |
+
"learning_rate": 2.5519848771266543e-06,
|
485 |
+
"loss": 0.5575,
|
486 |
+
"step": 567
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 2.938775510204082,
|
490 |
+
"grad_norm": 3.2630369663238525,
|
491 |
+
"learning_rate": 1.7013232514177694e-06,
|
492 |
+
"loss": 0.5858,
|
493 |
+
"step": 576
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.9846938775510203,
|
497 |
+
"grad_norm": 20.04022789001465,
|
498 |
+
"learning_rate": 8.506616257088847e-07,
|
499 |
+
"loss": 0.6399,
|
500 |
+
"step": 585
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 3.0,
|
504 |
+
"eval_accuracy": 0.6938775510204082,
|
505 |
+
"eval_f1_macro": 0.693991401598852,
|
506 |
+
"eval_f1_micro": 0.6938775510204082,
|
507 |
+
"eval_f1_weighted": 0.6939914015988521,
|
508 |
+
"eval_loss": 0.877387523651123,
|
509 |
+
"eval_precision_macro": 0.6961606483158189,
|
510 |
+
"eval_precision_micro": 0.6938775510204082,
|
511 |
+
"eval_precision_weighted": 0.6961606483158188,
|
512 |
+
"eval_recall_macro": 0.6938775510204082,
|
513 |
+
"eval_recall_micro": 0.6938775510204082,
|
514 |
+
"eval_recall_weighted": 0.6938775510204082,
|
515 |
+
"eval_runtime": 0.8233,
|
516 |
+
"eval_samples_per_second": 476.156,
|
517 |
+
"eval_steps_per_second": 30.367,
|
518 |
+
"step": 588
|
519 |
+
}
|
520 |
+
],
|
521 |
+
"logging_steps": 9,
|
522 |
+
"max_steps": 588,
|
523 |
+
"num_input_tokens_seen": 0,
|
524 |
+
"num_train_epochs": 3,
|
525 |
+
"save_steps": 500,
|
526 |
+
"stateful_callbacks": {
|
527 |
+
"EarlyStoppingCallback": {
|
528 |
+
"args": {
|
529 |
+
"early_stopping_patience": 5,
|
530 |
+
"early_stopping_threshold": 0.01
|
531 |
+
},
|
532 |
+
"attributes": {
|
533 |
+
"early_stopping_patience_counter": 0
|
534 |
+
}
|
535 |
+
},
|
536 |
+
"TrainerControl": {
|
537 |
+
"args": {
|
538 |
+
"should_epoch_stop": false,
|
539 |
+
"should_evaluate": false,
|
540 |
+
"should_log": false,
|
541 |
+
"should_save": true,
|
542 |
+
"should_training_stop": true
|
543 |
+
},
|
544 |
+
"attributes": {}
|
545 |
+
}
|
546 |
+
},
|
547 |
+
"total_flos": 308634810052608.0,
|
548 |
+
"train_batch_size": 8,
|
549 |
+
"trial_name": null,
|
550 |
+
"trial_params": null
|
551 |
+
}
|
checkpoint-588/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e02db52b9b9af7ea77109756932b87466c60fda3484b44d34e0dba9a123d74ba
|
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 sha256:0e3b6195fccb5468983f303c71c51a42ebaf7fcd5da18f4fc64b2d12b73b5aa0
|
3 |
+
size 442268672
|
runs/Aug05_22-45-28_r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc/events.out.tfevents.1722897929.r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc.131.0
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 sha256:28df7afe8db7365e9900f7bfcd178e3fd534f0f8220ce9cebb3622ee1fb9ee30
|
3 |
+
size 21709
|
runs/Aug05_22-45-28_r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc/events.out.tfevents.1722898001.r-apriandito-autotrain-gpu-tz1drlwq-12668-ujmdc.131.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11f1e8a4c1bebd7dc1a03e9bff9126fa8769a14ff10b68e7055cd6bc01d9992d
|
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:e02db52b9b9af7ea77109756932b87466c60fda3484b44d34e0dba9a123d74ba
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-8c1y5-lsgog/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": "autotrain-8c1y5-lsgog",
|
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
|
|