Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +37 -0
- autotrain-data/dataset_dict.json +1 -0
- autotrain-data/train/data-00000-of-00001.arrow +3 -0
- autotrain-data/train/dataset_info.json +0 -0
- autotrain-data/train/state.json +16 -0
- autotrain-data/validation/data-00000-of-00001.arrow +3 -0
- autotrain-data/validation/dataset_info.json +0 -0
- autotrain-data/validation/state.json +16 -0
- checkpoint-20424/config.json +3 -0
- checkpoint-20424/model.safetensors +3 -0
- checkpoint-20424/optimizer.pt +3 -0
- checkpoint-20424/rng_state.pth +3 -0
- checkpoint-20424/scheduler.pt +3 -0
- checkpoint-20424/trainer_state.json +180 -0
- checkpoint-20424/training_args.bin +3 -0
- config.json +3 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-20424/config.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
config.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
datasets:
|
9 |
+
- bert-multilingual-uncased-seoul-mapo/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 10.881439208984375
|
18 |
+
|
19 |
+
f1_macro: 2.0884651199784053e-09
|
20 |
+
|
21 |
+
f1_micro: 5.5086301872934264e-05
|
22 |
+
|
23 |
+
f1_weighted: 6.068667007649333e-09
|
24 |
+
|
25 |
+
precision_macro: 1.0442900828992278e-09
|
26 |
+
|
27 |
+
precision_micro: 5.5086301872934264e-05
|
28 |
+
|
29 |
+
precision_weighted: 3.034500654036041e-09
|
30 |
+
|
31 |
+
recall_macro: 1.895734597156398e-05
|
32 |
+
|
33 |
+
recall_micro: 5.5086301872934264e-05
|
34 |
+
|
35 |
+
recall_weighted: 5.5086301872934264e-05
|
36 |
+
|
37 |
+
accuracy: 5.5086301872934264e-05
|
autotrain-data/dataset_dict.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"splits": ["train", "validation"]}
|
autotrain-data/train/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b76d5a1aa24ea9542c3754f1d4457dbbbb0d6e58cc79aa13e0cce907141d8ab
|
3 |
+
size 8271144
|
autotrain-data/train/dataset_info.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
autotrain-data/train/state.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "569b8763400540ba",
|
8 |
+
"_format_columns": [
|
9 |
+
"autotrain_text",
|
10 |
+
"autotrain_label"
|
11 |
+
],
|
12 |
+
"_format_kwargs": {},
|
13 |
+
"_format_type": null,
|
14 |
+
"_output_all_columns": false,
|
15 |
+
"_split": null
|
16 |
+
}
|
autotrain-data/validation/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b76d5a1aa24ea9542c3754f1d4457dbbbb0d6e58cc79aa13e0cce907141d8ab
|
3 |
+
size 8271144
|
autotrain-data/validation/dataset_info.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
autotrain-data/validation/state.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "569b8763400540ba",
|
8 |
+
"_format_columns": [
|
9 |
+
"autotrain_text",
|
10 |
+
"autotrain_label"
|
11 |
+
],
|
12 |
+
"_format_kwargs": {},
|
13 |
+
"_format_type": null,
|
14 |
+
"_output_all_columns": false,
|
15 |
+
"_split": null
|
16 |
+
}
|
checkpoint-20424/config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30bf199832255bf22ab2f4c359bfb505214667765c744ee2cd9a8e1f5770a2ea
|
3 |
+
size 10683194
|
checkpoint-20424/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68360b3d50798a2eac1a70f0600a4febac2f251cfc9afba03590c2a6ae28dea8
|
3 |
+
size 831708216
|
checkpoint-20424/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4409deed287097e9e83339f6758b5bf548d3dd87bd9d47c065ceab8c57e4e469
|
3 |
+
size 1663537402
|
checkpoint-20424/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:549cd76df73cadda6b6fc09b8c61f4b8d765a08797ab0e520843b2d26cb59430
|
3 |
+
size 14244
|
checkpoint-20424/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad99518938fa647ab0b4173e6e8716de2d3b659f55fd1664b87aaf18be688e2d
|
3 |
+
size 1064
|
checkpoint-20424/trainer_state.json
ADDED
@@ -0,0 +1,180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 10.881439208984375,
|
3 |
+
"best_model_checkpoint": "bert-multilingual-uncased-seoul-mapo\\checkpoint-20424",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 20424,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2,
|
13 |
+
"grad_norm": 4.823001861572266,
|
14 |
+
"learning_rate": 3.3186490455212925e-05,
|
15 |
+
"loss": 10.8897,
|
16 |
+
"step": 1361
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4,
|
20 |
+
"grad_norm": 10.075815200805664,
|
21 |
+
"learning_rate": 4.816658506066047e-05,
|
22 |
+
"loss": 10.9188,
|
23 |
+
"step": 2722
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6,
|
27 |
+
"grad_norm": 9.569664001464844,
|
28 |
+
"learning_rate": 4.446439257929384e-05,
|
29 |
+
"loss": 10.9979,
|
30 |
+
"step": 4083
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.8,
|
34 |
+
"grad_norm": 8.838366508483887,
|
35 |
+
"learning_rate": 4.076220009792721e-05,
|
36 |
+
"loss": 11.0794,
|
37 |
+
"step": 5444
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"grad_norm": 9.55294418334961,
|
42 |
+
"learning_rate": 3.706000761656058e-05,
|
43 |
+
"loss": 11.0159,
|
44 |
+
"step": 6805
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"eval_accuracy": 1.8362100624311422e-05,
|
49 |
+
"eval_f1_macro": 6.961806052611587e-10,
|
50 |
+
"eval_f1_micro": 1.8362100624311422e-05,
|
51 |
+
"eval_f1_weighted": 6.743210967228447e-10,
|
52 |
+
"eval_loss": 10.912298202514648,
|
53 |
+
"eval_precision_macro": 3.480966942997426e-10,
|
54 |
+
"eval_precision_micro": 1.8362100624311422e-05,
|
55 |
+
"eval_precision_weighted": 3.371667393373379e-10,
|
56 |
+
"eval_recall_macro": 1.895734597156398e-05,
|
57 |
+
"eval_recall_micro": 1.8362100624311422e-05,
|
58 |
+
"eval_recall_weighted": 1.8362100624311422e-05,
|
59 |
+
"eval_runtime": 5760.3648,
|
60 |
+
"eval_samples_per_second": 9.454,
|
61 |
+
"eval_steps_per_second": 0.591,
|
62 |
+
"step": 6808
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.2,
|
66 |
+
"grad_norm": 4.205029010772705,
|
67 |
+
"learning_rate": 3.3357815135193955e-05,
|
68 |
+
"loss": 10.918,
|
69 |
+
"step": 8166
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.4,
|
73 |
+
"grad_norm": 5.503857135772705,
|
74 |
+
"learning_rate": 2.9655622653827325e-05,
|
75 |
+
"loss": 10.907,
|
76 |
+
"step": 9527
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 1.6,
|
80 |
+
"grad_norm": 4.5869550704956055,
|
81 |
+
"learning_rate": 2.5953430172460695e-05,
|
82 |
+
"loss": 10.8973,
|
83 |
+
"step": 10888
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.8,
|
87 |
+
"grad_norm": 8.75169849395752,
|
88 |
+
"learning_rate": 2.2251237691094066e-05,
|
89 |
+
"loss": 10.896,
|
90 |
+
"step": 12249
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.0,
|
94 |
+
"grad_norm": 8.687349319458008,
|
95 |
+
"learning_rate": 1.8549045209727436e-05,
|
96 |
+
"loss": 10.9367,
|
97 |
+
"step": 13610
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.0,
|
101 |
+
"eval_accuracy": 0.0006426735218508997,
|
102 |
+
"eval_f1_macro": 2.435111878171352e-08,
|
103 |
+
"eval_f1_micro": 0.0006426735218508997,
|
104 |
+
"eval_f1_weighted": 8.255279664109179e-07,
|
105 |
+
"eval_loss": 10.890863418579102,
|
106 |
+
"eval_precision_macro": 1.218338430049099e-08,
|
107 |
+
"eval_precision_micro": 0.0006426735218508997,
|
108 |
+
"eval_precision_weighted": 4.1302925568823887e-07,
|
109 |
+
"eval_recall_macro": 1.895734597156398e-05,
|
110 |
+
"eval_recall_micro": 0.0006426735218508997,
|
111 |
+
"eval_recall_weighted": 0.0006426735218508997,
|
112 |
+
"eval_runtime": 229.7364,
|
113 |
+
"eval_samples_per_second": 237.054,
|
114 |
+
"eval_steps_per_second": 14.817,
|
115 |
+
"step": 13616
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 2.2,
|
119 |
+
"grad_norm": 5.189822673797607,
|
120 |
+
"learning_rate": 1.4846852728360808e-05,
|
121 |
+
"loss": 10.9037,
|
122 |
+
"step": 14971
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 2.4,
|
126 |
+
"grad_norm": 4.2194414138793945,
|
127 |
+
"learning_rate": 1.1147380447200914e-05,
|
128 |
+
"loss": 10.8914,
|
129 |
+
"step": 16332
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 2.6,
|
133 |
+
"grad_norm": 3.2576804161071777,
|
134 |
+
"learning_rate": 7.445187965834286e-06,
|
135 |
+
"loss": 10.8939,
|
136 |
+
"step": 17693
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 2.8,
|
140 |
+
"grad_norm": 3.3207333087921143,
|
141 |
+
"learning_rate": 3.7457156846743925e-06,
|
142 |
+
"loss": 10.8859,
|
143 |
+
"step": 19054
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 3.0,
|
147 |
+
"grad_norm": 4.7934651374816895,
|
148 |
+
"learning_rate": 5.440400413470432e-08,
|
149 |
+
"loss": 10.8979,
|
150 |
+
"step": 20415
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 3.0,
|
154 |
+
"eval_accuracy": 5.5086301872934264e-05,
|
155 |
+
"eval_f1_macro": 2.0884651199784053e-09,
|
156 |
+
"eval_f1_micro": 5.5086301872934264e-05,
|
157 |
+
"eval_f1_weighted": 6.068667007649333e-09,
|
158 |
+
"eval_loss": 10.881439208984375,
|
159 |
+
"eval_precision_macro": 1.0442900828992278e-09,
|
160 |
+
"eval_precision_micro": 5.5086301872934264e-05,
|
161 |
+
"eval_precision_weighted": 3.034500654036041e-09,
|
162 |
+
"eval_recall_macro": 1.895734597156398e-05,
|
163 |
+
"eval_recall_micro": 5.5086301872934264e-05,
|
164 |
+
"eval_recall_weighted": 5.5086301872934264e-05,
|
165 |
+
"eval_runtime": 229.8136,
|
166 |
+
"eval_samples_per_second": 236.975,
|
167 |
+
"eval_steps_per_second": 14.812,
|
168 |
+
"step": 20424
|
169 |
+
}
|
170 |
+
],
|
171 |
+
"logging_steps": 1361,
|
172 |
+
"max_steps": 20424,
|
173 |
+
"num_input_tokens_seen": 0,
|
174 |
+
"num_train_epochs": 3,
|
175 |
+
"save_steps": 500,
|
176 |
+
"total_flos": 1.583647415497728e+16,
|
177 |
+
"train_batch_size": 8,
|
178 |
+
"trial_name": null,
|
179 |
+
"trial_params": null
|
180 |
+
}
|
checkpoint-20424/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af067aa29cb53eba11342b2bbe220c7f4c9480b4c431468bf3f6d0bb25b0641c
|
3 |
+
size 4984
|
config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30bf199832255bf22ab2f4c359bfb505214667765c744ee2cd9a8e1f5770a2ea
|
3 |
+
size 10683194
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68360b3d50798a2eac1a70f0600a4febac2f251cfc9afba03590c2a6ae28dea8
|
3 |
+
size 831708216
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af067aa29cb53eba11342b2bbe220c7f4c9480b4c431468bf3f6d0bb25b0641c
|
3 |
+
size 4984
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "bert-multilingual-uncased-seoul-mapo/autotrain-data",
|
3 |
+
"model": "google-bert/bert-base-multilingual-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": "bert-multilingual-uncased-seoul-mapo",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"save_strategy": "epoch",
|
25 |
+
"push_to_hub": true,
|
26 |
+
"repo_id": "SungmoKim/bert-multilingual-uncased-seoul-mapo",
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"username": "SungmoKim",
|
29 |
+
"log": "none"
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|