Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +37 -0
- checkpoint-446/config.json +44 -0
- checkpoint-446/model.safetensors +3 -0
- checkpoint-446/optimizer.pt +3 -0
- checkpoint-446/rng_state.pth +3 -0
- checkpoint-446/scheduler.pt +3 -0
- checkpoint-446/trainer_state.json +337 -0
- checkpoint-446/training_args.bin +3 -0
- config.json +44 -0
- model.safetensors +3 -0
- runs/Apr30_06-44-49_r-nawincom-textclass2-hwsouds3-cf295-98bbt/events.out.tfevents.1714459490.r-nawincom-textclass2-hwsouds3-cf295-98bbt.62.0 +2 -2
- runs/Apr30_06-44-49_r-nawincom-textclass2-hwsouds3-cf295-98bbt/events.out.tfevents.1714459650.r-nawincom-textclass2-hwsouds3-cf295-98bbt.62.1 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
- training_params.json +28 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.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 |
+
- autotrain-7ejr4-3wbhb/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.34203216433525085
|
18 |
+
|
19 |
+
f1_macro: 0.9457020850649197
|
20 |
+
|
21 |
+
f1_micro: 0.946067415730337
|
22 |
+
|
23 |
+
f1_weighted: 0.9461015789750475
|
24 |
+
|
25 |
+
precision_macro: 0.9447370569809594
|
26 |
+
|
27 |
+
precision_micro: 0.946067415730337
|
28 |
+
|
29 |
+
precision_weighted: 0.9466487598452521
|
30 |
+
|
31 |
+
recall_macro: 0.9472065189712249
|
32 |
+
|
33 |
+
recall_micro: 0.946067415730337
|
34 |
+
|
35 |
+
recall_weighted: 0.946067415730337
|
36 |
+
|
37 |
+
accuracy: 0.946067415730337
|
checkpoint-446/config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "papluca/xlm-roberta-base-language-detection",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"XLMRobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "business",
|
16 |
+
"1": "entertainment",
|
17 |
+
"2": "politics",
|
18 |
+
"3": "sport",
|
19 |
+
"4": "tech"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"business": 0,
|
25 |
+
"entertainment": 1,
|
26 |
+
"politics": 2,
|
27 |
+
"sport": 3,
|
28 |
+
"tech": 4
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-05,
|
31 |
+
"max_position_embeddings": 514,
|
32 |
+
"model_type": "xlm-roberta",
|
33 |
+
"num_attention_heads": 12,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"output_past": true,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.40.1",
|
41 |
+
"type_vocab_size": 1,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 250002
|
44 |
+
}
|
checkpoint-446/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9314d9a470ad4dc010ff93505deb3ee739b2c2937042c4416dd0a01d90e37222
|
3 |
+
size 1112214236
|
checkpoint-446/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ddeff3b01c6e7e0ce4370df50b0170b722894b8224e22c470212ef51e4e680c
|
3 |
+
size 2224548090
|
checkpoint-446/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53baf86f8a96a1dd3cf8551790d356b7f8592e5ad0257eef9380a747a00379f6
|
3 |
+
size 14244
|
checkpoint-446/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4216d5b6dd557c6240c6a96b80fdf539ddaf40ac04a7e09efc71cbf5efda2d90
|
3 |
+
size 1064
|
checkpoint-446/trainer_state.json
ADDED
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.34203216433525085,
|
3 |
+
"best_model_checkpoint": "autotrain-7ejr4-3wbhb/checkpoint-446",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 446,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04932735426008968,
|
13 |
+
"grad_norm": 5.397119045257568,
|
14 |
+
"learning_rate": 8.208955223880597e-06,
|
15 |
+
"loss": 1.6001,
|
16 |
+
"step": 11
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09865470852017937,
|
20 |
+
"grad_norm": 10.270828247070312,
|
21 |
+
"learning_rate": 1.6417910447761194e-05,
|
22 |
+
"loss": 1.6421,
|
23 |
+
"step": 22
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.14798206278026907,
|
27 |
+
"grad_norm": 6.842929363250732,
|
28 |
+
"learning_rate": 2.4626865671641793e-05,
|
29 |
+
"loss": 1.5659,
|
30 |
+
"step": 33
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.19730941704035873,
|
34 |
+
"grad_norm": 14.523164749145508,
|
35 |
+
"learning_rate": 3.208955223880597e-05,
|
36 |
+
"loss": 1.2199,
|
37 |
+
"step": 44
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.24663677130044842,
|
41 |
+
"grad_norm": Infinity,
|
42 |
+
"learning_rate": 3.9552238805970146e-05,
|
43 |
+
"loss": 0.9104,
|
44 |
+
"step": 55
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.29596412556053814,
|
48 |
+
"grad_norm": Infinity,
|
49 |
+
"learning_rate": 4.7014925373134335e-05,
|
50 |
+
"loss": 0.6866,
|
51 |
+
"step": 66
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3452914798206278,
|
55 |
+
"grad_norm": 39.58903884887695,
|
56 |
+
"learning_rate": 4.941860465116279e-05,
|
57 |
+
"loss": 0.9257,
|
58 |
+
"step": 77
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.39461883408071746,
|
62 |
+
"grad_norm": 38.08815383911133,
|
63 |
+
"learning_rate": 4.8504983388704325e-05,
|
64 |
+
"loss": 0.5447,
|
65 |
+
"step": 88
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.4439461883408072,
|
69 |
+
"grad_norm": 32.093482971191406,
|
70 |
+
"learning_rate": 4.7674418604651164e-05,
|
71 |
+
"loss": 0.5951,
|
72 |
+
"step": 99
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.49327354260089684,
|
76 |
+
"grad_norm": 9.36325454711914,
|
77 |
+
"learning_rate": 4.684385382059801e-05,
|
78 |
+
"loss": 0.4972,
|
79 |
+
"step": 110
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.5426008968609866,
|
83 |
+
"grad_norm": 16.48912811279297,
|
84 |
+
"learning_rate": 4.593023255813954e-05,
|
85 |
+
"loss": 0.5117,
|
86 |
+
"step": 121
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5919282511210763,
|
90 |
+
"grad_norm": 15.17750072479248,
|
91 |
+
"learning_rate": 4.5016611295681064e-05,
|
92 |
+
"loss": 0.5249,
|
93 |
+
"step": 132
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.6412556053811659,
|
97 |
+
"grad_norm": 73.44496154785156,
|
98 |
+
"learning_rate": 4.410299003322259e-05,
|
99 |
+
"loss": 0.2932,
|
100 |
+
"step": 143
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6905829596412556,
|
104 |
+
"grad_norm": 7.012796878814697,
|
105 |
+
"learning_rate": 4.3189368770764125e-05,
|
106 |
+
"loss": 0.3703,
|
107 |
+
"step": 154
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.7399103139013453,
|
111 |
+
"grad_norm": 36.769142150878906,
|
112 |
+
"learning_rate": 4.227574750830565e-05,
|
113 |
+
"loss": 0.384,
|
114 |
+
"step": 165
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7892376681614349,
|
118 |
+
"grad_norm": 0.5750433206558228,
|
119 |
+
"learning_rate": 4.136212624584718e-05,
|
120 |
+
"loss": 0.2024,
|
121 |
+
"step": 176
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.8385650224215246,
|
125 |
+
"grad_norm": 0.8097955584526062,
|
126 |
+
"learning_rate": 4.0448504983388706e-05,
|
127 |
+
"loss": 0.2261,
|
128 |
+
"step": 187
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.8878923766816144,
|
132 |
+
"grad_norm": 0.3052847683429718,
|
133 |
+
"learning_rate": 3.953488372093023e-05,
|
134 |
+
"loss": 0.3784,
|
135 |
+
"step": 198
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.9372197309417041,
|
139 |
+
"grad_norm": 9.378923416137695,
|
140 |
+
"learning_rate": 3.862126245847176e-05,
|
141 |
+
"loss": 0.334,
|
142 |
+
"step": 209
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.9865470852017937,
|
146 |
+
"grad_norm": 57.845924377441406,
|
147 |
+
"learning_rate": 3.7707641196013294e-05,
|
148 |
+
"loss": 0.5124,
|
149 |
+
"step": 220
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.0,
|
153 |
+
"eval_accuracy": 0.8337078651685393,
|
154 |
+
"eval_f1_macro": 0.8277707222765114,
|
155 |
+
"eval_f1_micro": 0.8337078651685393,
|
156 |
+
"eval_f1_weighted": 0.8270484241051885,
|
157 |
+
"eval_loss": 0.6007972359657288,
|
158 |
+
"eval_precision_macro": 0.8743021944472813,
|
159 |
+
"eval_precision_micro": 0.8337078651685393,
|
160 |
+
"eval_precision_weighted": 0.8814664248669926,
|
161 |
+
"eval_recall_macro": 0.8408823529411764,
|
162 |
+
"eval_recall_micro": 0.8337078651685393,
|
163 |
+
"eval_recall_weighted": 0.8337078651685393,
|
164 |
+
"eval_runtime": 1.7336,
|
165 |
+
"eval_samples_per_second": 256.693,
|
166 |
+
"eval_steps_per_second": 16.151,
|
167 |
+
"step": 223
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.0358744394618835,
|
171 |
+
"grad_norm": 4.146377086639404,
|
172 |
+
"learning_rate": 3.679401993355482e-05,
|
173 |
+
"loss": 0.4657,
|
174 |
+
"step": 231
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.0852017937219731,
|
178 |
+
"grad_norm": 2.958444833755493,
|
179 |
+
"learning_rate": 3.588039867109635e-05,
|
180 |
+
"loss": 0.2262,
|
181 |
+
"step": 242
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.1345291479820627,
|
185 |
+
"grad_norm": 18.36431312561035,
|
186 |
+
"learning_rate": 3.4966777408637875e-05,
|
187 |
+
"loss": 0.2503,
|
188 |
+
"step": 253
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.1838565022421526,
|
192 |
+
"grad_norm": 0.3763713538646698,
|
193 |
+
"learning_rate": 3.40531561461794e-05,
|
194 |
+
"loss": 0.1309,
|
195 |
+
"step": 264
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.2331838565022422,
|
199 |
+
"grad_norm": 0.1498165726661682,
|
200 |
+
"learning_rate": 3.313953488372093e-05,
|
201 |
+
"loss": 0.1149,
|
202 |
+
"step": 275
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.2825112107623318,
|
206 |
+
"grad_norm": 0.13080233335494995,
|
207 |
+
"learning_rate": 3.222591362126246e-05,
|
208 |
+
"loss": 0.2224,
|
209 |
+
"step": 286
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.3318385650224216,
|
213 |
+
"grad_norm": 6.366682052612305,
|
214 |
+
"learning_rate": 3.131229235880399e-05,
|
215 |
+
"loss": 0.3254,
|
216 |
+
"step": 297
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.3811659192825112,
|
220 |
+
"grad_norm": 0.08186858147382736,
|
221 |
+
"learning_rate": 3.0398671096345517e-05,
|
222 |
+
"loss": 0.0981,
|
223 |
+
"step": 308
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.4304932735426008,
|
227 |
+
"grad_norm": 0.14895343780517578,
|
228 |
+
"learning_rate": 2.9485049833887047e-05,
|
229 |
+
"loss": 0.1536,
|
230 |
+
"step": 319
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.4798206278026906,
|
234 |
+
"grad_norm": 0.07964171469211578,
|
235 |
+
"learning_rate": 2.857142857142857e-05,
|
236 |
+
"loss": 0.0458,
|
237 |
+
"step": 330
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.5291479820627802,
|
241 |
+
"grad_norm": 0.16557298600673676,
|
242 |
+
"learning_rate": 2.76578073089701e-05,
|
243 |
+
"loss": 0.2189,
|
244 |
+
"step": 341
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.57847533632287,
|
248 |
+
"grad_norm": 13.367328643798828,
|
249 |
+
"learning_rate": 2.674418604651163e-05,
|
250 |
+
"loss": 0.2818,
|
251 |
+
"step": 352
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.6278026905829597,
|
255 |
+
"grad_norm": 0.042071498930454254,
|
256 |
+
"learning_rate": 2.591362126245847e-05,
|
257 |
+
"loss": 0.1282,
|
258 |
+
"step": 363
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.6771300448430493,
|
262 |
+
"grad_norm": 0.0784522220492363,
|
263 |
+
"learning_rate": 2.5e-05,
|
264 |
+
"loss": 0.2491,
|
265 |
+
"step": 374
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.726457399103139,
|
269 |
+
"grad_norm": 0.17997685074806213,
|
270 |
+
"learning_rate": 2.4086378737541528e-05,
|
271 |
+
"loss": 0.022,
|
272 |
+
"step": 385
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.7757847533632287,
|
276 |
+
"grad_norm": 36.073631286621094,
|
277 |
+
"learning_rate": 2.3172757475083055e-05,
|
278 |
+
"loss": 0.1468,
|
279 |
+
"step": 396
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.8251121076233185,
|
283 |
+
"grad_norm": 46.98909378051758,
|
284 |
+
"learning_rate": 2.2259136212624586e-05,
|
285 |
+
"loss": 0.2726,
|
286 |
+
"step": 407
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.8744394618834082,
|
290 |
+
"grad_norm": 0.6519285440444946,
|
291 |
+
"learning_rate": 2.1345514950166116e-05,
|
292 |
+
"loss": 0.0038,
|
293 |
+
"step": 418
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.9237668161434978,
|
297 |
+
"grad_norm": 29.345619201660156,
|
298 |
+
"learning_rate": 2.0431893687707643e-05,
|
299 |
+
"loss": 0.251,
|
300 |
+
"step": 429
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.9730941704035874,
|
304 |
+
"grad_norm": 0.05096792057156563,
|
305 |
+
"learning_rate": 1.951827242524917e-05,
|
306 |
+
"loss": 0.3514,
|
307 |
+
"step": 440
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 2.0,
|
311 |
+
"eval_accuracy": 0.946067415730337,
|
312 |
+
"eval_f1_macro": 0.9457020850649197,
|
313 |
+
"eval_f1_micro": 0.946067415730337,
|
314 |
+
"eval_f1_weighted": 0.9461015789750475,
|
315 |
+
"eval_loss": 0.34203216433525085,
|
316 |
+
"eval_precision_macro": 0.9447370569809594,
|
317 |
+
"eval_precision_micro": 0.946067415730337,
|
318 |
+
"eval_precision_weighted": 0.9466487598452521,
|
319 |
+
"eval_recall_macro": 0.9472065189712249,
|
320 |
+
"eval_recall_micro": 0.946067415730337,
|
321 |
+
"eval_recall_weighted": 0.946067415730337,
|
322 |
+
"eval_runtime": 1.7697,
|
323 |
+
"eval_samples_per_second": 251.457,
|
324 |
+
"eval_steps_per_second": 15.822,
|
325 |
+
"step": 446
|
326 |
+
}
|
327 |
+
],
|
328 |
+
"logging_steps": 11,
|
329 |
+
"max_steps": 669,
|
330 |
+
"num_input_tokens_seen": 0,
|
331 |
+
"num_train_epochs": 3,
|
332 |
+
"save_steps": 500,
|
333 |
+
"total_flos": 234175146792960.0,
|
334 |
+
"train_batch_size": 8,
|
335 |
+
"trial_name": null,
|
336 |
+
"trial_params": null
|
337 |
+
}
|
checkpoint-446/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dbb18bda7bd55a4f6a105f4c0cbfd62d9632c3a562cdbb4693af6112eb906d5
|
3 |
+
size 5048
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "papluca/xlm-roberta-base-language-detection",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"XLMRobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "business",
|
16 |
+
"1": "entertainment",
|
17 |
+
"2": "politics",
|
18 |
+
"3": "sport",
|
19 |
+
"4": "tech"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"business": 0,
|
25 |
+
"entertainment": 1,
|
26 |
+
"politics": 2,
|
27 |
+
"sport": 3,
|
28 |
+
"tech": 4
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-05,
|
31 |
+
"max_position_embeddings": 514,
|
32 |
+
"model_type": "xlm-roberta",
|
33 |
+
"num_attention_heads": 12,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"output_past": true,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.40.1",
|
41 |
+
"type_vocab_size": 1,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 250002
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9314d9a470ad4dc010ff93505deb3ee739b2c2937042c4416dd0a01d90e37222
|
3 |
+
size 1112214236
|
runs/Apr30_06-44-49_r-nawincom-textclass2-hwsouds3-cf295-98bbt/events.out.tfevents.1714459490.r-nawincom-textclass2-hwsouds3-cf295-98bbt.62.0
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:eb010ef1d1ffd68fad1883964ec5e072f72cc6c14bccf9e5b2805e0f74d38bc8
|
3 |
+
size 20591
|
runs/Apr30_06-44-49_r-nawincom-textclass2-hwsouds3-cf295-98bbt/events.out.tfevents.1714459650.r-nawincom-textclass2-hwsouds3-cf295-98bbt.62.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa0564add3d490875c3ac890e0a2c82a6dc4418ea671369301affd7347f382a6
|
3 |
+
size 921
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
|
3 |
+
size 17082999
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dbb18bda7bd55a4f6a105f4c0cbfd62d9632c3a562cdbb4693af6112eb906d5
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-7ejr4-3wbhb/autotrain-data",
|
3 |
+
"model": "papluca/xlm-roberta-base-language-detection",
|
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-7ejr4-3wbhb",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"evaluation_strategy": "epoch",
|
26 |
+
"username": "NawinCom",
|
27 |
+
"log": "tensorboard"
|
28 |
+
}
|