Hugging Face's logo

mariagrandury
/
bluesky-spanish-classifier

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mariagrandury commited on
Commit
d615e1f
·
verified ·
1 Parent(s): c35ca9d

Model save

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. logs/events.out.tfevents.1740153917.a2d653e866f9.226.1 +3 -0
  3. logs/events.out.tfevents.1740157409.a2d653e866f9.226.2 +3 -0
  4. model.safetensors +1 -1
  5. model_stats.json +337 -0
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.1812
19
- - Classification Report: {'ar': {'precision': 0.10526315789473684, 'recall': 0.08695652173913043, 'f1-score': 0.09523809523809523, 'support': 207.0}, 'cl': {'precision': 0.17346938775510204, 'recall': 0.19391634980988592, 'f1-score': 0.18312387791741472, 'support': 263.0}, 'co': {'precision': 0.06451612903225806, 'recall': 0.011695906432748537, 'f1-score': 0.019801980198019802, 'support': 171.0}, 'es': {'precision': 0.24783362218370883, 'recall': 0.4307228915662651, 'f1-score': 0.3146314631463146, 'support': 332.0}, 'mx': {'precision': 0.15086206896551724, 'recall': 0.1724137931034483, 'f1-score': 0.16091954022988506, 'support': 203.0}, 'pe': {'precision': 0.061946902654867256, 'recall': 0.043478260869565216, 'f1-score': 0.051094890510948905, 'support': 161.0}, 'pr': {'precision': 0.5, 'recall': 0.02, 'f1-score': 0.038461538461538464, 'support': 50.0}, 'uy': {'precision': 0.3181818181818182, 'recall': 0.06086956521739131, 'f1-score': 0.10218978102189781, 'support': 115.0}, 've': {'precision': 0.012195121951219513, 'recall': 0.045454545454545456, 'f1-score': 0.019230769230769232, 'support': 22.0}, 'accuracy': 0.17388451443569553, 'macro avg': {'precision': 0.18158535651324753, 'recall': 0.11838975935477558, 'f1-score': 0.10941021510609822, 'support': 1524.0}, 'weighted avg': {'precision': 0.1726919923848946, 'recall': 0.17388451443569553, 'f1-score': 0.151384890214964, 'support': 1524.0}}
20
 
21
  ## Model description
22
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Classification Report |
50
- |:-------------:|:------:|:----:|:---------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
51
- | 2.1638 | 0.0022 | 2 | 2.1812 | {'ar': {'precision': 0.10526315789473684, 'recall': 0.08695652173913043, 'f1-score': 0.09523809523809523, 'support': 207.0}, 'cl': {'precision': 0.17346938775510204, 'recall': 0.19391634980988592, 'f1-score': 0.18312387791741472, 'support': 263.0}, 'co': {'precision': 0.06451612903225806, 'recall': 0.011695906432748537, 'f1-score': 0.019801980198019802, 'support': 171.0}, 'es': {'precision': 0.24783362218370883, 'recall': 0.4307228915662651, 'f1-score': 0.3146314631463146, 'support': 332.0}, 'mx': {'precision': 0.15086206896551724, 'recall': 0.1724137931034483, 'f1-score': 0.16091954022988506, 'support': 203.0}, 'pe': {'precision': 0.061946902654867256, 'recall': 0.043478260869565216, 'f1-score': 0.051094890510948905, 'support': 161.0}, 'pr': {'precision': 0.5, 'recall': 0.02, 'f1-score': 0.038461538461538464, 'support': 50.0}, 'uy': {'precision': 0.3181818181818182, 'recall': 0.06086956521739131, 'f1-score': 0.10218978102189781, 'support': 115.0}, 've': {'precision': 0.012195121951219513, 'recall': 0.045454545454545456, 'f1-score': 0.019230769230769232, 'support': 22.0}, 'accuracy': 0.17388451443569553, 'macro avg': {'precision': 0.18158535651324753, 'recall': 0.11838975935477558, 'f1-score': 0.10941021510609822, 'support': 1524.0}, 'weighted avg': {'precision': 0.1726919923848946, 'recall': 0.17388451443569553, 'f1-score': 0.151384890214964, 'support': 1524.0}} |
52
 
53
 
54
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.2149
19
+ - Classification Report: {'ar': {'precision': 0.125, 'recall': 0.014492753623188406, 'f1-score': 0.025974025974025976, 'support': 207.0}, 'cl': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 263.0}, 'co': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 171.0}, 'es': {'precision': 0.6666666666666666, 'recall': 0.006024096385542169, 'f1-score': 0.011940298507462687, 'support': 332.0}, 'mx': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 203.0}, 'pe': {'precision': 0.03333333333333333, 'recall': 0.006211180124223602, 'f1-score': 0.010471204188481676, 'support': 161.0}, 'pr': {'precision': 0.09401709401709402, 'recall': 0.22, 'f1-score': 0.1317365269461078, 'support': 50.0}, 'uy': {'precision': 0.07073715562174236, 'recall': 0.8260869565217391, 'f1-score': 0.13031550068587106, 'support': 115.0}, 've': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 22.0}, 'accuracy': 0.07349081364829396, 'macro avg': {'precision': 0.10997269440431515, 'recall': 0.1192016651838548, 'f1-score': 0.03449306181132769, 'support': 1524.0}, 'weighted avg': {'precision': 0.17415395511637471, 'recall': 0.07349081364829396, 'f1-score': 0.021390928662484977, 'support': 1524.0}}
20
 
21
  ## Model description
22
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Classification Report |
50
+ |:-------------:|:------:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
51
+ | 2.2248 | 0.0022 | 2 | 2.2149 | {'ar': {'precision': 0.125, 'recall': 0.014492753623188406, 'f1-score': 0.025974025974025976, 'support': 207.0}, 'cl': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 263.0}, 'co': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 171.0}, 'es': {'precision': 0.6666666666666666, 'recall': 0.006024096385542169, 'f1-score': 0.011940298507462687, 'support': 332.0}, 'mx': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 203.0}, 'pe': {'precision': 0.03333333333333333, 'recall': 0.006211180124223602, 'f1-score': 0.010471204188481676, 'support': 161.0}, 'pr': {'precision': 0.09401709401709402, 'recall': 0.22, 'f1-score': 0.1317365269461078, 'support': 50.0}, 'uy': {'precision': 0.07073715562174236, 'recall': 0.8260869565217391, 'f1-score': 0.13031550068587106, 'support': 115.0}, 've': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 22.0}, 'accuracy': 0.07349081364829396, 'macro avg': {'precision': 0.10997269440431515, 'recall': 0.1192016651838548, 'f1-score': 0.03449306181132769, 'support': 1524.0}, 'weighted avg': {'precision': 0.17415395511637471, 'recall': 0.07349081364829396, 'f1-score': 0.021390928662484977, 'support': 1524.0}} |
52
 
53
 
54
  ### Framework versions
logs/events.out.tfevents.1740153917.a2d653e866f9.226.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c9ef810960f8d264ed0fee8f36dc0b93ed92857586335e4a82806b89f24990
3
+ size 354
logs/events.out.tfevents.1740157409.a2d653e866f9.226.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3bb36e9610814a3402076559002106e036a12ab7db6c82ea90aaddcdf2f44a1
3
+ size 6355
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a59e6079206454140cd9de2a558ebfe6c234d41668e5122b99f4a63e3862ff46
3
  size 269328660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9ad0f28c73e32d964399d0a61f45d861c8a1af2235599dd7b8c5d38517ce4a
3
  size 269328660
model_stats.json ADDED
@@ -0,0 +1,337 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "splits": {
4
+ "train": {
5
+ "num_examples": 3553,
6
+ "features": [
7
+ "author",
8
+ "country",
9
+ "post_text",
10
+ "created_at",
11
+ "likes",
12
+ "quotes",
13
+ "replies",
14
+ "reposts",
15
+ "post_id",
16
+ "lang",
17
+ "tags",
18
+ "image_links",
19
+ "profile_info",
20
+ "processed_text",
21
+ "__index_level_0__"
22
+ ],
23
+ "first_example": {
24
+ "author": "apalet.bsky.social",
25
+ "country": "cl",
26
+ "post_text": "Me lloran los ojos sin pedir permiso ni razón.",
27
+ "created_at": "2024-12-31T01:15:04.751Z",
28
+ "likes": 8,
29
+ "quotes": 0,
30
+ "replies": 1,
31
+ "reposts": 0,
32
+ "post_id": "at://did:plc:y4bvfcu7wrx7jlyjg6qglqzl/app.bsky.feed.post/3lekuofg3xk2v",
33
+ "lang": "es",
34
+ "tags": "",
35
+ "image_links": "",
36
+ "profile_info": {
37
+ "description": "Leo y olvido \nwww.laurel.cl\nhttps://revistadossier.udp.cl",
38
+ "display_name": "Andrea Palet",
39
+ "feed_uri": null,
40
+ "followers_count": 1355,
41
+ "follows_count": 304,
42
+ "indexed_at": "2024-11-30T20:22:38.048Z",
43
+ "posts_count": 515
44
+ },
45
+ "processed_text": "lloran ojos pedir permiso razón",
46
+ "__index_level_0__": 4653
47
+ },
48
+ "country_distribution": {
49
+ "ar": {
50
+ "count": 483,
51
+ "percentage": 13.594145792288206
52
+ },
53
+ "cl": {
54
+ "count": 614,
55
+ "percentage": 17.28117084154236
56
+ },
57
+ "co": {
58
+ "count": 399,
59
+ "percentage": 11.229946524064172
60
+ },
61
+ "es": {
62
+ "count": 774,
63
+ "percentage": 21.784407542921475
64
+ },
65
+ "mx": {
66
+ "count": 473,
67
+ "percentage": 13.312693498452013
68
+ },
69
+ "pe": {
70
+ "count": 376,
71
+ "percentage": 10.582606248240923
72
+ },
73
+ "pr": {
74
+ "count": 117,
75
+ "percentage": 3.2929918378834784
76
+ },
77
+ "uy": {
78
+ "count": 267,
79
+ "percentage": 7.5147762454264
80
+ },
81
+ "ve": {
82
+ "count": 50,
83
+ "percentage": 1.407261469180974
84
+ }
85
+ }
86
+ },
87
+ "test": {
88
+ "num_examples": 1524,
89
+ "features": [
90
+ "author",
91
+ "country",
92
+ "post_text",
93
+ "created_at",
94
+ "likes",
95
+ "quotes",
96
+ "replies",
97
+ "reposts",
98
+ "post_id",
99
+ "lang",
100
+ "tags",
101
+ "image_links",
102
+ "profile_info",
103
+ "processed_text",
104
+ "__index_level_0__"
105
+ ],
106
+ "first_example": {
107
+ "author": "rpalomino.bsky.social",
108
+ "country": "pe",
109
+ "post_text": "Dos libros que he estado esperando leer hace mucho.",
110
+ "created_at": "2024-12-25T16:32:48.934Z",
111
+ "likes": 2,
112
+ "quotes": 0,
113
+ "replies": 1,
114
+ "reposts": 0,
115
+ "post_id": "at://did:plc:65xzu4se42blbypbgmki3xxv/app.bsky.feed.post/3le5f5vxtmc2h",
116
+ "lang": "es",
117
+ "tags": "",
118
+ "image_links": "",
119
+ "profile_info": {
120
+ "description": "Literatura y sociedad.",
121
+ "display_name": "Roy Palomino",
122
+ "feed_uri": null,
123
+ "followers_count": 174,
124
+ "follows_count": 283,
125
+ "indexed_at": "2024-11-25T05:12:19.445Z",
126
+ "posts_count": 90
127
+ },
128
+ "processed_text": "libros esperando leer",
129
+ "__index_level_0__": 3477
130
+ },
131
+ "country_distribution": {
132
+ "ar": {
133
+ "count": 207,
134
+ "percentage": 13.582677165354331
135
+ },
136
+ "cl": {
137
+ "count": 263,
138
+ "percentage": 17.25721784776903
139
+ },
140
+ "co": {
141
+ "count": 171,
142
+ "percentage": 11.220472440944881
143
+ },
144
+ "es": {
145
+ "count": 332,
146
+ "percentage": 21.784776902887142
147
+ },
148
+ "mx": {
149
+ "count": 203,
150
+ "percentage": 13.32020997375328
151
+ },
152
+ "pe": {
153
+ "count": 161,
154
+ "percentage": 10.564304461942257
155
+ },
156
+ "pr": {
157
+ "count": 50,
158
+ "percentage": 3.2808398950131235
159
+ },
160
+ "uy": {
161
+ "count": 115,
162
+ "percentage": 7.545931758530183
163
+ },
164
+ "ve": {
165
+ "count": 22,
166
+ "percentage": 1.4435695538057742
167
+ }
168
+ }
169
+ }
170
+ },
171
+ "processed": {
172
+ "train_examples": 3553,
173
+ "test_examples": 1524
174
+ }
175
+ },
176
+ "model": {
177
+ "name": "dccuchile/distilbert-base-spanish-uncased",
178
+ "num_parameters": 67329033,
179
+ "config": {
180
+ "learning_rate": 2e-05,
181
+ "batch_size": 4,
182
+ "epochs": 1,
183
+ "max_length": 32
184
+ },
185
+ "hub_url": "https://huggingface.co/None/bluesky-spanish-classifier"
186
+ },
187
+ "training": {
188
+ "runtime_seconds": 97.8884,
189
+ "loss": 2.1454918384552,
190
+ "steps_per_second": 0.02
191
+ },
192
+ "evaluation": {
193
+ "ar": {
194
+ "precision": 0.10526315789473684,
195
+ "recall": 0.08695652173913043,
196
+ "f1-score": 0.09523809523809523,
197
+ "support": 207.0
198
+ },
199
+ "cl": {
200
+ "precision": 0.17346938775510204,
201
+ "recall": 0.19391634980988592,
202
+ "f1-score": 0.18312387791741472,
203
+ "support": 263.0
204
+ },
205
+ "co": {
206
+ "precision": 0.06451612903225806,
207
+ "recall": 0.011695906432748537,
208
+ "f1-score": 0.019801980198019802,
209
+ "support": 171.0
210
+ },
211
+ "es": {
212
+ "precision": 0.24783362218370883,
213
+ "recall": 0.4307228915662651,
214
+ "f1-score": 0.3146314631463146,
215
+ "support": 332.0
216
+ },
217
+ "mx": {
218
+ "precision": 0.15086206896551724,
219
+ "recall": 0.1724137931034483,
220
+ "f1-score": 0.16091954022988506,
221
+ "support": 203.0
222
+ },
223
+ "pe": {
224
+ "precision": 0.061946902654867256,
225
+ "recall": 0.043478260869565216,
226
+ "f1-score": 0.051094890510948905,
227
+ "support": 161.0
228
+ },
229
+ "pr": {
230
+ "precision": 0.5,
231
+ "recall": 0.02,
232
+ "f1-score": 0.038461538461538464,
233
+ "support": 50.0
234
+ },
235
+ "uy": {
236
+ "precision": 0.3181818181818182,
237
+ "recall": 0.06086956521739131,
238
+ "f1-score": 0.10218978102189781,
239
+ "support": 115.0
240
+ },
241
+ "ve": {
242
+ "precision": 0.012195121951219513,
243
+ "recall": 0.045454545454545456,
244
+ "f1-score": 0.019230769230769232,
245
+ "support": 22.0
246
+ },
247
+ "accuracy": 0.17388451443569553,
248
+ "macro avg": {
249
+ "precision": 0.18158535651324753,
250
+ "recall": 0.11838975935477558,
251
+ "f1-score": 0.10941021510609822,
252
+ "support": 1524.0
253
+ },
254
+ "weighted avg": {
255
+ "precision": 0.1726919923848946,
256
+ "recall": 0.17388451443569553,
257
+ "f1-score": 0.151384890214964,
258
+ "support": 1524.0
259
+ },
260
+ "final": {
261
+ "eval_loss": 2.181152582168579,
262
+ "eval_classification_report": {
263
+ "ar": {
264
+ "precision": 0.10526315789473684,
265
+ "recall": 0.08695652173913043,
266
+ "f1-score": 0.09523809523809523,
267
+ "support": 207.0
268
+ },
269
+ "cl": {
270
+ "precision": 0.17346938775510204,
271
+ "recall": 0.19391634980988592,
272
+ "f1-score": 0.18312387791741472,
273
+ "support": 263.0
274
+ },
275
+ "co": {
276
+ "precision": 0.06451612903225806,
277
+ "recall": 0.011695906432748537,
278
+ "f1-score": 0.019801980198019802,
279
+ "support": 171.0
280
+ },
281
+ "es": {
282
+ "precision": 0.24783362218370883,
283
+ "recall": 0.4307228915662651,
284
+ "f1-score": 0.3146314631463146,
285
+ "support": 332.0
286
+ },
287
+ "mx": {
288
+ "precision": 0.15086206896551724,
289
+ "recall": 0.1724137931034483,
290
+ "f1-score": 0.16091954022988506,
291
+ "support": 203.0
292
+ },
293
+ "pe": {
294
+ "precision": 0.061946902654867256,
295
+ "recall": 0.043478260869565216,
296
+ "f1-score": 0.051094890510948905,
297
+ "support": 161.0
298
+ },
299
+ "pr": {
300
+ "precision": 0.5,
301
+ "recall": 0.02,
302
+ "f1-score": 0.038461538461538464,
303
+ "support": 50.0
304
+ },
305
+ "uy": {
306
+ "precision": 0.3181818181818182,
307
+ "recall": 0.06086956521739131,
308
+ "f1-score": 0.10218978102189781,
309
+ "support": 115.0
310
+ },
311
+ "ve": {
312
+ "precision": 0.012195121951219513,
313
+ "recall": 0.045454545454545456,
314
+ "f1-score": 0.019230769230769232,
315
+ "support": 22.0
316
+ },
317
+ "accuracy": 0.17388451443569553,
318
+ "macro avg": {
319
+ "precision": 0.18158535651324753,
320
+ "recall": 0.11838975935477558,
321
+ "f1-score": 0.10941021510609822,
322
+ "support": 1524.0
323
+ },
324
+ "weighted avg": {
325
+ "precision": 0.1726919923848946,
326
+ "recall": 0.17388451443569553,
327
+ "f1-score": 0.151384890214964,
328
+ "support": 1524.0
329
+ }
330
+ },
331
+ "eval_runtime": 97.6642,
332
+ "eval_samples_per_second": 15.604,
333
+ "eval_steps_per_second": 3.901,
334
+ "epoch": 0.0022497187851518562
335
+ }
336
+ }
337
+ }