Hugging Face's logo

luukschmitz
/
GeoBERT

Text Classification
Transformers
TensorBoard
Safetensors
bert
Trained with AutoTrain
text-embeddings-inference
Model card Files
xet
 Metrics Community
luukschmitz commited on
Commit
b3563a4
·
verified ·
1 Parent(s): a9f8e9e

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. README.md +37 -0
  2. checkpoint-500/config.json +40 -0
  3. checkpoint-500/model.safetensors +3 -0
  4. checkpoint-500/optimizer.pt +3 -0
  5. checkpoint-500/rng_state.pth +3 -0
  6. checkpoint-500/scheduler.pt +3 -0
  7. checkpoint-500/trainer_state.json +372 -0
  8. checkpoint-500/training_args.bin +3 -0
  9. config.json +40 -0
  10. model.safetensors +3 -0
  11. runs/Apr09_19-48-10_r-luukschmitz-geo-bert-x404zocc-de95c-iykfq/events.out.tfevents.1712692090.r-luukschmitz-geo-bert-x404zocc-de95c-iykfq.230.0 +2 -2
  12. runs/Apr09_19-48-10_r-luukschmitz-geo-bert-x404zocc-de95c-iykfq/events.out.tfevents.1712692442.r-luukschmitz-geo-bert-x404zocc-de95c-iykfq.230.1 +3 -0
  13. special_tokens_map.json +7 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +57 -0
  16. training_args.bin +3 -0
  17. training_params.json +30 -0
  18. vocab.txt +0 -0
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
+ - GeoBERT/autotrain-data
10
+ ---
11
+
12
+ # Model Trained Using AutoTrain
13
+
14
+ - Problem type: Text Classification
15
+
16
+ ## Validation Metrics
17
+ loss: 0.9093852639198303
18
+
19
+ f1_macro: 0.5823605917694434
20
+
21
+ f1_micro: 0.6589958158995816
22
+
23
+ f1_weighted: 0.6565370798157575
24
+
25
+ precision_macro: 0.6115906152670858
26
+
27
+ precision_micro: 0.6589958158995816
28
+
29
+ precision_weighted: 0.6611483212824585
30
+
31
+ recall_macro: 0.5656902456694988
32
+
33
+ recall_micro: 0.6589958158995816
34
+
35
+ recall_weighted: 0.6589958158995816
36
+
37
+ accuracy: 0.6589958158995816
checkpoint-500/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ProsusAI/finbert",
3
+ "_num_labels": 4,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": 0,
15
+ "1": 1,
16
+ "2": 2,
17
+ "3": 3
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "0": 0,
23
+ "1": 1,
24
+ "2": 2,
25
+ "3": 3
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.39.3",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e875df351c5a349c3b83d3813266d32e465f8601981d1b5bfefaa09d639f73
3
+ size 437964800
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd6efad6786bb4fac344d21fbc7b659a5e5c3dc5f5e6c4683b5851f486e6f1c
3
+ size 876050682
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce61854aa178345c5f2a1188e4707e024f8c546f2fbe4520a3ad71282719c7f0
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3a1573a20060d1fc6831d62c6fe7bb6c9ac17df17961279540c2632ff6fd4c
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9093852639198303,
3
+ "best_model_checkpoint": "GeoBERT/checkpoint-500",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "grad_norm": 9.578972816467285,
14
+ "learning_rate": 4.4e-06,
15
+ "loss": 1.3411,
16
+ "step": 11
17
+ },
18
+ {
19
+ "epoch": 0.09,
20
+ "grad_norm": 10.498757362365723,
21
+ "learning_rate": 8.8e-06,
22
+ "loss": 1.2504,
23
+ "step": 22
24
+ },
25
+ {
26
+ "epoch": 0.13,
27
+ "grad_norm": 6.937590599060059,
28
+ "learning_rate": 1.32e-05,
29
+ "loss": 1.234,
30
+ "step": 33
31
+ },
32
+ {
33
+ "epoch": 0.18,
34
+ "grad_norm": 4.935857772827148,
35
+ "learning_rate": 1.76e-05,
36
+ "loss": 1.1156,
37
+ "step": 44
38
+ },
39
+ {
40
+ "epoch": 0.22,
41
+ "grad_norm": 8.856083869934082,
42
+ "learning_rate": 2.2000000000000003e-05,
43
+ "loss": 0.9942,
44
+ "step": 55
45
+ },
46
+ {
47
+ "epoch": 0.26,
48
+ "grad_norm": 7.843554973602295,
49
+ "learning_rate": 2.64e-05,
50
+ "loss": 0.9665,
51
+ "step": 66
52
+ },
53
+ {
54
+ "epoch": 0.31,
55
+ "grad_norm": 7.1852126121521,
56
+ "learning_rate": 3.08e-05,
57
+ "loss": 1.1064,
58
+ "step": 77
59
+ },
60
+ {
61
+ "epoch": 0.35,
62
+ "grad_norm": 11.667104721069336,
63
+ "learning_rate": 3.52e-05,
64
+ "loss": 1.1114,
65
+ "step": 88
66
+ },
67
+ {
68
+ "epoch": 0.4,
69
+ "grad_norm": 10.513388633728027,
70
+ "learning_rate": 3.960000000000001e-05,
71
+ "loss": 0.9571,
72
+ "step": 99
73
+ },
74
+ {
75
+ "epoch": 0.44,
76
+ "grad_norm": 9.239156723022461,
77
+ "learning_rate": 4.4000000000000006e-05,
78
+ "loss": 0.93,
79
+ "step": 110
80
+ },
81
+ {
82
+ "epoch": 0.48,
83
+ "grad_norm": 6.3955302238464355,
84
+ "learning_rate": 4.8e-05,
85
+ "loss": 0.9277,
86
+ "step": 121
87
+ },
88
+ {
89
+ "epoch": 0.53,
90
+ "grad_norm": 7.602996826171875,
91
+ "learning_rate": 4.973333333333334e-05,
92
+ "loss": 0.9696,
93
+ "step": 132
94
+ },
95
+ {
96
+ "epoch": 0.57,
97
+ "grad_norm": 6.260980129241943,
98
+ "learning_rate": 4.924444444444445e-05,
99
+ "loss": 0.9792,
100
+ "step": 143
101
+ },
102
+ {
103
+ "epoch": 0.62,
104
+ "grad_norm": 12.462403297424316,
105
+ "learning_rate": 4.875555555555556e-05,
106
+ "loss": 1.1474,
107
+ "step": 154
108
+ },
109
+ {
110
+ "epoch": 0.66,
111
+ "grad_norm": 11.24273681640625,
112
+ "learning_rate": 4.826666666666667e-05,
113
+ "loss": 1.0853,
114
+ "step": 165
115
+ },
116
+ {
117
+ "epoch": 0.7,
118
+ "grad_norm": 5.870580673217773,
119
+ "learning_rate": 4.7777777777777784e-05,
120
+ "loss": 1.0063,
121
+ "step": 176
122
+ },
123
+ {
124
+ "epoch": 0.75,
125
+ "grad_norm": 7.315596580505371,
126
+ "learning_rate": 4.728888888888889e-05,
127
+ "loss": 0.8158,
128
+ "step": 187
129
+ },
130
+ {
131
+ "epoch": 0.79,
132
+ "grad_norm": 9.08304214477539,
133
+ "learning_rate": 4.6800000000000006e-05,
134
+ "loss": 0.8146,
135
+ "step": 198
136
+ },
137
+ {
138
+ "epoch": 0.84,
139
+ "grad_norm": 7.242616176605225,
140
+ "learning_rate": 4.6311111111111113e-05,
141
+ "loss": 0.881,
142
+ "step": 209
143
+ },
144
+ {
145
+ "epoch": 0.88,
146
+ "grad_norm": 6.810551643371582,
147
+ "learning_rate": 4.582222222222222e-05,
148
+ "loss": 1.02,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 0.92,
153
+ "grad_norm": 9.252344131469727,
154
+ "learning_rate": 4.5333333333333335e-05,
155
+ "loss": 0.8745,
156
+ "step": 231
157
+ },
158
+ {
159
+ "epoch": 0.97,
160
+ "grad_norm": 5.250942707061768,
161
+ "learning_rate": 4.484444444444444e-05,
162
+ "loss": 0.8428,
163
+ "step": 242
164
+ },
165
+ {
166
+ "epoch": 1.0,
167
+ "eval_accuracy": 0.5794979079497908,
168
+ "eval_f1_macro": 0.3207391363205631,
169
+ "eval_f1_micro": 0.5794979079497908,
170
+ "eval_f1_weighted": 0.5288849063689292,
171
+ "eval_loss": 1.0058727264404297,
172
+ "eval_precision_macro": 0.30283025619006726,
173
+ "eval_precision_micro": 0.5794979079497908,
174
+ "eval_precision_weighted": 0.5213967302096602,
175
+ "eval_recall_macro": 0.37342191224507815,
176
+ "eval_recall_micro": 0.5794979079497908,
177
+ "eval_recall_weighted": 0.5794979079497908,
178
+ "eval_runtime": 6.8009,
179
+ "eval_samples_per_second": 70.284,
180
+ "eval_steps_per_second": 4.411,
181
+ "step": 250
182
+ },
183
+ {
184
+ "epoch": 1.01,
185
+ "grad_norm": 8.098525047302246,
186
+ "learning_rate": 4.435555555555556e-05,
187
+ "loss": 0.8954,
188
+ "step": 253
189
+ },
190
+ {
191
+ "epoch": 1.06,
192
+ "grad_norm": 8.491247177124023,
193
+ "learning_rate": 4.3866666666666665e-05,
194
+ "loss": 0.6923,
195
+ "step": 264
196
+ },
197
+ {
198
+ "epoch": 1.1,
199
+ "grad_norm": 8.242985725402832,
200
+ "learning_rate": 4.337777777777778e-05,
201
+ "loss": 0.7433,
202
+ "step": 275
203
+ },
204
+ {
205
+ "epoch": 1.14,
206
+ "grad_norm": 9.606861114501953,
207
+ "learning_rate": 4.2888888888888886e-05,
208
+ "loss": 0.7633,
209
+ "step": 286
210
+ },
211
+ {
212
+ "epoch": 1.19,
213
+ "grad_norm": 4.706633567810059,
214
+ "learning_rate": 4.24e-05,
215
+ "loss": 0.6287,
216
+ "step": 297
217
+ },
218
+ {
219
+ "epoch": 1.23,
220
+ "grad_norm": 16.51137351989746,
221
+ "learning_rate": 4.1911111111111115e-05,
222
+ "loss": 0.6284,
223
+ "step": 308
224
+ },
225
+ {
226
+ "epoch": 1.28,
227
+ "grad_norm": 13.114934921264648,
228
+ "learning_rate": 4.142222222222222e-05,
229
+ "loss": 0.8798,
230
+ "step": 319
231
+ },
232
+ {
233
+ "epoch": 1.32,
234
+ "grad_norm": 10.896364212036133,
235
+ "learning_rate": 4.093333333333334e-05,
236
+ "loss": 0.6527,
237
+ "step": 330
238
+ },
239
+ {
240
+ "epoch": 1.36,
241
+ "grad_norm": 7.2867913246154785,
242
+ "learning_rate": 4.0444444444444444e-05,
243
+ "loss": 0.5512,
244
+ "step": 341
245
+ },
246
+ {
247
+ "epoch": 1.41,
248
+ "grad_norm": 6.902933597564697,
249
+ "learning_rate": 3.995555555555556e-05,
250
+ "loss": 0.7718,
251
+ "step": 352
252
+ },
253
+ {
254
+ "epoch": 1.45,
255
+ "grad_norm": 6.432639122009277,
256
+ "learning_rate": 3.9466666666666666e-05,
257
+ "loss": 0.5573,
258
+ "step": 363
259
+ },
260
+ {
261
+ "epoch": 1.5,
262
+ "grad_norm": 7.4120073318481445,
263
+ "learning_rate": 3.897777777777778e-05,
264
+ "loss": 0.6316,
265
+ "step": 374
266
+ },
267
+ {
268
+ "epoch": 1.54,
269
+ "grad_norm": 4.322595596313477,
270
+ "learning_rate": 3.848888888888889e-05,
271
+ "loss": 0.6219,
272
+ "step": 385
273
+ },
274
+ {
275
+ "epoch": 1.58,
276
+ "grad_norm": 5.752494812011719,
277
+ "learning_rate": 3.8e-05,
278
+ "loss": 0.5568,
279
+ "step": 396
280
+ },
281
+ {
282
+ "epoch": 1.63,
283
+ "grad_norm": 13.906458854675293,
284
+ "learning_rate": 3.7511111111111116e-05,
285
+ "loss": 0.7011,
286
+ "step": 407
287
+ },
288
+ {
289
+ "epoch": 1.67,
290
+ "grad_norm": 1.0408498048782349,
291
+ "learning_rate": 3.7022222222222224e-05,
292
+ "loss": 0.3148,
293
+ "step": 418
294
+ },
295
+ {
296
+ "epoch": 1.72,
297
+ "grad_norm": 9.536336898803711,
298
+ "learning_rate": 3.653333333333334e-05,
299
+ "loss": 0.7209,
300
+ "step": 429
301
+ },
302
+ {
303
+ "epoch": 1.76,
304
+ "grad_norm": 4.775065898895264,
305
+ "learning_rate": 3.6044444444444446e-05,
306
+ "loss": 0.637,
307
+ "step": 440
308
+ },
309
+ {
310
+ "epoch": 1.8,
311
+ "grad_norm": 16.23617172241211,
312
+ "learning_rate": 3.555555555555556e-05,
313
+ "loss": 0.6103,
314
+ "step": 451
315
+ },
316
+ {
317
+ "epoch": 1.85,
318
+ "grad_norm": 15.569254875183105,
319
+ "learning_rate": 3.506666666666667e-05,
320
+ "loss": 0.5131,
321
+ "step": 462
322
+ },
323
+ {
324
+ "epoch": 1.89,
325
+ "grad_norm": 11.499606132507324,
326
+ "learning_rate": 3.457777777777778e-05,
327
+ "loss": 0.5525,
328
+ "step": 473
329
+ },
330
+ {
331
+ "epoch": 1.94,
332
+ "grad_norm": 8.275940895080566,
333
+ "learning_rate": 3.408888888888889e-05,
334
+ "loss": 0.5643,
335
+ "step": 484
336
+ },
337
+ {
338
+ "epoch": 1.98,
339
+ "grad_norm": 5.744302272796631,
340
+ "learning_rate": 3.3600000000000004e-05,
341
+ "loss": 0.4863,
342
+ "step": 495
343
+ },
344
+ {
345
+ "epoch": 2.0,
346
+ "eval_accuracy": 0.6589958158995816,
347
+ "eval_f1_macro": 0.5823605917694434,
348
+ "eval_f1_micro": 0.6589958158995816,
349
+ "eval_f1_weighted": 0.6565370798157575,
350
+ "eval_loss": 0.9093852639198303,
351
+ "eval_precision_macro": 0.6115906152670858,
352
+ "eval_precision_micro": 0.6589958158995816,
353
+ "eval_precision_weighted": 0.6611483212824585,
354
+ "eval_recall_macro": 0.5656902456694988,
355
+ "eval_recall_micro": 0.6589958158995816,
356
+ "eval_recall_weighted": 0.6589958158995816,
357
+ "eval_runtime": 6.8834,
358
+ "eval_samples_per_second": 69.442,
359
+ "eval_steps_per_second": 4.358,
360
+ "step": 500
361
+ }
362
+ ],
363
+ "logging_steps": 11,
364
+ "max_steps": 1250,
365
+ "num_input_tokens_seen": 0,
366
+ "num_train_epochs": 5,
367
+ "save_steps": 500,
368
+ "total_flos": 1051936888823808.0,
369
+ "train_batch_size": 8,
370
+ "trial_name": null,
371
+ "trial_params": null
372
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1256c066f15f4b5447972871596b51de2eeddb61fd83d38b3933c9a257b3bb14
3
+ size 4920
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ProsusAI/finbert",
3
+ "_num_labels": 4,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": 0,
15
+ "1": 1,
16
+ "2": 2,
17
+ "3": 3
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "0": 0,
23
+ "1": 1,
24
+ "2": 2,
25
+ "3": 3
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.39.3",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e875df351c5a349c3b83d3813266d32e465f8601981d1b5bfefaa09d639f73
3
+ size 437964800
runs/Apr09_19-48-10_r-luukschmitz-geo-bert-x404zocc-de95c-iykfq/events.out.tfevents.1712692090.r-luukschmitz-geo-bert-x404zocc-de95c-iykfq.230.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a15022f009ac822f9b42efa92a3893e943d2cb2304a3ff5a63ddf2477f08359e
3
- size 31677
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7ef0d15d999d766108ac73412bc91954db2f7d0251b21b4ed57ec6c2a94187
3
+ size 33075
runs/Apr09_19-48-10_r-luukschmitz-geo-bert-x404zocc-de95c-iykfq/events.out.tfevents.1712692442.r-luukschmitz-geo-bert-x404zocc-de95c-iykfq.230.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa5d919cfe76cecb1ee03ad510ce6f0a5f606d84787383db523153aa313e7c7b
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
+ "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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
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 sha256:1256c066f15f4b5447972871596b51de2eeddb61fd83d38b3933c9a257b3bb14
3
+ size 4920
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "GeoBERT/autotrain-data",
3
+ "model": "ProsusAI/finbert",
4
+ "lr": 5e-05,
5
+ "epochs": 5,
6
+ "max_seq_length": 512,
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": "GeoBERT",
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": "luukschmitz/GeoBERT",
27
+ "evaluation_strategy": "epoch",
28
+ "username": "luukschmitz",
29
+ "log": "tensorboard"
30
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff