Alireza1044 commited on
Commit
ce8224e
1 Parent(s): 96f6ac7
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - accuracy
11
+ model_index:
12
+ - name: mnli
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: GLUE MNLI
19
+ type: glue
20
+ args: mnli
21
+ metric:
22
+ name: Accuracy
23
+ type: accuracy
24
+ value: 0.8500813669650122
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # mnli
31
+
32
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE MNLI dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.5383
35
+ - Accuracy: 0.8501
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 3e-05
55
+ - train_batch_size: 64
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 4.0
61
+
62
+ ### Training results
63
+
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.9.1
69
+ - Pytorch 1.9.0+cu102
70
+ - Datasets 1.10.2
71
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.8500813669650122,
4
+ "eval_loss": 0.5383013486862183,
5
+ "eval_runtime": 50.6991,
6
+ "eval_samples": 9832,
7
+ "eval_samples_per_second": 193.929,
8
+ "eval_steps_per_second": 24.241,
9
+ "train_loss": 0.3001841343599317,
10
+ "train_runtime": 18121.6674,
11
+ "train_samples": 392702,
12
+ "train_samples_per_second": 86.681,
13
+ "train_steps_per_second": 1.354
14
+ }
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "finetuning_task": "mnli",
13
+ "gap_size": 0,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_dropout_prob": 0,
16
+ "hidden_size": 768,
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1",
20
+ "2": "LABEL_2"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "inner_group_num": 1,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "albert",
33
+ "net_structure_type": 0,
34
+ "num_attention_heads": 12,
35
+ "num_hidden_groups": 1,
36
+ "num_hidden_layers": 12,
37
+ "num_memory_blocks": 0,
38
+ "pad_token_id": 0,
39
+ "position_embedding_type": "absolute",
40
+ "problem_type": "single_label_classification",
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.9.1",
43
+ "type_vocab_size": 2,
44
+ "vocab_size": 30000
45
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.8500813669650122,
4
+ "eval_loss": 0.5383013486862183,
5
+ "eval_runtime": 50.6991,
6
+ "eval_samples": 9832,
7
+ "eval_samples_per_second": 193.929,
8
+ "eval_steps_per_second": 24.241
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3228d57b4e7e1da04cc582bf139060a5afe2fd5bc2e4dc1f415e1ab4ddcf7c9a
3
+ size 46758609
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.3001841343599317,
4
+ "train_runtime": 18121.6674,
5
+ "train_samples": 392702,
6
+ "train_samples_per_second": 86.681,
7
+ "train_steps_per_second": 1.354
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 24544,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 2.9388852672750976e-05,
13
+ "loss": 0.6805,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 2.877770534550196e-05,
19
+ "loss": 0.5507,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.24,
24
+ "learning_rate": 2.8166558018252934e-05,
25
+ "loss": 0.5379,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.33,
30
+ "learning_rate": 2.7555410691003913e-05,
31
+ "loss": 0.5057,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.41,
36
+ "learning_rate": 2.694426336375489e-05,
37
+ "loss": 0.4835,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.49,
42
+ "learning_rate": 2.6333116036505867e-05,
43
+ "loss": 0.4697,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.57,
48
+ "learning_rate": 2.5721968709256846e-05,
49
+ "loss": 0.4676,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.65,
54
+ "learning_rate": 2.511082138200782e-05,
55
+ "loss": 0.4621,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.73,
60
+ "learning_rate": 2.4499674054758804e-05,
61
+ "loss": 0.4496,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.81,
66
+ "learning_rate": 2.388852672750978e-05,
67
+ "loss": 0.4382,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.9,
72
+ "learning_rate": 2.3277379400260758e-05,
73
+ "loss": 0.4452,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.98,
78
+ "learning_rate": 2.2666232073011734e-05,
79
+ "loss": 0.4366,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.06,
84
+ "learning_rate": 2.2055084745762713e-05,
85
+ "loss": 0.3681,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.14,
90
+ "learning_rate": 2.144393741851369e-05,
91
+ "loss": 0.3505,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.22,
96
+ "learning_rate": 2.0832790091264667e-05,
97
+ "loss": 0.3528,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.3,
102
+ "learning_rate": 2.0221642764015646e-05,
103
+ "loss": 0.3458,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.39,
108
+ "learning_rate": 1.9610495436766625e-05,
109
+ "loss": 0.3527,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.47,
114
+ "learning_rate": 1.89993481095176e-05,
115
+ "loss": 0.3432,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.55,
120
+ "learning_rate": 1.838820078226858e-05,
121
+ "loss": 0.3428,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.63,
126
+ "learning_rate": 1.7777053455019558e-05,
127
+ "loss": 0.3478,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.71,
132
+ "learning_rate": 1.7165906127770537e-05,
133
+ "loss": 0.3424,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.79,
138
+ "learning_rate": 1.6554758800521512e-05,
139
+ "loss": 0.3433,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.87,
144
+ "learning_rate": 1.5943611473272488e-05,
145
+ "loss": 0.3417,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.96,
150
+ "learning_rate": 1.533246414602347e-05,
151
+ "loss": 0.3323,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.04,
156
+ "learning_rate": 1.4721316818774445e-05,
157
+ "loss": 0.2957,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.12,
162
+ "learning_rate": 1.4110169491525424e-05,
163
+ "loss": 0.2283,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.2,
168
+ "learning_rate": 1.3499022164276401e-05,
169
+ "loss": 0.2252,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.28,
174
+ "learning_rate": 1.288787483702738e-05,
175
+ "loss": 0.2299,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.36,
180
+ "learning_rate": 1.2276727509778357e-05,
181
+ "loss": 0.2373,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.44,
186
+ "learning_rate": 1.1665580182529336e-05,
187
+ "loss": 0.2281,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.53,
192
+ "learning_rate": 1.1054432855280312e-05,
193
+ "loss": 0.2314,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.61,
198
+ "learning_rate": 1.044328552803129e-05,
199
+ "loss": 0.2409,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.69,
204
+ "learning_rate": 9.83213820078227e-06,
205
+ "loss": 0.2375,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 2.77,
210
+ "learning_rate": 9.220990873533247e-06,
211
+ "loss": 0.2308,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 2.85,
216
+ "learning_rate": 8.609843546284226e-06,
217
+ "loss": 0.2371,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 2.93,
222
+ "learning_rate": 7.998696219035203e-06,
223
+ "loss": 0.2328,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 3.01,
228
+ "learning_rate": 7.38754889178618e-06,
229
+ "loss": 0.2145,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 3.1,
234
+ "learning_rate": 6.776401564537158e-06,
235
+ "loss": 0.1336,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 3.18,
240
+ "learning_rate": 6.165254237288136e-06,
241
+ "loss": 0.1356,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 3.26,
246
+ "learning_rate": 5.554106910039114e-06,
247
+ "loss": 0.1381,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 3.34,
252
+ "learning_rate": 4.942959582790091e-06,
253
+ "loss": 0.1343,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 3.42,
258
+ "learning_rate": 4.331812255541069e-06,
259
+ "loss": 0.1385,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 3.5,
264
+ "learning_rate": 3.720664928292047e-06,
265
+ "loss": 0.1316,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 3.59,
270
+ "learning_rate": 3.109517601043025e-06,
271
+ "loss": 0.1314,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 3.67,
276
+ "learning_rate": 2.498370273794003e-06,
277
+ "loss": 0.1221,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 3.75,
282
+ "learning_rate": 1.8872229465449805e-06,
283
+ "loss": 0.1301,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 3.83,
288
+ "learning_rate": 1.2760756192959583e-06,
289
+ "loss": 0.1249,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 3.91,
294
+ "learning_rate": 6.649282920469362e-07,
295
+ "loss": 0.1215,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 3.99,
300
+ "learning_rate": 5.378096479791395e-08,
301
+ "loss": 0.1225,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 4.0,
306
+ "step": 24544,
307
+ "total_flos": 9385760063993856.0,
308
+ "train_loss": 0.3001841343599317,
309
+ "train_runtime": 18121.6674,
310
+ "train_samples_per_second": 86.681,
311
+ "train_steps_per_second": 1.354
312
+ }
313
+ ],
314
+ "max_steps": 24544,
315
+ "num_train_epochs": 4,
316
+ "total_flos": 9385760063993856.0,
317
+ "trial_name": null,
318
+ "trial_params": null
319
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc30ee9a46e627693246aa5f5963c200aa9bc8ec1adf1061f9ebe32f77a41a8
3
+ size 2607