josecannete commited on
Commit
1bef7cf
1 Parent(s): e21812b

adding model finetuned on MLDoc

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9739999771118164,
4
+ "eval_loss": 0.12496982514858246,
5
+ "eval_runtime": 52.2788,
6
+ "eval_samples": 1000,
7
+ "eval_samples_per_second": 19.128,
8
+ "eval_steps_per_second": 2.391,
9
+ "train_loss": 0.06767434234748233,
10
+ "train_runtime": 11146.6816,
11
+ "train_samples": 9458,
12
+ "train_samples_per_second": 3.394,
13
+ "train_steps_per_second": 0.212
14
+ }
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CenIA/albert_xxlarge_spanish",
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
+ "gap_size": 0,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 4096,
16
+ "id2label": {
17
+ "0": "LABEL_0",
18
+ "1": "LABEL_1",
19
+ "2": "LABEL_2",
20
+ "3": "LABEL_3"
21
+ },
22
+ "initializer_range": 0.01,
23
+ "inner_group_num": 1,
24
+ "intermediate_size": 16384,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "layers_to_keep": [],
33
+ "max_position_embeddings": 512,
34
+ "model_type": "albert",
35
+ "net_structure_type": 0,
36
+ "num_attention_heads": 64,
37
+ "num_hidden_groups": 1,
38
+ "num_hidden_layers": 12,
39
+ "num_memory_blocks": 0,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "problem_type": "single_label_classification",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.15.0",
45
+ "type_vocab_size": 2,
46
+ "vocab_size": 31000
47
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9739999771118164,
4
+ "eval_loss": 0.12496982514858246,
5
+ "eval_runtime": 52.2788,
6
+ "eval_samples": 1000,
7
+ "eval_samples_per_second": 19.128,
8
+ "eval_steps_per_second": 2.391
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8cdc557df9ea23c791c1b31f84557b093c93e4ea1cda07227059320af0db957
3
+ size 890974929
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": "[MASK]"}
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": true, "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": "CenIA/albert_xxlarge_spanish", "tokenizer_class": "AlbertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.06767434234748233,
4
+ "train_runtime": 11146.6816,
5
+ "train_samples": 9458,
6
+ "train_samples_per_second": 3.394,
7
+ "train_steps_per_second": 0.212
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.12496982514858246,
3
+ "best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_xxlarge/epochs_4_bs_16_lr_5e-6/checkpoint-900",
4
+ "epoch": 3.9991546914623837,
5
+ "global_step": 2364,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "eval_accuracy": 0.6899999976158142,
13
+ "eval_loss": 0.9207698702812195,
14
+ "eval_runtime": 53.4599,
15
+ "eval_samples_per_second": 18.706,
16
+ "eval_steps_per_second": 2.338,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.34,
21
+ "eval_accuracy": 0.8460000157356262,
22
+ "eval_loss": 0.4446202516555786,
23
+ "eval_runtime": 53.5207,
24
+ "eval_samples_per_second": 18.684,
25
+ "eval_steps_per_second": 2.336,
26
+ "step": 200
27
+ },
28
+ {
29
+ "epoch": 0.51,
30
+ "eval_accuracy": 0.9229999780654907,
31
+ "eval_loss": 0.31312161684036255,
32
+ "eval_runtime": 52.7206,
33
+ "eval_samples_per_second": 18.968,
34
+ "eval_steps_per_second": 2.371,
35
+ "step": 300
36
+ },
37
+ {
38
+ "epoch": 0.68,
39
+ "eval_accuracy": 0.9449999928474426,
40
+ "eval_loss": 0.29927751421928406,
41
+ "eval_runtime": 53.4208,
42
+ "eval_samples_per_second": 18.719,
43
+ "eval_steps_per_second": 2.34,
44
+ "step": 400
45
+ },
46
+ {
47
+ "epoch": 0.85,
48
+ "learning_rate": 3.95093062605753e-06,
49
+ "loss": 0.1599,
50
+ "step": 500
51
+ },
52
+ {
53
+ "epoch": 0.85,
54
+ "eval_accuracy": 0.953000009059906,
55
+ "eval_loss": 0.22006945312023163,
56
+ "eval_runtime": 52.7047,
57
+ "eval_samples_per_second": 18.974,
58
+ "eval_steps_per_second": 2.372,
59
+ "step": 500
60
+ },
61
+ {
62
+ "epoch": 1.02,
63
+ "eval_accuracy": 0.9279999732971191,
64
+ "eval_loss": 0.3698674440383911,
65
+ "eval_runtime": 52.7048,
66
+ "eval_samples_per_second": 18.974,
67
+ "eval_steps_per_second": 2.372,
68
+ "step": 600
69
+ },
70
+ {
71
+ "epoch": 1.18,
72
+ "eval_accuracy": 0.9580000042915344,
73
+ "eval_loss": 0.23167340457439423,
74
+ "eval_runtime": 52.7049,
75
+ "eval_samples_per_second": 18.974,
76
+ "eval_steps_per_second": 2.372,
77
+ "step": 700
78
+ },
79
+ {
80
+ "epoch": 1.35,
81
+ "eval_accuracy": 0.9639999866485596,
82
+ "eval_loss": 0.16574066877365112,
83
+ "eval_runtime": 53.2433,
84
+ "eval_samples_per_second": 18.782,
85
+ "eval_steps_per_second": 2.348,
86
+ "step": 800
87
+ },
88
+ {
89
+ "epoch": 1.52,
90
+ "eval_accuracy": 0.9739999771118164,
91
+ "eval_loss": 0.12496982514858246,
92
+ "eval_runtime": 52.7138,
93
+ "eval_samples_per_second": 18.97,
94
+ "eval_steps_per_second": 2.371,
95
+ "step": 900
96
+ },
97
+ {
98
+ "epoch": 1.69,
99
+ "learning_rate": 2.8934010152284262e-06,
100
+ "loss": 0.0708,
101
+ "step": 1000
102
+ },
103
+ {
104
+ "epoch": 1.69,
105
+ "eval_accuracy": 0.9549999833106995,
106
+ "eval_loss": 0.23840972781181335,
107
+ "eval_runtime": 52.6578,
108
+ "eval_samples_per_second": 18.991,
109
+ "eval_steps_per_second": 2.374,
110
+ "step": 1000
111
+ },
112
+ {
113
+ "epoch": 1.86,
114
+ "eval_accuracy": 0.9700000286102295,
115
+ "eval_loss": 0.1677614450454712,
116
+ "eval_runtime": 52.6824,
117
+ "eval_samples_per_second": 18.982,
118
+ "eval_steps_per_second": 2.373,
119
+ "step": 1100
120
+ },
121
+ {
122
+ "epoch": 2.03,
123
+ "eval_accuracy": 0.9710000157356262,
124
+ "eval_loss": 0.1557045578956604,
125
+ "eval_runtime": 53.1989,
126
+ "eval_samples_per_second": 18.797,
127
+ "eval_steps_per_second": 2.35,
128
+ "step": 1200
129
+ },
130
+ {
131
+ "epoch": 2.2,
132
+ "eval_accuracy": 0.9629999995231628,
133
+ "eval_loss": 0.22913765907287598,
134
+ "eval_runtime": 52.6879,
135
+ "eval_samples_per_second": 18.98,
136
+ "eval_steps_per_second": 2.372,
137
+ "step": 1300
138
+ },
139
+ {
140
+ "epoch": 2.37,
141
+ "eval_accuracy": 0.9670000076293945,
142
+ "eval_loss": 0.17893917858600616,
143
+ "eval_runtime": 52.8001,
144
+ "eval_samples_per_second": 18.939,
145
+ "eval_steps_per_second": 2.367,
146
+ "step": 1400
147
+ },
148
+ {
149
+ "epoch": 2.54,
150
+ "learning_rate": 1.8358714043993234e-06,
151
+ "loss": 0.0453,
152
+ "step": 1500
153
+ },
154
+ {
155
+ "epoch": 2.54,
156
+ "eval_accuracy": 0.9710000157356262,
157
+ "eval_loss": 0.16048669815063477,
158
+ "eval_runtime": 52.6463,
159
+ "eval_samples_per_second": 18.995,
160
+ "eval_steps_per_second": 2.374,
161
+ "step": 1500
162
+ },
163
+ {
164
+ "epoch": 2.71,
165
+ "eval_accuracy": 0.9520000219345093,
166
+ "eval_loss": 0.2762700319290161,
167
+ "eval_runtime": 52.6922,
168
+ "eval_samples_per_second": 18.978,
169
+ "eval_steps_per_second": 2.372,
170
+ "step": 1600
171
+ },
172
+ {
173
+ "epoch": 2.88,
174
+ "eval_accuracy": 0.9649999737739563,
175
+ "eval_loss": 0.18934407830238342,
176
+ "eval_runtime": 52.6384,
177
+ "eval_samples_per_second": 18.998,
178
+ "eval_steps_per_second": 2.375,
179
+ "step": 1700
180
+ },
181
+ {
182
+ "epoch": 3.05,
183
+ "eval_accuracy": 0.9739999771118164,
184
+ "eval_loss": 0.16606220602989197,
185
+ "eval_runtime": 52.7133,
186
+ "eval_samples_per_second": 18.971,
187
+ "eval_steps_per_second": 2.371,
188
+ "step": 1800
189
+ },
190
+ {
191
+ "epoch": 3.21,
192
+ "eval_accuracy": 0.9660000205039978,
193
+ "eval_loss": 0.222770556807518,
194
+ "eval_runtime": 53.295,
195
+ "eval_samples_per_second": 18.763,
196
+ "eval_steps_per_second": 2.345,
197
+ "step": 1900
198
+ },
199
+ {
200
+ "epoch": 3.38,
201
+ "learning_rate": 7.7834179357022e-07,
202
+ "loss": 0.0294,
203
+ "step": 2000
204
+ },
205
+ {
206
+ "epoch": 3.38,
207
+ "eval_accuracy": 0.9639999866485596,
208
+ "eval_loss": 0.20788319408893585,
209
+ "eval_runtime": 52.7008,
210
+ "eval_samples_per_second": 18.975,
211
+ "eval_steps_per_second": 2.372,
212
+ "step": 2000
213
+ },
214
+ {
215
+ "epoch": 3.55,
216
+ "eval_accuracy": 0.9660000205039978,
217
+ "eval_loss": 0.18167437613010406,
218
+ "eval_runtime": 52.7113,
219
+ "eval_samples_per_second": 18.971,
220
+ "eval_steps_per_second": 2.371,
221
+ "step": 2100
222
+ },
223
+ {
224
+ "epoch": 3.72,
225
+ "eval_accuracy": 0.9620000123977661,
226
+ "eval_loss": 0.20487231016159058,
227
+ "eval_runtime": 52.7823,
228
+ "eval_samples_per_second": 18.946,
229
+ "eval_steps_per_second": 2.368,
230
+ "step": 2200
231
+ },
232
+ {
233
+ "epoch": 3.89,
234
+ "eval_accuracy": 0.9670000076293945,
235
+ "eval_loss": 0.19099852442741394,
236
+ "eval_runtime": 53.0072,
237
+ "eval_samples_per_second": 18.865,
238
+ "eval_steps_per_second": 2.358,
239
+ "step": 2300
240
+ },
241
+ {
242
+ "epoch": 4.0,
243
+ "step": 2364,
244
+ "total_flos": 1.796922868289472e+16,
245
+ "train_loss": 0.06767434234748233,
246
+ "train_runtime": 11146.6816,
247
+ "train_samples_per_second": 3.394,
248
+ "train_steps_per_second": 0.212
249
+ }
250
+ ],
251
+ "max_steps": 2364,
252
+ "num_train_epochs": 4,
253
+ "total_flos": 1.796922868289472e+16,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48532441e49fcfa32383c324a073e4ba394ae35c58bc1f469ff2fbe452196356
3
+ size 2991