Saving best model of baseline_BERT_50K_steps to hub
Browse files- README.md +96 -0
- all_results.json +7 -0
- config.json +361 -0
- model.safetensors +3 -0
- runs/Feb04_23-14-48_jordy-OMEN/events.out.tfevents.1707084891.jordy-OMEN.182531.0 +3 -0
- runs/Feb04_23-14-48_jordy-OMEN/events.out.tfevents.1707103774.jordy-OMEN.182531.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- train_results.json +7 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- arxiv_dataset
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- precision
|
11 |
+
- recall
|
12 |
+
- f1
|
13 |
+
model-index:
|
14 |
+
- name: baseline_BERT_50K_steps
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Text Classification
|
18 |
+
type: text-classification
|
19 |
+
dataset:
|
20 |
+
name: arxiv_dataset
|
21 |
+
type: arxiv_dataset
|
22 |
+
config: default
|
23 |
+
split: train
|
24 |
+
args: default
|
25 |
+
metrics:
|
26 |
+
- name: Accuracy
|
27 |
+
type: accuracy
|
28 |
+
value: 0.9936787420400056
|
29 |
+
- name: Precision
|
30 |
+
type: precision
|
31 |
+
value: 0.7967781908302355
|
32 |
+
- name: Recall
|
33 |
+
type: recall
|
34 |
+
value: 0.4734468476760239
|
35 |
+
- name: F1
|
36 |
+
type: f1
|
37 |
+
value: 0.5939610876970152
|
38 |
+
---
|
39 |
+
|
40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
+
should probably proofread and complete it, then remove this comment. -->
|
42 |
+
|
43 |
+
# baseline_BERT_50K_steps
|
44 |
+
|
45 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the arxiv_dataset dataset.
|
46 |
+
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.0192
|
48 |
+
- Accuracy: 0.9937
|
49 |
+
- Precision: 0.7968
|
50 |
+
- Recall: 0.4734
|
51 |
+
- F1: 0.5940
|
52 |
+
- Hamming: 0.0063
|
53 |
+
|
54 |
+
## Model description
|
55 |
+
|
56 |
+
More information needed
|
57 |
+
|
58 |
+
## Intended uses & limitations
|
59 |
+
|
60 |
+
More information needed
|
61 |
+
|
62 |
+
## Training and evaluation data
|
63 |
+
|
64 |
+
More information needed
|
65 |
+
|
66 |
+
## Training procedure
|
67 |
+
|
68 |
+
### Training hyperparameters
|
69 |
+
|
70 |
+
The following hyperparameters were used during training:
|
71 |
+
- learning_rate: 2e-05
|
72 |
+
- train_batch_size: 6
|
73 |
+
- eval_batch_size: 6
|
74 |
+
- seed: 42
|
75 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
76 |
+
- lr_scheduler_type: linear
|
77 |
+
- lr_scheduler_warmup_ratio: 0.1
|
78 |
+
- training_steps: 50000
|
79 |
+
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming |
|
83 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
|
84 |
+
| 0.0343 | 0.03 | 10000 | 0.0315 | 0.9912 | 0.7679 | 0.1370 | 0.2326 | 0.0088 |
|
85 |
+
| 0.0244 | 0.06 | 20000 | 0.0234 | 0.9925 | 0.7813 | 0.3262 | 0.4602 | 0.0075 |
|
86 |
+
| 0.0219 | 0.09 | 30000 | 0.0210 | 0.9931 | 0.7572 | 0.4320 | 0.5502 | 0.0069 |
|
87 |
+
| 0.0204 | 0.12 | 40000 | 0.0197 | 0.9935 | 0.7738 | 0.4711 | 0.5857 | 0.0065 |
|
88 |
+
| 0.0197 | 0.15 | 50000 | 0.0192 | 0.9937 | 0.7968 | 0.4734 | 0.5940 | 0.0063 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.37.2
|
94 |
+
- Pytorch 1.12.1+cu113
|
95 |
+
- Datasets 2.16.1
|
96 |
+
- Tokenizers 0.15.1
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.15,
|
3 |
+
"train_loss": 0.036997793807983397,
|
4 |
+
"train_runtime": 18671.9874,
|
5 |
+
"train_samples_per_second": 16.067,
|
6 |
+
"train_steps_per_second": 2.678
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "adap-org",
|
14 |
+
"1": "alg-geom",
|
15 |
+
"2": "astro-ph",
|
16 |
+
"3": "astro-ph.CO",
|
17 |
+
"4": "astro-ph.EP",
|
18 |
+
"5": "astro-ph.GA",
|
19 |
+
"6": "astro-ph.HE",
|
20 |
+
"7": "astro-ph.IM",
|
21 |
+
"8": "astro-ph.SR",
|
22 |
+
"9": "atom-ph",
|
23 |
+
"10": "chao-dyn",
|
24 |
+
"11": "chem-ph",
|
25 |
+
"12": "cmp-lg",
|
26 |
+
"13": "comp-gas",
|
27 |
+
"14": "cond-mat",
|
28 |
+
"15": "cond-mat.dis-nn",
|
29 |
+
"16": "cond-mat.mes-hall",
|
30 |
+
"17": "cond-mat.mtrl-sci",
|
31 |
+
"18": "cond-mat.other",
|
32 |
+
"19": "cond-mat.quant-gas",
|
33 |
+
"20": "cond-mat.soft",
|
34 |
+
"21": "cond-mat.stat-mech",
|
35 |
+
"22": "cond-mat.str-el",
|
36 |
+
"23": "cond-mat.supr-con",
|
37 |
+
"24": "cs.AI",
|
38 |
+
"25": "cs.AR",
|
39 |
+
"26": "cs.CC",
|
40 |
+
"27": "cs.CE",
|
41 |
+
"28": "cs.CG",
|
42 |
+
"29": "cs.CL",
|
43 |
+
"30": "cs.CR",
|
44 |
+
"31": "cs.CV",
|
45 |
+
"32": "cs.CY",
|
46 |
+
"33": "cs.DB",
|
47 |
+
"34": "cs.DC",
|
48 |
+
"35": "cs.DL",
|
49 |
+
"36": "cs.DM",
|
50 |
+
"37": "cs.DS",
|
51 |
+
"38": "cs.ET",
|
52 |
+
"39": "cs.FL",
|
53 |
+
"40": "cs.GL",
|
54 |
+
"41": "cs.GR",
|
55 |
+
"42": "cs.GT",
|
56 |
+
"43": "cs.HC",
|
57 |
+
"44": "cs.IR",
|
58 |
+
"45": "cs.LG",
|
59 |
+
"46": "cs.LO",
|
60 |
+
"47": "cs.MA",
|
61 |
+
"48": "cs.MM",
|
62 |
+
"49": "cs.MS",
|
63 |
+
"50": "cs.NA",
|
64 |
+
"51": "cs.NE",
|
65 |
+
"52": "cs.NI",
|
66 |
+
"53": "cs.OH",
|
67 |
+
"54": "cs.OS",
|
68 |
+
"55": "cs.PF",
|
69 |
+
"56": "cs.PL",
|
70 |
+
"57": "cs.RO",
|
71 |
+
"58": "cs.SC",
|
72 |
+
"59": "cs.SD",
|
73 |
+
"60": "cs.SE",
|
74 |
+
"61": "cs.SI",
|
75 |
+
"62": "cs.SY",
|
76 |
+
"63": "dg-ga",
|
77 |
+
"64": "econ.EM",
|
78 |
+
"65": "econ.GN",
|
79 |
+
"66": "econ.TH",
|
80 |
+
"67": "eess.AS",
|
81 |
+
"68": "eess.IV",
|
82 |
+
"69": "eess.SP",
|
83 |
+
"70": "eess.SY",
|
84 |
+
"71": "funct-an",
|
85 |
+
"72": "gr-qc",
|
86 |
+
"73": "hep-ex",
|
87 |
+
"74": "hep-lat",
|
88 |
+
"75": "hep-ph",
|
89 |
+
"76": "hep-th",
|
90 |
+
"77": "math.AC",
|
91 |
+
"78": "math.AG",
|
92 |
+
"79": "math.AP",
|
93 |
+
"80": "math.AT",
|
94 |
+
"81": "math.CA",
|
95 |
+
"82": "math.CO",
|
96 |
+
"83": "math.CT",
|
97 |
+
"84": "math.CV",
|
98 |
+
"85": "math.DG",
|
99 |
+
"86": "math.DS",
|
100 |
+
"87": "math.FA",
|
101 |
+
"88": "math.GM",
|
102 |
+
"89": "math.GN",
|
103 |
+
"90": "math.GR",
|
104 |
+
"91": "math.GT",
|
105 |
+
"92": "math.HO",
|
106 |
+
"93": "math.KT",
|
107 |
+
"94": "math.LO",
|
108 |
+
"95": "math.MG",
|
109 |
+
"96": "math.NA",
|
110 |
+
"97": "math.NT",
|
111 |
+
"98": "math.OA",
|
112 |
+
"99": "math.OC",
|
113 |
+
"100": "math.PR",
|
114 |
+
"101": "math.QA",
|
115 |
+
"102": "math.RA",
|
116 |
+
"103": "math.RT",
|
117 |
+
"104": "math.SG",
|
118 |
+
"105": "math.SP",
|
119 |
+
"106": "mtrl-th",
|
120 |
+
"107": "nlin.AO",
|
121 |
+
"108": "nlin.CD",
|
122 |
+
"109": "nlin.CG",
|
123 |
+
"110": "nlin.PS",
|
124 |
+
"111": "nlin.SI",
|
125 |
+
"112": "nucl-ex",
|
126 |
+
"113": "nucl-th",
|
127 |
+
"114": "patt-sol",
|
128 |
+
"115": "physics.acc-ph",
|
129 |
+
"116": "physics.ao-ph",
|
130 |
+
"117": "physics.app-ph",
|
131 |
+
"118": "physics.atm-clus",
|
132 |
+
"119": "physics.atom-ph",
|
133 |
+
"120": "physics.bio-ph",
|
134 |
+
"121": "physics.chem-ph",
|
135 |
+
"122": "physics.class-ph",
|
136 |
+
"123": "physics.comp-ph",
|
137 |
+
"124": "physics.data-an",
|
138 |
+
"125": "physics.ed-ph",
|
139 |
+
"126": "physics.flu-dyn",
|
140 |
+
"127": "physics.gen-ph",
|
141 |
+
"128": "physics.geo-ph",
|
142 |
+
"129": "physics.hist-ph",
|
143 |
+
"130": "physics.ins-det",
|
144 |
+
"131": "physics.med-ph",
|
145 |
+
"132": "physics.optics",
|
146 |
+
"133": "physics.plasm-ph",
|
147 |
+
"134": "physics.pop-ph",
|
148 |
+
"135": "physics.soc-ph",
|
149 |
+
"136": "physics.space-ph",
|
150 |
+
"137": "q-alg",
|
151 |
+
"138": "q-bio.BM",
|
152 |
+
"139": "q-bio.CB",
|
153 |
+
"140": "q-bio.GN",
|
154 |
+
"141": "q-bio.MN",
|
155 |
+
"142": "q-bio.NC",
|
156 |
+
"143": "q-bio.OT",
|
157 |
+
"144": "q-bio.PE",
|
158 |
+
"145": "q-bio.QM",
|
159 |
+
"146": "q-bio.SC",
|
160 |
+
"147": "q-bio.TO",
|
161 |
+
"148": "q-fin.CP",
|
162 |
+
"149": "q-fin.EC",
|
163 |
+
"150": "q-fin.GN",
|
164 |
+
"151": "q-fin.MF",
|
165 |
+
"152": "q-fin.PM",
|
166 |
+
"153": "q-fin.PR",
|
167 |
+
"154": "q-fin.RM",
|
168 |
+
"155": "q-fin.ST",
|
169 |
+
"156": "q-fin.TR",
|
170 |
+
"157": "quant-ph",
|
171 |
+
"158": "solv-int",
|
172 |
+
"159": "stat.AP",
|
173 |
+
"160": "stat.CO",
|
174 |
+
"161": "stat.ME",
|
175 |
+
"162": "stat.ML",
|
176 |
+
"163": "stat.OT",
|
177 |
+
"164": "supr-con"
|
178 |
+
},
|
179 |
+
"initializer_range": 0.02,
|
180 |
+
"intermediate_size": 3072,
|
181 |
+
"label2id": {
|
182 |
+
"adap-org": 0,
|
183 |
+
"alg-geom": 1,
|
184 |
+
"astro-ph": 2,
|
185 |
+
"astro-ph.CO": 3,
|
186 |
+
"astro-ph.EP": 4,
|
187 |
+
"astro-ph.GA": 5,
|
188 |
+
"astro-ph.HE": 6,
|
189 |
+
"astro-ph.IM": 7,
|
190 |
+
"astro-ph.SR": 8,
|
191 |
+
"atom-ph": 9,
|
192 |
+
"chao-dyn": 10,
|
193 |
+
"chem-ph": 11,
|
194 |
+
"cmp-lg": 12,
|
195 |
+
"comp-gas": 13,
|
196 |
+
"cond-mat": 14,
|
197 |
+
"cond-mat.dis-nn": 15,
|
198 |
+
"cond-mat.mes-hall": 16,
|
199 |
+
"cond-mat.mtrl-sci": 17,
|
200 |
+
"cond-mat.other": 18,
|
201 |
+
"cond-mat.quant-gas": 19,
|
202 |
+
"cond-mat.soft": 20,
|
203 |
+
"cond-mat.stat-mech": 21,
|
204 |
+
"cond-mat.str-el": 22,
|
205 |
+
"cond-mat.supr-con": 23,
|
206 |
+
"cs.AI": 24,
|
207 |
+
"cs.AR": 25,
|
208 |
+
"cs.CC": 26,
|
209 |
+
"cs.CE": 27,
|
210 |
+
"cs.CG": 28,
|
211 |
+
"cs.CL": 29,
|
212 |
+
"cs.CR": 30,
|
213 |
+
"cs.CV": 31,
|
214 |
+
"cs.CY": 32,
|
215 |
+
"cs.DB": 33,
|
216 |
+
"cs.DC": 34,
|
217 |
+
"cs.DL": 35,
|
218 |
+
"cs.DM": 36,
|
219 |
+
"cs.DS": 37,
|
220 |
+
"cs.ET": 38,
|
221 |
+
"cs.FL": 39,
|
222 |
+
"cs.GL": 40,
|
223 |
+
"cs.GR": 41,
|
224 |
+
"cs.GT": 42,
|
225 |
+
"cs.HC": 43,
|
226 |
+
"cs.IR": 44,
|
227 |
+
"cs.LG": 45,
|
228 |
+
"cs.LO": 46,
|
229 |
+
"cs.MA": 47,
|
230 |
+
"cs.MM": 48,
|
231 |
+
"cs.MS": 49,
|
232 |
+
"cs.NA": 50,
|
233 |
+
"cs.NE": 51,
|
234 |
+
"cs.NI": 52,
|
235 |
+
"cs.OH": 53,
|
236 |
+
"cs.OS": 54,
|
237 |
+
"cs.PF": 55,
|
238 |
+
"cs.PL": 56,
|
239 |
+
"cs.RO": 57,
|
240 |
+
"cs.SC": 58,
|
241 |
+
"cs.SD": 59,
|
242 |
+
"cs.SE": 60,
|
243 |
+
"cs.SI": 61,
|
244 |
+
"cs.SY": 62,
|
245 |
+
"dg-ga": 63,
|
246 |
+
"econ.EM": 64,
|
247 |
+
"econ.GN": 65,
|
248 |
+
"econ.TH": 66,
|
249 |
+
"eess.AS": 67,
|
250 |
+
"eess.IV": 68,
|
251 |
+
"eess.SP": 69,
|
252 |
+
"eess.SY": 70,
|
253 |
+
"funct-an": 71,
|
254 |
+
"gr-qc": 72,
|
255 |
+
"hep-ex": 73,
|
256 |
+
"hep-lat": 74,
|
257 |
+
"hep-ph": 75,
|
258 |
+
"hep-th": 76,
|
259 |
+
"math.AC": 77,
|
260 |
+
"math.AG": 78,
|
261 |
+
"math.AP": 79,
|
262 |
+
"math.AT": 80,
|
263 |
+
"math.CA": 81,
|
264 |
+
"math.CO": 82,
|
265 |
+
"math.CT": 83,
|
266 |
+
"math.CV": 84,
|
267 |
+
"math.DG": 85,
|
268 |
+
"math.DS": 86,
|
269 |
+
"math.FA": 87,
|
270 |
+
"math.GM": 88,
|
271 |
+
"math.GN": 89,
|
272 |
+
"math.GR": 90,
|
273 |
+
"math.GT": 91,
|
274 |
+
"math.HO": 92,
|
275 |
+
"math.KT": 93,
|
276 |
+
"math.LO": 94,
|
277 |
+
"math.MG": 95,
|
278 |
+
"math.NA": 96,
|
279 |
+
"math.NT": 97,
|
280 |
+
"math.OA": 98,
|
281 |
+
"math.OC": 99,
|
282 |
+
"math.PR": 100,
|
283 |
+
"math.QA": 101,
|
284 |
+
"math.RA": 102,
|
285 |
+
"math.RT": 103,
|
286 |
+
"math.SG": 104,
|
287 |
+
"math.SP": 105,
|
288 |
+
"mtrl-th": 106,
|
289 |
+
"nlin.AO": 107,
|
290 |
+
"nlin.CD": 108,
|
291 |
+
"nlin.CG": 109,
|
292 |
+
"nlin.PS": 110,
|
293 |
+
"nlin.SI": 111,
|
294 |
+
"nucl-ex": 112,
|
295 |
+
"nucl-th": 113,
|
296 |
+
"patt-sol": 114,
|
297 |
+
"physics.acc-ph": 115,
|
298 |
+
"physics.ao-ph": 116,
|
299 |
+
"physics.app-ph": 117,
|
300 |
+
"physics.atm-clus": 118,
|
301 |
+
"physics.atom-ph": 119,
|
302 |
+
"physics.bio-ph": 120,
|
303 |
+
"physics.chem-ph": 121,
|
304 |
+
"physics.class-ph": 122,
|
305 |
+
"physics.comp-ph": 123,
|
306 |
+
"physics.data-an": 124,
|
307 |
+
"physics.ed-ph": 125,
|
308 |
+
"physics.flu-dyn": 126,
|
309 |
+
"physics.gen-ph": 127,
|
310 |
+
"physics.geo-ph": 128,
|
311 |
+
"physics.hist-ph": 129,
|
312 |
+
"physics.ins-det": 130,
|
313 |
+
"physics.med-ph": 131,
|
314 |
+
"physics.optics": 132,
|
315 |
+
"physics.plasm-ph": 133,
|
316 |
+
"physics.pop-ph": 134,
|
317 |
+
"physics.soc-ph": 135,
|
318 |
+
"physics.space-ph": 136,
|
319 |
+
"q-alg": 137,
|
320 |
+
"q-bio.BM": 138,
|
321 |
+
"q-bio.CB": 139,
|
322 |
+
"q-bio.GN": 140,
|
323 |
+
"q-bio.MN": 141,
|
324 |
+
"q-bio.NC": 142,
|
325 |
+
"q-bio.OT": 143,
|
326 |
+
"q-bio.PE": 144,
|
327 |
+
"q-bio.QM": 145,
|
328 |
+
"q-bio.SC": 146,
|
329 |
+
"q-bio.TO": 147,
|
330 |
+
"q-fin.CP": 148,
|
331 |
+
"q-fin.EC": 149,
|
332 |
+
"q-fin.GN": 150,
|
333 |
+
"q-fin.MF": 151,
|
334 |
+
"q-fin.PM": 152,
|
335 |
+
"q-fin.PR": 153,
|
336 |
+
"q-fin.RM": 154,
|
337 |
+
"q-fin.ST": 155,
|
338 |
+
"q-fin.TR": 156,
|
339 |
+
"quant-ph": 157,
|
340 |
+
"solv-int": 158,
|
341 |
+
"stat.AP": 159,
|
342 |
+
"stat.CO": 160,
|
343 |
+
"stat.ME": 161,
|
344 |
+
"stat.ML": 162,
|
345 |
+
"stat.OT": 163,
|
346 |
+
"supr-con": 164
|
347 |
+
},
|
348 |
+
"layer_norm_eps": 1e-12,
|
349 |
+
"max_position_embeddings": 512,
|
350 |
+
"model_type": "bert",
|
351 |
+
"num_attention_heads": 12,
|
352 |
+
"num_hidden_layers": 12,
|
353 |
+
"pad_token_id": 0,
|
354 |
+
"position_embedding_type": "absolute",
|
355 |
+
"problem_type": "multi_label_classification",
|
356 |
+
"torch_dtype": "float32",
|
357 |
+
"transformers_version": "4.37.2",
|
358 |
+
"type_vocab_size": 2,
|
359 |
+
"use_cache": true,
|
360 |
+
"vocab_size": 30522
|
361 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce735465cf6c1d59c6135f5b88157d17d351e281185bf3aa9383ca8127e3f3a7
|
3 |
+
size 438460036
|
runs/Feb04_23-14-48_jordy-OMEN/events.out.tfevents.1707084891.jordy-OMEN.182531.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6238b9b2bd331821ee23dfb7b99f8d6bfe0da205d6aebd417d2b28e73c77dd33
|
3 |
+
size 17789
|
runs/Feb04_23-14-48_jordy-OMEN/events.out.tfevents.1707103774.jordy-OMEN.182531.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c4bfa7977692ed3d7690af5ad209a503058c287ced6872290312c82890f5de
|
3 |
+
size 573
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.15,
|
3 |
+
"train_loss": 0.036997793807983397,
|
4 |
+
"train_runtime": 18671.9874,
|
5 |
+
"train_samples_per_second": 16.067,
|
6 |
+
"train_steps_per_second": 2.678
|
7 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f238cb2ce193f29dfc9918d1d7353b294a4859f3d9d70c13324355132df8313
|
3 |
+
size 4335
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|