Hugging Face's logo

timonziegenbein
/
appropriateness-classifier-multilabel

Text Classification
Transformers
PyTorch
English
deberta-v2
text-embeddings-inference
Model card Files
xet
Community
2
NHWP25179 commited on
Commit
a9fe236
·
1 Parent(s): 4360f46

init

Browse files
Files changed (12) hide show
  1. added_tokens.json +3 -0
  2. config.json +68 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +9 -0
  8. spm.model +3 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +16 -0
  11. trainer_state.json +405 -0
  12. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
3
+ "architectures": [
4
+ "AppropriatenessMultilabelModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 4096,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_11": 11,
33
+ "LABEL_12": 12,
34
+ "LABEL_13": 13,
35
+ "LABEL_2": 2,
36
+ "LABEL_3": 3,
37
+ "LABEL_4": 4,
38
+ "LABEL_5": 5,
39
+ "LABEL_6": 6,
40
+ "LABEL_7": 7,
41
+ "LABEL_8": 8,
42
+ "LABEL_9": 9
43
+ },
44
+ "layer_norm_eps": 1e-07,
45
+ "max_position_embeddings": 512,
46
+ "max_relative_positions": -1,
47
+ "model_type": "deberta-v2",
48
+ "norm_rel_ebd": "layer_norm",
49
+ "num_attention_heads": 16,
50
+ "num_hidden_layers": 24,
51
+ "pad_token_id": 0,
52
+ "pooler_dropout": 0,
53
+ "pooler_hidden_act": "gelu",
54
+ "pooler_hidden_size": 1024,
55
+ "pos_att_type": [
56
+ "p2c",
57
+ "c2p"
58
+ ],
59
+ "position_biased_input": false,
60
+ "position_buckets": 256,
61
+ "problem_type": "multi_label_classification",
62
+ "relative_attention": true,
63
+ "share_att_key": true,
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.28.0.dev0",
66
+ "type_vocab_size": 0,
67
+ "vocab_size": 128100
68
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79617dd30b8b08315c276737e78bb46c002174577a0e4f3aa56960b1115f1201
3
+ size 3480840261
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0971e5bdc412cb4c63009ef95bcf1c48899fa5d9814a6102b2f5673320c1b0a7
3
+ size 1740445433
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e87f3411c6ef1a86461dcb40fe4e29a7ecdd37b1dce8038f7ebd895d299d7e
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b1f09f3139755125a05f9c9578726850f39440541793061967be8e7efc5119
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "sp_model_kwargs": {},
11
+ "special_tokens_map_file": null,
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }
trainer_state.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.681284212993957,
3
+ "best_model_checkpoint": "/bigwork/nhwpziet/appropriateness-style-transfer/data/models/multilabel-debertav3-conservative/fold0/fold0.0/checkpoint-1250",
4
+ "epoch": 18.229166666666668,
5
+ "global_step": 1750,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.6,
12
+ "eval_Appropriateness_macroF1": 0.6499349052509764,
13
+ "eval_Appropriateness_precision": 0.663745660824655,
14
+ "eval_Appropriateness_recall": 0.6624663978494624,
15
+ "eval_Commitment_macroF1": 0.48068768147730356,
16
+ "eval_Commitment_precision": 0.6111764705882352,
17
+ "eval_Commitment_recall": 0.5880626223091976,
18
+ "eval_Committed Openness_macroF1": 0.5892457057505601,
19
+ "eval_Committed Openness_precision": 0.6571428571428571,
20
+ "eval_Committed Openness_recall": 0.6731601731601732,
21
+ "eval_Committed Seriousness_macroF1": 0.6182764603817235,
22
+ "eval_Committed Seriousness_precision": 0.6083439761600681,
23
+ "eval_Committed Seriousness_recall": 0.77997799779978,
24
+ "eval_Emotional Intensity_macroF1": 0.574343023682986,
25
+ "eval_Emotional Intensity_precision": 0.5939801879603759,
26
+ "eval_Emotional Intensity_recall": 0.6541666666666667,
27
+ "eval_Emotional Typology_macroF1": 0.5431247790738777,
28
+ "eval_Emotional Typology_precision": 0.6008333333333333,
29
+ "eval_Emotional Typology_recall": 0.65625,
30
+ "eval_Emotions_macroF1": 0.530779524924724,
31
+ "eval_Emotions_precision": 0.5917211328976035,
32
+ "eval_Emotions_recall": 0.6085163418909165,
33
+ "eval_Intelligibility_macroF1": 0.6261437908496732,
34
+ "eval_Intelligibility_precision": 0.625,
35
+ "eval_Intelligibility_recall": 0.6328999638858794,
36
+ "eval_Intelligible Organization_macroF1": 0.5602359709424212,
37
+ "eval_Intelligible Organization_precision": 0.5534420289855072,
38
+ "eval_Intelligible Organization_recall": 0.6025789626195306,
39
+ "eval_Intelligible Position_macroF1": 0.6010933398284214,
40
+ "eval_Intelligible Position_precision": 0.5964783923519656,
41
+ "eval_Intelligible Position_recall": 0.6235632183908046,
42
+ "eval_Intelligible Relevance_macroF1": 0.528479573942976,
43
+ "eval_Intelligible Relevance_precision": 0.5802107728337236,
44
+ "eval_Intelligible Relevance_recall": 0.6112658080983873,
45
+ "eval_Not classified_macroF1": 0.4965675057208238,
46
+ "eval_Not classified_precision": 0.49318181818181817,
47
+ "eval_Not classified_recall": 0.5,
48
+ "eval_Orthography_macroF1": 0.5675185241191593,
49
+ "eval_Orthography_precision": 0.5641177243463408,
50
+ "eval_Orthography_recall": 0.7877358490566038,
51
+ "eval_Other_macroF1": 0.6333333333333333,
52
+ "eval_Other_precision": 0.6477093206951027,
53
+ "eval_Other_recall": 0.6220095693779903,
54
+ "eval_loss": 1.0271475315093994,
55
+ "eval_mean_F1": 0.5714117228056399,
56
+ "eval_mean_precision": 0.5990774054501132,
57
+ "eval_mean_recall": 0.6430466836503852,
58
+ "eval_runtime": 2.5376,
59
+ "eval_samples_per_second": 86.696,
60
+ "eval_steps_per_second": 5.517,
61
+ "step": 250
62
+ },
63
+ {
64
+ "epoch": 5.21,
65
+ "learning_rate": 2.483101851851852e-06,
66
+ "loss": 0.9858,
67
+ "step": 500
68
+ },
69
+ {
70
+ "epoch": 5.21,
71
+ "eval_Appropriateness_macroF1": 0.665130632415188,
72
+ "eval_Appropriateness_precision": 0.7096551724137932,
73
+ "eval_Appropriateness_recall": 0.6915322580645161,
74
+ "eval_Commitment_macroF1": 0.7509093975090939,
75
+ "eval_Commitment_precision": 0.7618189102564102,
76
+ "eval_Commitment_recall": 0.7435933277420557,
77
+ "eval_Committed Openness_macroF1": 0.7043862174872828,
78
+ "eval_Committed Openness_precision": 0.7002627627627627,
79
+ "eval_Committed Openness_recall": 0.7099567099567099,
80
+ "eval_Committed Seriousness_macroF1": 0.7135416666666666,
81
+ "eval_Committed Seriousness_precision": 0.6732215153267784,
82
+ "eval_Committed Seriousness_recall": 0.8294829482948295,
83
+ "eval_Emotional Intensity_macroF1": 0.679588485017508,
84
+ "eval_Emotional Intensity_precision": 0.6660829284826573,
85
+ "eval_Emotional Intensity_recall": 0.7041666666666666,
86
+ "eval_Emotional Typology_macroF1": 0.6851543561435789,
87
+ "eval_Emotional Typology_precision": 0.672855451512216,
88
+ "eval_Emotional Typology_recall": 0.7073863636363636,
89
+ "eval_Emotions_macroF1": 0.714746897409436,
90
+ "eval_Emotions_precision": 0.7212543554006968,
91
+ "eval_Emotions_recall": 0.709506134653057,
92
+ "eval_Intelligibility_macroF1": 0.634313796343138,
93
+ "eval_Intelligibility_precision": 0.6514896304874198,
94
+ "eval_Intelligibility_recall": 0.6299205489346335,
95
+ "eval_Intelligible Organization_macroF1": 0.5869602321215225,
96
+ "eval_Intelligible Organization_precision": 0.5771428571428572,
97
+ "eval_Intelligible Organization_recall": 0.676035931614025,
98
+ "eval_Intelligible Position_macroF1": 0.6466018283244253,
99
+ "eval_Intelligible Position_precision": 0.6393939393939394,
100
+ "eval_Intelligible Position_recall": 0.6580459770114943,
101
+ "eval_Intelligible Relevance_macroF1": 0.6084230126783319,
102
+ "eval_Intelligible Relevance_precision": 0.6041666666666666,
103
+ "eval_Intelligible Relevance_recall": 0.6160227404571296,
104
+ "eval_Not classified_macroF1": 0.48717948717948717,
105
+ "eval_Not classified_precision": 0.49292452830188677,
106
+ "eval_Not classified_recall": 0.4815668202764977,
107
+ "eval_Orthography_macroF1": 0.5915611814345991,
108
+ "eval_Orthography_precision": 0.5756166002067642,
109
+ "eval_Orthography_recall": 0.8018867924528301,
110
+ "eval_Other_macroF1": 0.6100006112843084,
111
+ "eval_Other_precision": 0.5868421052631579,
112
+ "eval_Other_recall": 0.7153110047846889,
113
+ "eval_loss": 0.9632763266563416,
114
+ "eval_mean_F1": 0.6484641287153262,
115
+ "eval_mean_precision": 0.6451948159727147,
116
+ "eval_mean_recall": 0.6910295874675355,
117
+ "eval_runtime": 2.3793,
118
+ "eval_samples_per_second": 92.466,
119
+ "eval_steps_per_second": 5.884,
120
+ "step": 500
121
+ },
122
+ {
123
+ "epoch": 7.81,
124
+ "eval_Appropriateness_macroF1": 0.6687855470056876,
125
+ "eval_Appropriateness_precision": 0.7210960960960962,
126
+ "eval_Appropriateness_recall": 0.6979166666666667,
127
+ "eval_Commitment_macroF1": 0.7442119098170052,
128
+ "eval_Commitment_precision": 0.778556095356457,
129
+ "eval_Commitment_recall": 0.7297549156648961,
130
+ "eval_Committed Openness_macroF1": 0.6861471861471862,
131
+ "eval_Committed Openness_precision": 0.6861471861471862,
132
+ "eval_Committed Openness_recall": 0.6861471861471862,
133
+ "eval_Committed Seriousness_macroF1": 0.7894233070112466,
134
+ "eval_Committed Seriousness_precision": 0.758078231292517,
135
+ "eval_Committed Seriousness_recall": 0.8338833883388339,
136
+ "eval_Emotional Intensity_macroF1": 0.671913835956918,
137
+ "eval_Emotional Intensity_precision": 0.665079365079365,
138
+ "eval_Emotional Intensity_recall": 0.6805555555555556,
139
+ "eval_Emotional Typology_macroF1": 0.6675863881224543,
140
+ "eval_Emotional Typology_precision": 0.6706795077581594,
141
+ "eval_Emotional Typology_recall": 0.6647727272727273,
142
+ "eval_Emotions_macroF1": 0.6727568690185514,
143
+ "eval_Emotions_precision": 0.6957771114442779,
144
+ "eval_Emotions_recall": 0.6615630477368801,
145
+ "eval_Intelligibility_macroF1": 0.6358605696781047,
146
+ "eval_Intelligibility_precision": 0.6641622415546267,
147
+ "eval_Intelligibility_recall": 0.6311845431563741,
148
+ "eval_Intelligible Organization_macroF1": 0.6031397786553557,
149
+ "eval_Intelligible Organization_precision": 0.5866545893719807,
150
+ "eval_Intelligible Organization_recall": 0.6663286004056794,
151
+ "eval_Intelligible Position_macroF1": 0.6535852713178294,
152
+ "eval_Intelligible Position_precision": 0.6494117647058824,
153
+ "eval_Intelligible Position_recall": 0.6586706646676661,
154
+ "eval_Intelligible Relevance_macroF1": 0.6247058823529412,
155
+ "eval_Intelligible Relevance_precision": 0.6265664160401002,
156
+ "eval_Intelligible Relevance_recall": 0.6230421162547859,
157
+ "eval_Not classified_macroF1": 0.46987951807228917,
158
+ "eval_Not classified_precision": 0.49242424242424243,
159
+ "eval_Not classified_recall": 0.44930875576036866,
160
+ "eval_Orthography_macroF1": 0.6369636963696369,
161
+ "eval_Orthography_precision": 0.6019345238095238,
162
+ "eval_Orthography_recall": 0.8231132075471699,
163
+ "eval_Other_macroF1": 0.6201803184346825,
164
+ "eval_Other_precision": 0.5941220238095238,
165
+ "eval_Other_recall": 0.7200956937799043,
166
+ "eval_loss": 1.0039398670196533,
167
+ "eval_mean_F1": 0.6532242912828492,
168
+ "eval_mean_precision": 0.6564778139207099,
169
+ "eval_mean_recall": 0.6804526477824782,
170
+ "eval_runtime": 2.3736,
171
+ "eval_samples_per_second": 92.687,
172
+ "eval_steps_per_second": 5.898,
173
+ "step": 750
174
+ },
175
+ {
176
+ "epoch": 10.42,
177
+ "learning_rate": 1.6439814814814818e-06,
178
+ "loss": 0.6344,
179
+ "step": 1000
180
+ },
181
+ {
182
+ "epoch": 10.42,
183
+ "eval_Appropriateness_macroF1": 0.7227215438335501,
184
+ "eval_Appropriateness_precision": 0.7335093454027324,
185
+ "eval_Appropriateness_recall": 0.7340389784946236,
186
+ "eval_Commitment_macroF1": 0.7471264367816092,
187
+ "eval_Commitment_precision": 0.7442557442557443,
188
+ "eval_Commitment_recall": 0.75062901873078,
189
+ "eval_Committed Openness_macroF1": 0.7027304072313857,
190
+ "eval_Committed Openness_precision": 0.6964285714285714,
191
+ "eval_Committed Openness_recall": 0.7164502164502164,
192
+ "eval_Committed Seriousness_macroF1": 0.7809150020502607,
193
+ "eval_Committed Seriousness_precision": 0.7471794871794872,
194
+ "eval_Committed Seriousness_recall": 0.8314081408140814,
195
+ "eval_Emotional Intensity_macroF1": 0.7108560413563481,
196
+ "eval_Emotional Intensity_precision": 0.6917723476647077,
197
+ "eval_Emotional Intensity_recall": 0.7583333333333333,
198
+ "eval_Emotional Typology_macroF1": 0.6484848484848484,
199
+ "eval_Emotional Typology_precision": 0.6385281385281385,
200
+ "eval_Emotional Typology_recall": 0.6818181818181819,
201
+ "eval_Emotions_macroF1": 0.7161290322580646,
202
+ "eval_Emotions_precision": 0.7097610135329686,
203
+ "eval_Emotions_recall": 0.7253325085060316,
204
+ "eval_Intelligibility_macroF1": 0.6560919540229884,
205
+ "eval_Intelligibility_precision": 0.6597222222222222,
206
+ "eval_Intelligibility_recall": 0.653665583243048,
207
+ "eval_Intelligible Organization_macroF1": 0.6163150492264416,
208
+ "eval_Intelligible Organization_precision": 0.5989583333333333,
209
+ "eval_Intelligible Organization_recall": 0.6541582150101419,
210
+ "eval_Intelligible Position_macroF1": 0.6809374637428935,
211
+ "eval_Intelligible Position_precision": 0.6711672473867596,
212
+ "eval_Intelligible Position_recall": 0.6964017991004497,
213
+ "eval_Intelligible Relevance_macroF1": 0.6410148436677545,
214
+ "eval_Intelligible Relevance_precision": 0.6337918251877865,
215
+ "eval_Intelligible Relevance_recall": 0.6591251885369533,
216
+ "eval_Not classified_macroF1": 0.4835680751173709,
217
+ "eval_Not classified_precision": 0.49282296650717705,
218
+ "eval_Not classified_recall": 0.47465437788018433,
219
+ "eval_Orthography_macroF1": 0.6474358974358975,
220
+ "eval_Orthography_precision": 0.6151960784313726,
221
+ "eval_Orthography_recall": 0.7216981132075472,
222
+ "eval_Other_macroF1": 0.6251457268406422,
223
+ "eval_Other_precision": 0.607843137254902,
224
+ "eval_Other_recall": 0.65311004784689,
225
+ "eval_loss": 1.042500615119934,
226
+ "eval_mean_F1": 0.6699623087178611,
227
+ "eval_mean_precision": 0.6600668898797073,
228
+ "eval_mean_recall": 0.6936302644980331,
229
+ "eval_runtime": 2.3751,
230
+ "eval_samples_per_second": 92.628,
231
+ "eval_steps_per_second": 5.895,
232
+ "step": 1000
233
+ },
234
+ {
235
+ "epoch": 13.02,
236
+ "eval_Appropriateness_macroF1": 0.7133461562325495,
237
+ "eval_Appropriateness_precision": 0.7343254138433828,
238
+ "eval_Appropriateness_recall": 0.729502688172043,
239
+ "eval_Commitment_macroF1": 0.7317334894156667,
240
+ "eval_Commitment_precision": 0.7467780183524075,
241
+ "eval_Commitment_recall": 0.7230453825365762,
242
+ "eval_Committed Openness_macroF1": 0.6888108477221735,
243
+ "eval_Committed Openness_precision": 0.6873065015479876,
244
+ "eval_Committed Openness_recall": 0.6904761904761905,
245
+ "eval_Committed Seriousness_macroF1": 0.8377037086714506,
246
+ "eval_Committed Seriousness_precision": 0.8296674522126211,
247
+ "eval_Committed Seriousness_recall": 0.8462596259625963,
248
+ "eval_Emotional Intensity_macroF1": 0.7021316792090431,
249
+ "eval_Emotional Intensity_precision": 0.68795683954055,
250
+ "eval_Emotional Intensity_recall": 0.725,
251
+ "eval_Emotional Typology_macroF1": 0.6717985439789951,
252
+ "eval_Emotional Typology_precision": 0.6619812583668006,
253
+ "eval_Emotional Typology_recall": 0.6875,
254
+ "eval_Emotions_macroF1": 0.7263898811886428,
255
+ "eval_Emotions_precision": 0.7332317073170731,
256
+ "eval_Emotions_recall": 0.7208475100525827,
257
+ "eval_Intelligibility_macroF1": 0.6780801872988002,
258
+ "eval_Intelligibility_precision": 0.7053571428571428,
259
+ "eval_Intelligibility_recall": 0.670278078728783,
260
+ "eval_Intelligible Organization_macroF1": 0.6212121212121213,
261
+ "eval_Intelligible Organization_precision": 0.6037228938783343,
262
+ "eval_Intelligible Organization_recall": 0.6566212691973341,
263
+ "eval_Intelligible Position_macroF1": 0.6759941089837997,
264
+ "eval_Intelligible Position_precision": 0.6702053602506091,
265
+ "eval_Intelligible Position_recall": 0.6832833583208395,
266
+ "eval_Intelligible Relevance_macroF1": 0.6514073348506237,
267
+ "eval_Intelligible Relevance_precision": 0.6504120879120879,
268
+ "eval_Intelligible Relevance_recall": 0.6524538809606684,
269
+ "eval_Not classified_macroF1": 0.48598130841121495,
270
+ "eval_Not classified_precision": 0.4928909952606635,
271
+ "eval_Not classified_recall": 0.4792626728110599,
272
+ "eval_Orthography_macroF1": 0.6974621827728466,
273
+ "eval_Orthography_precision": 0.6722488038277512,
274
+ "eval_Orthography_recall": 0.7334905660377358,
275
+ "eval_Other_macroF1": 0.6559274319674695,
276
+ "eval_Other_precision": 0.6498397435897436,
277
+ "eval_Other_recall": 0.6626794258373205,
278
+ "eval_loss": 1.1269534826278687,
279
+ "eval_mean_F1": 0.681284212993957,
280
+ "eval_mean_precision": 0.6804231584826539,
281
+ "eval_mean_recall": 0.690050046363838,
282
+ "eval_runtime": 2.3748,
283
+ "eval_samples_per_second": 92.64,
284
+ "eval_steps_per_second": 5.895,
285
+ "step": 1250
286
+ },
287
+ {
288
+ "epoch": 15.62,
289
+ "learning_rate": 8.048611111111111e-07,
290
+ "loss": 0.4806,
291
+ "step": 1500
292
+ },
293
+ {
294
+ "epoch": 15.62,
295
+ "eval_Appropriateness_macroF1": 0.7136304469100602,
296
+ "eval_Appropriateness_precision": 0.7265263157894737,
297
+ "eval_Appropriateness_recall": 0.7259744623655914,
298
+ "eval_Commitment_macroF1": 0.7376972530683812,
299
+ "eval_Commitment_precision": 0.7385510510510511,
300
+ "eval_Commitment_recall": 0.7368837946137359,
301
+ "eval_Committed Openness_macroF1": 0.6961904761904762,
302
+ "eval_Committed Openness_precision": 0.6914105886708626,
303
+ "eval_Committed Openness_recall": 0.7034632034632035,
304
+ "eval_Committed Seriousness_macroF1": 0.8271798900235664,
305
+ "eval_Committed Seriousness_precision": 0.8125,
306
+ "eval_Committed Seriousness_recall": 0.8437843784378438,
307
+ "eval_Emotional Intensity_macroF1": 0.715986019710948,
308
+ "eval_Emotional Intensity_precision": 0.7007193409908342,
309
+ "eval_Emotional Intensity_recall": 0.7402777777777778,
310
+ "eval_Emotional Typology_macroF1": 0.6764705882352942,
311
+ "eval_Emotional Typology_precision": 0.6652874564459931,
312
+ "eval_Emotional Typology_recall": 0.6960227272727273,
313
+ "eval_Emotions_macroF1": 0.7250000000000001,
314
+ "eval_Emotions_precision": 0.7274449942099168,
315
+ "eval_Emotions_recall": 0.7227549231879575,
316
+ "eval_Intelligibility_macroF1": 0.655406195207481,
317
+ "eval_Intelligibility_precision": 0.6635937957272462,
318
+ "eval_Intelligibility_recall": 0.6514084507042254,
319
+ "eval_Intelligible Organization_macroF1": 0.6212121212121213,
320
+ "eval_Intelligible Organization_precision": 0.6037228938783343,
321
+ "eval_Intelligible Organization_recall": 0.6566212691973341,
322
+ "eval_Intelligible Position_macroF1": 0.6520167212744323,
323
+ "eval_Intelligible Position_precision": 0.6427083333333333,
324
+ "eval_Intelligible Position_recall": 0.6711644177911045,
325
+ "eval_Intelligible Relevance_macroF1": 0.6329781508987191,
326
+ "eval_Intelligible Relevance_precision": 0.626731371954302,
327
+ "eval_Intelligible Relevance_recall": 0.6454345051630119,
328
+ "eval_Not classified_macroF1": 0.48598130841121495,
329
+ "eval_Not classified_precision": 0.4928909952606635,
330
+ "eval_Not classified_recall": 0.4792626728110599,
331
+ "eval_Orthography_macroF1": 0.6524486571879936,
332
+ "eval_Orthography_precision": 0.638095238095238,
333
+ "eval_Orthography_recall": 0.6709905660377358,
334
+ "eval_Other_macroF1": 0.6249573815206273,
335
+ "eval_Other_precision": 0.6309523809523809,
336
+ "eval_Other_recall": 0.6196172248803828,
337
+ "eval_loss": 1.1886050701141357,
338
+ "eval_mean_F1": 0.6726539435608083,
339
+ "eval_mean_precision": 0.6686524825971165,
340
+ "eval_mean_recall": 0.6831185981216922,
341
+ "eval_runtime": 2.3741,
342
+ "eval_samples_per_second": 92.666,
343
+ "eval_steps_per_second": 5.897,
344
+ "step": 1500
345
+ },
346
+ {
347
+ "epoch": 18.23,
348
+ "eval_Appropriateness_macroF1": 0.7089947089947091,
349
+ "eval_Appropriateness_precision": 0.7166666666666667,
350
+ "eval_Appropriateness_recall": 0.7184139784946236,
351
+ "eval_Commitment_macroF1": 0.7352832284339134,
352
+ "eval_Commitment_precision": 0.7337931034482759,
353
+ "eval_Commitment_recall": 0.7369303885937937,
354
+ "eval_Committed Openness_macroF1": 0.684019684019684,
355
+ "eval_Committed Openness_precision": 0.6788211788211789,
356
+ "eval_Committed Openness_recall": 0.6937229437229437,
357
+ "eval_Committed Seriousness_macroF1": 0.8075,
358
+ "eval_Committed Seriousness_precision": 0.7828282828282829,
359
+ "eval_Committed Seriousness_recall": 0.8388338833883389,
360
+ "eval_Emotional Intensity_macroF1": 0.715986019710948,
361
+ "eval_Emotional Intensity_precision": 0.7007193409908342,
362
+ "eval_Emotional Intensity_recall": 0.7402777777777778,
363
+ "eval_Emotional Typology_macroF1": 0.6764705882352942,
364
+ "eval_Emotional Typology_precision": 0.6652874564459931,
365
+ "eval_Emotional Typology_recall": 0.6960227272727273,
366
+ "eval_Emotions_macroF1": 0.7293122856619283,
367
+ "eval_Emotions_precision": 0.7331843337590465,
368
+ "eval_Emotions_recall": 0.7258995772760078,
369
+ "eval_Intelligibility_macroF1": 0.666206896551724,
370
+ "eval_Intelligibility_precision": 0.670045045045045,
371
+ "eval_Intelligibility_recall": 0.6635969664138678,
372
+ "eval_Intelligible Organization_macroF1": 0.6464646464646464,
373
+ "eval_Intelligible Organization_precision": 0.6248320859719823,
374
+ "eval_Intelligible Organization_recall": 0.6884960880904085,
375
+ "eval_Intelligible Position_macroF1": 0.6686656261124346,
376
+ "eval_Intelligible Position_precision": 0.6573200992555832,
377
+ "eval_Intelligible Position_recall": 0.6980259870064968,
378
+ "eval_Intelligible Relevance_macroF1": 0.6294346773344563,
379
+ "eval_Intelligible Relevance_precision": 0.6230611647644132,
380
+ "eval_Intelligible Relevance_recall": 0.646362687086669,
381
+ "eval_Not classified_macroF1": 0.48598130841121495,
382
+ "eval_Not classified_precision": 0.4928909952606635,
383
+ "eval_Not classified_recall": 0.4792626728110599,
384
+ "eval_Orthography_macroF1": 0.6974621827728466,
385
+ "eval_Orthography_precision": 0.6722488038277512,
386
+ "eval_Orthography_recall": 0.7334905660377358,
387
+ "eval_Other_macroF1": 0.6559274319674695,
388
+ "eval_Other_precision": 0.6498397435897436,
389
+ "eval_Other_recall": 0.6626794258373205,
390
+ "eval_loss": 1.1870639324188232,
391
+ "eval_mean_F1": 0.6791220917622336,
392
+ "eval_mean_precision": 0.6715384500482472,
393
+ "eval_mean_recall": 0.6944296907006979,
394
+ "eval_runtime": 2.3724,
395
+ "eval_samples_per_second": 92.734,
396
+ "eval_steps_per_second": 5.901,
397
+ "step": 1750
398
+ }
399
+ ],
400
+ "max_steps": 1920,
401
+ "num_train_epochs": 20,
402
+ "total_flos": 9734558105656692.0,
403
+ "trial_name": null,
404
+ "trial_params": null
405
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea47bcd63bcf9233291b64ac2c0916476130c1a9ceb58c9ff2ebafdc208e958b
3
+ size 3707