andrei-willenska commited on
Commit
3db8f86
·
1 Parent(s): 07278b0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-32/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-32/config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 1024,
9
+ "id2label": {
10
+ "0": "LABEL_0",
11
+ "1": "LABEL_1",
12
+ "2": "LABEL_2",
13
+ "3": "LABEL_3",
14
+ "4": "LABEL_4",
15
+ "5": "LABEL_5",
16
+ "6": "LABEL_6",
17
+ "7": "LABEL_7",
18
+ "8": "LABEL_8",
19
+ "9": "LABEL_9",
20
+ "10": "LABEL_10",
21
+ "11": "LABEL_11",
22
+ "12": "LABEL_12",
23
+ "13": "LABEL_13",
24
+ "14": "LABEL_14",
25
+ "15": "LABEL_15",
26
+ "16": "LABEL_16",
27
+ "17": "LABEL_17",
28
+ "18": "LABEL_18",
29
+ "19": "LABEL_19",
30
+ "20": "LABEL_20",
31
+ "21": "LABEL_21",
32
+ "22": "LABEL_22",
33
+ "23": "LABEL_23",
34
+ "24": "LABEL_24",
35
+ "25": "LABEL_25",
36
+ "26": "LABEL_26",
37
+ "27": "LABEL_27",
38
+ "28": "LABEL_28",
39
+ "29": "LABEL_29",
40
+ "30": "LABEL_30",
41
+ "31": "LABEL_31",
42
+ "32": "LABEL_32",
43
+ "33": "LABEL_33",
44
+ "34": "LABEL_34",
45
+ "35": "LABEL_35",
46
+ "36": "LABEL_36"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 4096,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_10": 10,
54
+ "LABEL_11": 11,
55
+ "LABEL_12": 12,
56
+ "LABEL_13": 13,
57
+ "LABEL_14": 14,
58
+ "LABEL_15": 15,
59
+ "LABEL_16": 16,
60
+ "LABEL_17": 17,
61
+ "LABEL_18": 18,
62
+ "LABEL_19": 19,
63
+ "LABEL_2": 2,
64
+ "LABEL_20": 20,
65
+ "LABEL_21": 21,
66
+ "LABEL_22": 22,
67
+ "LABEL_23": 23,
68
+ "LABEL_24": 24,
69
+ "LABEL_25": 25,
70
+ "LABEL_26": 26,
71
+ "LABEL_27": 27,
72
+ "LABEL_28": 28,
73
+ "LABEL_29": 29,
74
+ "LABEL_3": 3,
75
+ "LABEL_30": 30,
76
+ "LABEL_31": 31,
77
+ "LABEL_32": 32,
78
+ "LABEL_33": 33,
79
+ "LABEL_34": 34,
80
+ "LABEL_35": 35,
81
+ "LABEL_36": 36,
82
+ "LABEL_4": 4,
83
+ "LABEL_5": 5,
84
+ "LABEL_6": 6,
85
+ "LABEL_7": 7,
86
+ "LABEL_8": 8,
87
+ "LABEL_9": 9
88
+ },
89
+ "layer_norm_eps": 1e-07,
90
+ "legacy": true,
91
+ "max_position_embeddings": 512,
92
+ "max_relative_positions": -1,
93
+ "model_type": "deberta-v2",
94
+ "norm_rel_ebd": "layer_norm",
95
+ "num_attention_heads": 16,
96
+ "num_hidden_layers": 24,
97
+ "pad_token_id": 0,
98
+ "pooler_dropout": 0,
99
+ "pooler_hidden_act": "gelu",
100
+ "pooler_hidden_size": 1024,
101
+ "pos_att_type": [
102
+ "p2c",
103
+ "c2p"
104
+ ],
105
+ "position_biased_input": false,
106
+ "position_buckets": 256,
107
+ "problem_type": "multi_label_classification",
108
+ "relative_attention": true,
109
+ "share_att_key": true,
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.52.4",
112
+ "type_vocab_size": 0,
113
+ "vocab_size": 128100
114
+ }
checkpoint-32/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc6321b95e00d6e0eeb97b446ff7be984dac1361021e4d6b77b180d7c5156e9
3
+ size 1740447956
checkpoint-32/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc833adccfe16c618f5727621a4535618df80fa73954b47d6aa75203c07efa12
3
+ size 3481127617
checkpoint-32/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c6d6847e1bbb4063e75596bd7188b5ac39724581326534785704b5085d144fe
3
+ size 14645
checkpoint-32/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd2cb8f422941059c4c98358c0869d8d5f597300dbbfa691ce00f73f7193722
3
+ size 1465
checkpoint-32/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-32/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-32/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-32/trainer_state.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 32,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_f1_alb": 0.1607717041800643,
15
+ "eval_f1_aus": 0.0768,
16
+ "eval_f1_bel": 0.07342657342657342,
17
+ "eval_f1_bgr": 0.18902439024390244,
18
+ "eval_f1_can": 0.11006289308176101,
19
+ "eval_f1_cze": 0.11006289308176101,
20
+ "eval_f1_deu": 0.05815831987075929,
21
+ "eval_f1_dnk": 0.13131313131313133,
22
+ "eval_f1_esp": 0.08293460925039872,
23
+ "eval_f1_est": 0.09206349206349207,
24
+ "eval_f1_fra": 0.09508716323296355,
25
+ "eval_f1_fvey": 0.20059880239520958,
26
+ "eval_f1_gbr": 0.11006289308176101,
27
+ "eval_f1_grc": 0.1130298273155416,
28
+ "eval_f1_hrv": 0.08293460925039872,
29
+ "eval_f1_hun": 0.08293460925039872,
30
+ "eval_f1_isl": 0.0768,
31
+ "eval_f1_ita": 0.109375,
32
+ "eval_f1_jpn": 0.07987220447284345,
33
+ "eval_f1_kor": 0.11006289308176101,
34
+ "eval_f1_ltu": 0.10032362459546926,
35
+ "eval_f1_lux": 0.09508716323296355,
36
+ "eval_f1_lva": 0.0890302066772655,
37
+ "eval_f1_macro": 0.10584818936027048,
38
+ "eval_f1_micro": 0.10218027985681744,
39
+ "eval_f1_mkd": 0.07792207792207792,
40
+ "eval_f1_mne": 0.0972972972972973,
41
+ "eval_f1_nato": 0.22713864306784662,
42
+ "eval_f1_nld": 0.2318840579710145,
43
+ "eval_f1_nor": 0.11041009463722397,
44
+ "eval_f1_nzl": 0.048701298701298704,
45
+ "eval_f1_pol": 0.10708661417322834,
46
+ "eval_f1_prt": 0.0890302066772655,
47
+ "eval_f1_rou": 0.06752411575562701,
48
+ "eval_f1_svk": 0.14330218068535824,
49
+ "eval_f1_svn": 0.09487666034155598,
50
+ "eval_f1_tur": 0.06885245901639345,
51
+ "eval_f1_ukr": 0.06752411575562701,
52
+ "eval_f1_usa": 0.05501618122977346,
53
+ "eval_loss": 1.255063533782959,
54
+ "eval_precision_alb": 0.08771929824561403,
55
+ "eval_precision_aus": 0.03993344425956739,
56
+ "eval_precision_bel": 0.038112522686025406,
57
+ "eval_precision_bgr": 0.10472972972972973,
58
+ "eval_precision_can": 0.05823627287853577,
59
+ "eval_precision_cze": 0.05823627287853577,
60
+ "eval_precision_deu": 0.029950083194675542,
61
+ "eval_precision_dnk": 0.07046070460704607,
62
+ "eval_precision_esp": 0.04326123128119801,
63
+ "eval_precision_est": 0.048252911813643926,
64
+ "eval_precision_fra": 0.04991680532445923,
65
+ "eval_precision_fvey": 0.11148086522462562,
66
+ "eval_precision_gbr": 0.05823627287853577,
67
+ "eval_precision_grc": 0.059900166389351084,
68
+ "eval_precision_hrv": 0.04326123128119801,
69
+ "eval_precision_hun": 0.04326123128119801,
70
+ "eval_precision_isl": 0.03993344425956739,
71
+ "eval_precision_ita": 0.05785123966942149,
72
+ "eval_precision_jpn": 0.04159733777038269,
73
+ "eval_precision_kor": 0.05823627287853577,
74
+ "eval_precision_ltu": 0.05281090289608177,
75
+ "eval_precision_lux": 0.04991680532445923,
76
+ "eval_precision_lva": 0.04658901830282862,
77
+ "eval_precision_mkd": 0.04054054054054054,
78
+ "eval_precision_mne": 0.05113636363636364,
79
+ "eval_precision_nato": 0.1281198003327787,
80
+ "eval_precision_nld": 0.13157894736842105,
81
+ "eval_precision_nor": 0.05852842809364549,
82
+ "eval_precision_nzl": 0.024958402662229616,
83
+ "eval_precision_pol": 0.056572379367720464,
84
+ "eval_precision_prt": 0.04658901830282862,
85
+ "eval_precision_rou": 0.03494176372712146,
86
+ "eval_precision_svk": 0.07718120805369127,
87
+ "eval_precision_svn": 0.049800796812749,
88
+ "eval_precision_tur": 0.035653650254668934,
89
+ "eval_precision_ukr": 0.03494176372712146,
90
+ "eval_precision_usa": 0.028286189683860232,
91
+ "eval_recall_alb": 0.9615384615384616,
92
+ "eval_recall_aus": 1.0,
93
+ "eval_recall_bel": 1.0,
94
+ "eval_recall_bgr": 0.96875,
95
+ "eval_recall_can": 1.0,
96
+ "eval_recall_cze": 1.0,
97
+ "eval_recall_deu": 1.0,
98
+ "eval_recall_dnk": 0.9629629629629629,
99
+ "eval_recall_esp": 1.0,
100
+ "eval_recall_est": 1.0,
101
+ "eval_recall_fra": 1.0,
102
+ "eval_recall_fvey": 1.0,
103
+ "eval_recall_gbr": 1.0,
104
+ "eval_recall_grc": 1.0,
105
+ "eval_recall_hrv": 1.0,
106
+ "eval_recall_hun": 1.0,
107
+ "eval_recall_isl": 1.0,
108
+ "eval_recall_ita": 1.0,
109
+ "eval_recall_jpn": 1.0,
110
+ "eval_recall_kor": 1.0,
111
+ "eval_recall_ltu": 1.0,
112
+ "eval_recall_lux": 1.0,
113
+ "eval_recall_lva": 1.0,
114
+ "eval_recall_mkd": 1.0,
115
+ "eval_recall_mne": 1.0,
116
+ "eval_recall_nato": 1.0,
117
+ "eval_recall_nld": 0.975609756097561,
118
+ "eval_recall_nor": 0.9722222222222222,
119
+ "eval_recall_nzl": 1.0,
120
+ "eval_recall_pol": 1.0,
121
+ "eval_recall_prt": 1.0,
122
+ "eval_recall_rou": 1.0,
123
+ "eval_recall_svk": 1.0,
124
+ "eval_recall_svn": 1.0,
125
+ "eval_recall_tur": 1.0,
126
+ "eval_recall_ukr": 1.0,
127
+ "eval_recall_usa": 1.0,
128
+ "eval_runtime": 49.6571,
129
+ "eval_samples_per_second": 12.103,
130
+ "eval_steps_per_second": 0.201,
131
+ "step": 32
132
+ }
133
+ ],
134
+ "logging_steps": 500,
135
+ "max_steps": 96,
136
+ "num_input_tokens_seen": 0,
137
+ "num_train_epochs": 3,
138
+ "save_steps": 500,
139
+ "stateful_callbacks": {
140
+ "TrainerControl": {
141
+ "args": {
142
+ "should_epoch_stop": false,
143
+ "should_evaluate": false,
144
+ "should_log": false,
145
+ "should_save": true,
146
+ "should_training_stop": false
147
+ },
148
+ "attributes": {}
149
+ }
150
+ },
151
+ "total_flos": 1864095725568000.0,
152
+ "train_batch_size": 64,
153
+ "trial_name": null,
154
+ "trial_params": null
155
+ }
checkpoint-32/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d65cca4581314c1f96e4f97e717d8e4e02243ef563580ff9adca255b397e0e4
3
+ size 5649
checkpoint-64/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-64/config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 1024,
9
+ "id2label": {
10
+ "0": "LABEL_0",
11
+ "1": "LABEL_1",
12
+ "2": "LABEL_2",
13
+ "3": "LABEL_3",
14
+ "4": "LABEL_4",
15
+ "5": "LABEL_5",
16
+ "6": "LABEL_6",
17
+ "7": "LABEL_7",
18
+ "8": "LABEL_8",
19
+ "9": "LABEL_9",
20
+ "10": "LABEL_10",
21
+ "11": "LABEL_11",
22
+ "12": "LABEL_12",
23
+ "13": "LABEL_13",
24
+ "14": "LABEL_14",
25
+ "15": "LABEL_15",
26
+ "16": "LABEL_16",
27
+ "17": "LABEL_17",
28
+ "18": "LABEL_18",
29
+ "19": "LABEL_19",
30
+ "20": "LABEL_20",
31
+ "21": "LABEL_21",
32
+ "22": "LABEL_22",
33
+ "23": "LABEL_23",
34
+ "24": "LABEL_24",
35
+ "25": "LABEL_25",
36
+ "26": "LABEL_26",
37
+ "27": "LABEL_27",
38
+ "28": "LABEL_28",
39
+ "29": "LABEL_29",
40
+ "30": "LABEL_30",
41
+ "31": "LABEL_31",
42
+ "32": "LABEL_32",
43
+ "33": "LABEL_33",
44
+ "34": "LABEL_34",
45
+ "35": "LABEL_35",
46
+ "36": "LABEL_36"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 4096,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_10": 10,
54
+ "LABEL_11": 11,
55
+ "LABEL_12": 12,
56
+ "LABEL_13": 13,
57
+ "LABEL_14": 14,
58
+ "LABEL_15": 15,
59
+ "LABEL_16": 16,
60
+ "LABEL_17": 17,
61
+ "LABEL_18": 18,
62
+ "LABEL_19": 19,
63
+ "LABEL_2": 2,
64
+ "LABEL_20": 20,
65
+ "LABEL_21": 21,
66
+ "LABEL_22": 22,
67
+ "LABEL_23": 23,
68
+ "LABEL_24": 24,
69
+ "LABEL_25": 25,
70
+ "LABEL_26": 26,
71
+ "LABEL_27": 27,
72
+ "LABEL_28": 28,
73
+ "LABEL_29": 29,
74
+ "LABEL_3": 3,
75
+ "LABEL_30": 30,
76
+ "LABEL_31": 31,
77
+ "LABEL_32": 32,
78
+ "LABEL_33": 33,
79
+ "LABEL_34": 34,
80
+ "LABEL_35": 35,
81
+ "LABEL_36": 36,
82
+ "LABEL_4": 4,
83
+ "LABEL_5": 5,
84
+ "LABEL_6": 6,
85
+ "LABEL_7": 7,
86
+ "LABEL_8": 8,
87
+ "LABEL_9": 9
88
+ },
89
+ "layer_norm_eps": 1e-07,
90
+ "legacy": true,
91
+ "max_position_embeddings": 512,
92
+ "max_relative_positions": -1,
93
+ "model_type": "deberta-v2",
94
+ "norm_rel_ebd": "layer_norm",
95
+ "num_attention_heads": 16,
96
+ "num_hidden_layers": 24,
97
+ "pad_token_id": 0,
98
+ "pooler_dropout": 0,
99
+ "pooler_hidden_act": "gelu",
100
+ "pooler_hidden_size": 1024,
101
+ "pos_att_type": [
102
+ "p2c",
103
+ "c2p"
104
+ ],
105
+ "position_biased_input": false,
106
+ "position_buckets": 256,
107
+ "problem_type": "multi_label_classification",
108
+ "relative_attention": true,
109
+ "share_att_key": true,
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.52.4",
112
+ "type_vocab_size": 0,
113
+ "vocab_size": 128100
114
+ }
checkpoint-64/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959bb5f18d042edc608d314ec09e77bfea39259064a3d6316d9af2afb83d64b5
3
+ size 1740447956
checkpoint-64/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee91d3809c9977139eb624e0922ada91da12eafe5bc8905e905d59c8eb2184cd
3
+ size 3481127617
checkpoint-64/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a59a81a8220daedde48c34c6f98e96f82a2c61a8d9bab0c208a13ff4abf09d
3
+ size 14645
checkpoint-64/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fb37471ecb090778f6e1a7ad6bc4fba6286b245c3f5379dd66564b7677b905
3
+ size 1465
checkpoint-64/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-64/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-64/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-64/trainer_state.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 64,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_f1_alb": 0.1607717041800643,
15
+ "eval_f1_aus": 0.0768,
16
+ "eval_f1_bel": 0.07342657342657342,
17
+ "eval_f1_bgr": 0.18902439024390244,
18
+ "eval_f1_can": 0.11006289308176101,
19
+ "eval_f1_cze": 0.11006289308176101,
20
+ "eval_f1_deu": 0.05815831987075929,
21
+ "eval_f1_dnk": 0.13131313131313133,
22
+ "eval_f1_esp": 0.08293460925039872,
23
+ "eval_f1_est": 0.09206349206349207,
24
+ "eval_f1_fra": 0.09508716323296355,
25
+ "eval_f1_fvey": 0.20059880239520958,
26
+ "eval_f1_gbr": 0.11006289308176101,
27
+ "eval_f1_grc": 0.1130298273155416,
28
+ "eval_f1_hrv": 0.08293460925039872,
29
+ "eval_f1_hun": 0.08293460925039872,
30
+ "eval_f1_isl": 0.0768,
31
+ "eval_f1_ita": 0.109375,
32
+ "eval_f1_jpn": 0.07987220447284345,
33
+ "eval_f1_kor": 0.11006289308176101,
34
+ "eval_f1_ltu": 0.10032362459546926,
35
+ "eval_f1_lux": 0.09508716323296355,
36
+ "eval_f1_lva": 0.0890302066772655,
37
+ "eval_f1_macro": 0.10584818936027048,
38
+ "eval_f1_micro": 0.10218027985681744,
39
+ "eval_f1_mkd": 0.07792207792207792,
40
+ "eval_f1_mne": 0.0972972972972973,
41
+ "eval_f1_nato": 0.22713864306784662,
42
+ "eval_f1_nld": 0.2318840579710145,
43
+ "eval_f1_nor": 0.11041009463722397,
44
+ "eval_f1_nzl": 0.048701298701298704,
45
+ "eval_f1_pol": 0.10708661417322834,
46
+ "eval_f1_prt": 0.0890302066772655,
47
+ "eval_f1_rou": 0.06752411575562701,
48
+ "eval_f1_svk": 0.14330218068535824,
49
+ "eval_f1_svn": 0.09487666034155598,
50
+ "eval_f1_tur": 0.06885245901639345,
51
+ "eval_f1_ukr": 0.06752411575562701,
52
+ "eval_f1_usa": 0.05501618122977346,
53
+ "eval_loss": 1.255063533782959,
54
+ "eval_precision_alb": 0.08771929824561403,
55
+ "eval_precision_aus": 0.03993344425956739,
56
+ "eval_precision_bel": 0.038112522686025406,
57
+ "eval_precision_bgr": 0.10472972972972973,
58
+ "eval_precision_can": 0.05823627287853577,
59
+ "eval_precision_cze": 0.05823627287853577,
60
+ "eval_precision_deu": 0.029950083194675542,
61
+ "eval_precision_dnk": 0.07046070460704607,
62
+ "eval_precision_esp": 0.04326123128119801,
63
+ "eval_precision_est": 0.048252911813643926,
64
+ "eval_precision_fra": 0.04991680532445923,
65
+ "eval_precision_fvey": 0.11148086522462562,
66
+ "eval_precision_gbr": 0.05823627287853577,
67
+ "eval_precision_grc": 0.059900166389351084,
68
+ "eval_precision_hrv": 0.04326123128119801,
69
+ "eval_precision_hun": 0.04326123128119801,
70
+ "eval_precision_isl": 0.03993344425956739,
71
+ "eval_precision_ita": 0.05785123966942149,
72
+ "eval_precision_jpn": 0.04159733777038269,
73
+ "eval_precision_kor": 0.05823627287853577,
74
+ "eval_precision_ltu": 0.05281090289608177,
75
+ "eval_precision_lux": 0.04991680532445923,
76
+ "eval_precision_lva": 0.04658901830282862,
77
+ "eval_precision_mkd": 0.04054054054054054,
78
+ "eval_precision_mne": 0.05113636363636364,
79
+ "eval_precision_nato": 0.1281198003327787,
80
+ "eval_precision_nld": 0.13157894736842105,
81
+ "eval_precision_nor": 0.05852842809364549,
82
+ "eval_precision_nzl": 0.024958402662229616,
83
+ "eval_precision_pol": 0.056572379367720464,
84
+ "eval_precision_prt": 0.04658901830282862,
85
+ "eval_precision_rou": 0.03494176372712146,
86
+ "eval_precision_svk": 0.07718120805369127,
87
+ "eval_precision_svn": 0.049800796812749,
88
+ "eval_precision_tur": 0.035653650254668934,
89
+ "eval_precision_ukr": 0.03494176372712146,
90
+ "eval_precision_usa": 0.028286189683860232,
91
+ "eval_recall_alb": 0.9615384615384616,
92
+ "eval_recall_aus": 1.0,
93
+ "eval_recall_bel": 1.0,
94
+ "eval_recall_bgr": 0.96875,
95
+ "eval_recall_can": 1.0,
96
+ "eval_recall_cze": 1.0,
97
+ "eval_recall_deu": 1.0,
98
+ "eval_recall_dnk": 0.9629629629629629,
99
+ "eval_recall_esp": 1.0,
100
+ "eval_recall_est": 1.0,
101
+ "eval_recall_fra": 1.0,
102
+ "eval_recall_fvey": 1.0,
103
+ "eval_recall_gbr": 1.0,
104
+ "eval_recall_grc": 1.0,
105
+ "eval_recall_hrv": 1.0,
106
+ "eval_recall_hun": 1.0,
107
+ "eval_recall_isl": 1.0,
108
+ "eval_recall_ita": 1.0,
109
+ "eval_recall_jpn": 1.0,
110
+ "eval_recall_kor": 1.0,
111
+ "eval_recall_ltu": 1.0,
112
+ "eval_recall_lux": 1.0,
113
+ "eval_recall_lva": 1.0,
114
+ "eval_recall_mkd": 1.0,
115
+ "eval_recall_mne": 1.0,
116
+ "eval_recall_nato": 1.0,
117
+ "eval_recall_nld": 0.975609756097561,
118
+ "eval_recall_nor": 0.9722222222222222,
119
+ "eval_recall_nzl": 1.0,
120
+ "eval_recall_pol": 1.0,
121
+ "eval_recall_prt": 1.0,
122
+ "eval_recall_rou": 1.0,
123
+ "eval_recall_svk": 1.0,
124
+ "eval_recall_svn": 1.0,
125
+ "eval_recall_tur": 1.0,
126
+ "eval_recall_ukr": 1.0,
127
+ "eval_recall_usa": 1.0,
128
+ "eval_runtime": 49.6571,
129
+ "eval_samples_per_second": 12.103,
130
+ "eval_steps_per_second": 0.201,
131
+ "step": 32
132
+ },
133
+ {
134
+ "epoch": 2.0,
135
+ "eval_f1_alb": 0.16339869281045752,
136
+ "eval_f1_aus": 0.15584415584415584,
137
+ "eval_f1_bel": 0.13157894736842105,
138
+ "eval_f1_bgr": 0.19682539682539682,
139
+ "eval_f1_can": 0.11006289308176101,
140
+ "eval_f1_cze": 0.19435736677115986,
141
+ "eval_f1_deu": 0.11295681063122924,
142
+ "eval_f1_dnk": 0.16828478964401294,
143
+ "eval_f1_esp": 0.1488673139158576,
144
+ "eval_f1_est": 0.16666666666666666,
145
+ "eval_f1_fra": 0.19169329073482427,
146
+ "eval_f1_fvey": 0.20059880239520958,
147
+ "eval_f1_gbr": 0.219435736677116,
148
+ "eval_f1_grc": 0.225,
149
+ "eval_f1_hrv": 0.15584415584415584,
150
+ "eval_f1_hun": 0.16181229773462782,
151
+ "eval_f1_isl": 0.15584415584415584,
152
+ "eval_f1_ita": 0.18006430868167203,
153
+ "eval_f1_jpn": 0.15584415584415584,
154
+ "eval_f1_kor": 0.18808777429467086,
155
+ "eval_f1_ltu": 0.19745222929936307,
156
+ "eval_f1_lux": 0.17197452229299362,
157
+ "eval_f1_lva": 0.1794871794871795,
158
+ "eval_f1_macro": 0.16847450293714514,
159
+ "eval_f1_micro": 0.17011090720497885,
160
+ "eval_f1_mkd": 0.1498371335504886,
161
+ "eval_f1_mne": 0.17419354838709677,
162
+ "eval_f1_nato": 0.22713864306784662,
163
+ "eval_f1_nld": 0.24691358024691357,
164
+ "eval_f1_nor": 0.20754716981132076,
165
+ "eval_f1_nzl": 0.10067114093959731,
166
+ "eval_f1_pol": 0.20952380952380953,
167
+ "eval_f1_prt": 0.1794871794871795,
168
+ "eval_f1_rou": 0.13157894736842105,
169
+ "eval_f1_svk": 0.1503267973856209,
170
+ "eval_f1_svn": 0.1553398058252427,
171
+ "eval_f1_tur": 0.125,
172
+ "eval_f1_ukr": 0.1377049180327869,
173
+ "eval_f1_usa": 0.10631229235880399,
174
+ "eval_loss": 1.1108620166778564,
175
+ "eval_precision_alb": 0.08928571428571429,
176
+ "eval_precision_aus": 0.08450704225352113,
177
+ "eval_precision_bel": 0.0706713780918728,
178
+ "eval_precision_bgr": 0.10954063604240283,
179
+ "eval_precision_can": 0.05823627287853577,
180
+ "eval_precision_cze": 0.10915492957746478,
181
+ "eval_precision_deu": 0.06007067137809187,
182
+ "eval_precision_dnk": 0.09219858156028368,
183
+ "eval_precision_esp": 0.0812720848056537,
184
+ "eval_precision_est": 0.09187279151943463,
185
+ "eval_precision_fra": 0.10600706713780919,
186
+ "eval_precision_fvey": 0.11148086522462562,
187
+ "eval_precision_gbr": 0.12323943661971831,
188
+ "eval_precision_grc": 0.1267605633802817,
189
+ "eval_precision_hrv": 0.0851063829787234,
190
+ "eval_precision_hun": 0.08833922261484099,
191
+ "eval_precision_isl": 0.08450704225352113,
192
+ "eval_precision_ita": 0.0989399293286219,
193
+ "eval_precision_jpn": 0.08480565371024736,
194
+ "eval_precision_kor": 0.1056338028169014,
195
+ "eval_precision_ltu": 0.10954063604240283,
196
+ "eval_precision_lux": 0.09507042253521127,
197
+ "eval_precision_lva": 0.09859154929577464,
198
+ "eval_precision_mkd": 0.0812720848056537,
199
+ "eval_precision_mne": 0.09540636042402827,
200
+ "eval_precision_nato": 0.1281198003327787,
201
+ "eval_precision_nld": 0.1413427561837456,
202
+ "eval_precision_nor": 0.11702127659574468,
203
+ "eval_precision_nzl": 0.053003533568904596,
204
+ "eval_precision_pol": 0.11743772241992882,
205
+ "eval_precision_prt": 0.09859154929577464,
206
+ "eval_precision_rou": 0.0706713780918728,
207
+ "eval_precision_svk": 0.0812720848056537,
208
+ "eval_precision_svn": 0.08450704225352113,
209
+ "eval_precision_tur": 0.06713780918727916,
210
+ "eval_precision_ukr": 0.07394366197183098,
211
+ "eval_precision_usa": 0.056338028169014086,
212
+ "eval_recall_alb": 0.9615384615384616,
213
+ "eval_recall_aus": 1.0,
214
+ "eval_recall_bel": 0.9523809523809523,
215
+ "eval_recall_bgr": 0.96875,
216
+ "eval_recall_can": 1.0,
217
+ "eval_recall_cze": 0.8857142857142857,
218
+ "eval_recall_deu": 0.9444444444444444,
219
+ "eval_recall_dnk": 0.9629629629629629,
220
+ "eval_recall_esp": 0.8846153846153846,
221
+ "eval_recall_est": 0.896551724137931,
222
+ "eval_recall_fra": 1.0,
223
+ "eval_recall_fvey": 1.0,
224
+ "eval_recall_gbr": 1.0,
225
+ "eval_recall_grc": 1.0,
226
+ "eval_recall_hrv": 0.9230769230769231,
227
+ "eval_recall_hun": 0.9615384615384616,
228
+ "eval_recall_isl": 1.0,
229
+ "eval_recall_ita": 1.0,
230
+ "eval_recall_jpn": 0.96,
231
+ "eval_recall_kor": 0.8571428571428571,
232
+ "eval_recall_ltu": 1.0,
233
+ "eval_recall_lux": 0.9,
234
+ "eval_recall_lva": 1.0,
235
+ "eval_recall_mkd": 0.9583333333333334,
236
+ "eval_recall_mne": 1.0,
237
+ "eval_recall_nato": 1.0,
238
+ "eval_recall_nld": 0.975609756097561,
239
+ "eval_recall_nor": 0.9166666666666666,
240
+ "eval_recall_nzl": 1.0,
241
+ "eval_recall_pol": 0.9705882352941176,
242
+ "eval_recall_prt": 1.0,
243
+ "eval_recall_rou": 0.9523809523809523,
244
+ "eval_recall_svk": 1.0,
245
+ "eval_recall_svn": 0.96,
246
+ "eval_recall_tur": 0.9047619047619048,
247
+ "eval_recall_ukr": 1.0,
248
+ "eval_recall_usa": 0.9411764705882353,
249
+ "eval_runtime": 49.6461,
250
+ "eval_samples_per_second": 12.106,
251
+ "eval_steps_per_second": 0.201,
252
+ "step": 64
253
+ }
254
+ ],
255
+ "logging_steps": 500,
256
+ "max_steps": 96,
257
+ "num_input_tokens_seen": 0,
258
+ "num_train_epochs": 3,
259
+ "save_steps": 500,
260
+ "stateful_callbacks": {
261
+ "TrainerControl": {
262
+ "args": {
263
+ "should_epoch_stop": false,
264
+ "should_evaluate": false,
265
+ "should_log": false,
266
+ "should_save": true,
267
+ "should_training_stop": false
268
+ },
269
+ "attributes": {}
270
+ }
271
+ },
272
+ "total_flos": 3728191451136000.0,
273
+ "train_batch_size": 64,
274
+ "trial_name": null,
275
+ "trial_params": null
276
+ }
checkpoint-64/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d65cca4581314c1f96e4f97e717d8e4e02243ef563580ff9adca255b397e0e4
3
+ size 5649
checkpoint-96/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-96/config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 1024,
9
+ "id2label": {
10
+ "0": "LABEL_0",
11
+ "1": "LABEL_1",
12
+ "2": "LABEL_2",
13
+ "3": "LABEL_3",
14
+ "4": "LABEL_4",
15
+ "5": "LABEL_5",
16
+ "6": "LABEL_6",
17
+ "7": "LABEL_7",
18
+ "8": "LABEL_8",
19
+ "9": "LABEL_9",
20
+ "10": "LABEL_10",
21
+ "11": "LABEL_11",
22
+ "12": "LABEL_12",
23
+ "13": "LABEL_13",
24
+ "14": "LABEL_14",
25
+ "15": "LABEL_15",
26
+ "16": "LABEL_16",
27
+ "17": "LABEL_17",
28
+ "18": "LABEL_18",
29
+ "19": "LABEL_19",
30
+ "20": "LABEL_20",
31
+ "21": "LABEL_21",
32
+ "22": "LABEL_22",
33
+ "23": "LABEL_23",
34
+ "24": "LABEL_24",
35
+ "25": "LABEL_25",
36
+ "26": "LABEL_26",
37
+ "27": "LABEL_27",
38
+ "28": "LABEL_28",
39
+ "29": "LABEL_29",
40
+ "30": "LABEL_30",
41
+ "31": "LABEL_31",
42
+ "32": "LABEL_32",
43
+ "33": "LABEL_33",
44
+ "34": "LABEL_34",
45
+ "35": "LABEL_35",
46
+ "36": "LABEL_36"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 4096,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_10": 10,
54
+ "LABEL_11": 11,
55
+ "LABEL_12": 12,
56
+ "LABEL_13": 13,
57
+ "LABEL_14": 14,
58
+ "LABEL_15": 15,
59
+ "LABEL_16": 16,
60
+ "LABEL_17": 17,
61
+ "LABEL_18": 18,
62
+ "LABEL_19": 19,
63
+ "LABEL_2": 2,
64
+ "LABEL_20": 20,
65
+ "LABEL_21": 21,
66
+ "LABEL_22": 22,
67
+ "LABEL_23": 23,
68
+ "LABEL_24": 24,
69
+ "LABEL_25": 25,
70
+ "LABEL_26": 26,
71
+ "LABEL_27": 27,
72
+ "LABEL_28": 28,
73
+ "LABEL_29": 29,
74
+ "LABEL_3": 3,
75
+ "LABEL_30": 30,
76
+ "LABEL_31": 31,
77
+ "LABEL_32": 32,
78
+ "LABEL_33": 33,
79
+ "LABEL_34": 34,
80
+ "LABEL_35": 35,
81
+ "LABEL_36": 36,
82
+ "LABEL_4": 4,
83
+ "LABEL_5": 5,
84
+ "LABEL_6": 6,
85
+ "LABEL_7": 7,
86
+ "LABEL_8": 8,
87
+ "LABEL_9": 9
88
+ },
89
+ "layer_norm_eps": 1e-07,
90
+ "legacy": true,
91
+ "max_position_embeddings": 512,
92
+ "max_relative_positions": -1,
93
+ "model_type": "deberta-v2",
94
+ "norm_rel_ebd": "layer_norm",
95
+ "num_attention_heads": 16,
96
+ "num_hidden_layers": 24,
97
+ "pad_token_id": 0,
98
+ "pooler_dropout": 0,
99
+ "pooler_hidden_act": "gelu",
100
+ "pooler_hidden_size": 1024,
101
+ "pos_att_type": [
102
+ "p2c",
103
+ "c2p"
104
+ ],
105
+ "position_biased_input": false,
106
+ "position_buckets": 256,
107
+ "problem_type": "multi_label_classification",
108
+ "relative_attention": true,
109
+ "share_att_key": true,
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.52.4",
112
+ "type_vocab_size": 0,
113
+ "vocab_size": 128100
114
+ }
checkpoint-96/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cafd28c690b6561f4755abd3e2a2ccf2578e6ae7d0634264ad24ee840fb7ddf
3
+ size 1740447956
checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad46f5d4d0d7bcd256a022122e1bd934ac26b5ca4d26a324469ea56c26f0157
3
+ size 3481127617
checkpoint-96/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2244674d301d8df9d5711d1475115067d25378cff610f8c2546878dbd21b49fa
3
+ size 14645
checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a3db700992b9d68bffe4aa51af55d976bb97c6851c4617b52889d4a4a7403e9
3
+ size 1465
checkpoint-96/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-96/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-96/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,397 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 96,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_f1_alb": 0.1607717041800643,
15
+ "eval_f1_aus": 0.0768,
16
+ "eval_f1_bel": 0.07342657342657342,
17
+ "eval_f1_bgr": 0.18902439024390244,
18
+ "eval_f1_can": 0.11006289308176101,
19
+ "eval_f1_cze": 0.11006289308176101,
20
+ "eval_f1_deu": 0.05815831987075929,
21
+ "eval_f1_dnk": 0.13131313131313133,
22
+ "eval_f1_esp": 0.08293460925039872,
23
+ "eval_f1_est": 0.09206349206349207,
24
+ "eval_f1_fra": 0.09508716323296355,
25
+ "eval_f1_fvey": 0.20059880239520958,
26
+ "eval_f1_gbr": 0.11006289308176101,
27
+ "eval_f1_grc": 0.1130298273155416,
28
+ "eval_f1_hrv": 0.08293460925039872,
29
+ "eval_f1_hun": 0.08293460925039872,
30
+ "eval_f1_isl": 0.0768,
31
+ "eval_f1_ita": 0.109375,
32
+ "eval_f1_jpn": 0.07987220447284345,
33
+ "eval_f1_kor": 0.11006289308176101,
34
+ "eval_f1_ltu": 0.10032362459546926,
35
+ "eval_f1_lux": 0.09508716323296355,
36
+ "eval_f1_lva": 0.0890302066772655,
37
+ "eval_f1_macro": 0.10584818936027048,
38
+ "eval_f1_micro": 0.10218027985681744,
39
+ "eval_f1_mkd": 0.07792207792207792,
40
+ "eval_f1_mne": 0.0972972972972973,
41
+ "eval_f1_nato": 0.22713864306784662,
42
+ "eval_f1_nld": 0.2318840579710145,
43
+ "eval_f1_nor": 0.11041009463722397,
44
+ "eval_f1_nzl": 0.048701298701298704,
45
+ "eval_f1_pol": 0.10708661417322834,
46
+ "eval_f1_prt": 0.0890302066772655,
47
+ "eval_f1_rou": 0.06752411575562701,
48
+ "eval_f1_svk": 0.14330218068535824,
49
+ "eval_f1_svn": 0.09487666034155598,
50
+ "eval_f1_tur": 0.06885245901639345,
51
+ "eval_f1_ukr": 0.06752411575562701,
52
+ "eval_f1_usa": 0.05501618122977346,
53
+ "eval_loss": 1.255063533782959,
54
+ "eval_precision_alb": 0.08771929824561403,
55
+ "eval_precision_aus": 0.03993344425956739,
56
+ "eval_precision_bel": 0.038112522686025406,
57
+ "eval_precision_bgr": 0.10472972972972973,
58
+ "eval_precision_can": 0.05823627287853577,
59
+ "eval_precision_cze": 0.05823627287853577,
60
+ "eval_precision_deu": 0.029950083194675542,
61
+ "eval_precision_dnk": 0.07046070460704607,
62
+ "eval_precision_esp": 0.04326123128119801,
63
+ "eval_precision_est": 0.048252911813643926,
64
+ "eval_precision_fra": 0.04991680532445923,
65
+ "eval_precision_fvey": 0.11148086522462562,
66
+ "eval_precision_gbr": 0.05823627287853577,
67
+ "eval_precision_grc": 0.059900166389351084,
68
+ "eval_precision_hrv": 0.04326123128119801,
69
+ "eval_precision_hun": 0.04326123128119801,
70
+ "eval_precision_isl": 0.03993344425956739,
71
+ "eval_precision_ita": 0.05785123966942149,
72
+ "eval_precision_jpn": 0.04159733777038269,
73
+ "eval_precision_kor": 0.05823627287853577,
74
+ "eval_precision_ltu": 0.05281090289608177,
75
+ "eval_precision_lux": 0.04991680532445923,
76
+ "eval_precision_lva": 0.04658901830282862,
77
+ "eval_precision_mkd": 0.04054054054054054,
78
+ "eval_precision_mne": 0.05113636363636364,
79
+ "eval_precision_nato": 0.1281198003327787,
80
+ "eval_precision_nld": 0.13157894736842105,
81
+ "eval_precision_nor": 0.05852842809364549,
82
+ "eval_precision_nzl": 0.024958402662229616,
83
+ "eval_precision_pol": 0.056572379367720464,
84
+ "eval_precision_prt": 0.04658901830282862,
85
+ "eval_precision_rou": 0.03494176372712146,
86
+ "eval_precision_svk": 0.07718120805369127,
87
+ "eval_precision_svn": 0.049800796812749,
88
+ "eval_precision_tur": 0.035653650254668934,
89
+ "eval_precision_ukr": 0.03494176372712146,
90
+ "eval_precision_usa": 0.028286189683860232,
91
+ "eval_recall_alb": 0.9615384615384616,
92
+ "eval_recall_aus": 1.0,
93
+ "eval_recall_bel": 1.0,
94
+ "eval_recall_bgr": 0.96875,
95
+ "eval_recall_can": 1.0,
96
+ "eval_recall_cze": 1.0,
97
+ "eval_recall_deu": 1.0,
98
+ "eval_recall_dnk": 0.9629629629629629,
99
+ "eval_recall_esp": 1.0,
100
+ "eval_recall_est": 1.0,
101
+ "eval_recall_fra": 1.0,
102
+ "eval_recall_fvey": 1.0,
103
+ "eval_recall_gbr": 1.0,
104
+ "eval_recall_grc": 1.0,
105
+ "eval_recall_hrv": 1.0,
106
+ "eval_recall_hun": 1.0,
107
+ "eval_recall_isl": 1.0,
108
+ "eval_recall_ita": 1.0,
109
+ "eval_recall_jpn": 1.0,
110
+ "eval_recall_kor": 1.0,
111
+ "eval_recall_ltu": 1.0,
112
+ "eval_recall_lux": 1.0,
113
+ "eval_recall_lva": 1.0,
114
+ "eval_recall_mkd": 1.0,
115
+ "eval_recall_mne": 1.0,
116
+ "eval_recall_nato": 1.0,
117
+ "eval_recall_nld": 0.975609756097561,
118
+ "eval_recall_nor": 0.9722222222222222,
119
+ "eval_recall_nzl": 1.0,
120
+ "eval_recall_pol": 1.0,
121
+ "eval_recall_prt": 1.0,
122
+ "eval_recall_rou": 1.0,
123
+ "eval_recall_svk": 1.0,
124
+ "eval_recall_svn": 1.0,
125
+ "eval_recall_tur": 1.0,
126
+ "eval_recall_ukr": 1.0,
127
+ "eval_recall_usa": 1.0,
128
+ "eval_runtime": 49.6571,
129
+ "eval_samples_per_second": 12.103,
130
+ "eval_steps_per_second": 0.201,
131
+ "step": 32
132
+ },
133
+ {
134
+ "epoch": 2.0,
135
+ "eval_f1_alb": 0.16339869281045752,
136
+ "eval_f1_aus": 0.15584415584415584,
137
+ "eval_f1_bel": 0.13157894736842105,
138
+ "eval_f1_bgr": 0.19682539682539682,
139
+ "eval_f1_can": 0.11006289308176101,
140
+ "eval_f1_cze": 0.19435736677115986,
141
+ "eval_f1_deu": 0.11295681063122924,
142
+ "eval_f1_dnk": 0.16828478964401294,
143
+ "eval_f1_esp": 0.1488673139158576,
144
+ "eval_f1_est": 0.16666666666666666,
145
+ "eval_f1_fra": 0.19169329073482427,
146
+ "eval_f1_fvey": 0.20059880239520958,
147
+ "eval_f1_gbr": 0.219435736677116,
148
+ "eval_f1_grc": 0.225,
149
+ "eval_f1_hrv": 0.15584415584415584,
150
+ "eval_f1_hun": 0.16181229773462782,
151
+ "eval_f1_isl": 0.15584415584415584,
152
+ "eval_f1_ita": 0.18006430868167203,
153
+ "eval_f1_jpn": 0.15584415584415584,
154
+ "eval_f1_kor": 0.18808777429467086,
155
+ "eval_f1_ltu": 0.19745222929936307,
156
+ "eval_f1_lux": 0.17197452229299362,
157
+ "eval_f1_lva": 0.1794871794871795,
158
+ "eval_f1_macro": 0.16847450293714514,
159
+ "eval_f1_micro": 0.17011090720497885,
160
+ "eval_f1_mkd": 0.1498371335504886,
161
+ "eval_f1_mne": 0.17419354838709677,
162
+ "eval_f1_nato": 0.22713864306784662,
163
+ "eval_f1_nld": 0.24691358024691357,
164
+ "eval_f1_nor": 0.20754716981132076,
165
+ "eval_f1_nzl": 0.10067114093959731,
166
+ "eval_f1_pol": 0.20952380952380953,
167
+ "eval_f1_prt": 0.1794871794871795,
168
+ "eval_f1_rou": 0.13157894736842105,
169
+ "eval_f1_svk": 0.1503267973856209,
170
+ "eval_f1_svn": 0.1553398058252427,
171
+ "eval_f1_tur": 0.125,
172
+ "eval_f1_ukr": 0.1377049180327869,
173
+ "eval_f1_usa": 0.10631229235880399,
174
+ "eval_loss": 1.1108620166778564,
175
+ "eval_precision_alb": 0.08928571428571429,
176
+ "eval_precision_aus": 0.08450704225352113,
177
+ "eval_precision_bel": 0.0706713780918728,
178
+ "eval_precision_bgr": 0.10954063604240283,
179
+ "eval_precision_can": 0.05823627287853577,
180
+ "eval_precision_cze": 0.10915492957746478,
181
+ "eval_precision_deu": 0.06007067137809187,
182
+ "eval_precision_dnk": 0.09219858156028368,
183
+ "eval_precision_esp": 0.0812720848056537,
184
+ "eval_precision_est": 0.09187279151943463,
185
+ "eval_precision_fra": 0.10600706713780919,
186
+ "eval_precision_fvey": 0.11148086522462562,
187
+ "eval_precision_gbr": 0.12323943661971831,
188
+ "eval_precision_grc": 0.1267605633802817,
189
+ "eval_precision_hrv": 0.0851063829787234,
190
+ "eval_precision_hun": 0.08833922261484099,
191
+ "eval_precision_isl": 0.08450704225352113,
192
+ "eval_precision_ita": 0.0989399293286219,
193
+ "eval_precision_jpn": 0.08480565371024736,
194
+ "eval_precision_kor": 0.1056338028169014,
195
+ "eval_precision_ltu": 0.10954063604240283,
196
+ "eval_precision_lux": 0.09507042253521127,
197
+ "eval_precision_lva": 0.09859154929577464,
198
+ "eval_precision_mkd": 0.0812720848056537,
199
+ "eval_precision_mne": 0.09540636042402827,
200
+ "eval_precision_nato": 0.1281198003327787,
201
+ "eval_precision_nld": 0.1413427561837456,
202
+ "eval_precision_nor": 0.11702127659574468,
203
+ "eval_precision_nzl": 0.053003533568904596,
204
+ "eval_precision_pol": 0.11743772241992882,
205
+ "eval_precision_prt": 0.09859154929577464,
206
+ "eval_precision_rou": 0.0706713780918728,
207
+ "eval_precision_svk": 0.0812720848056537,
208
+ "eval_precision_svn": 0.08450704225352113,
209
+ "eval_precision_tur": 0.06713780918727916,
210
+ "eval_precision_ukr": 0.07394366197183098,
211
+ "eval_precision_usa": 0.056338028169014086,
212
+ "eval_recall_alb": 0.9615384615384616,
213
+ "eval_recall_aus": 1.0,
214
+ "eval_recall_bel": 0.9523809523809523,
215
+ "eval_recall_bgr": 0.96875,
216
+ "eval_recall_can": 1.0,
217
+ "eval_recall_cze": 0.8857142857142857,
218
+ "eval_recall_deu": 0.9444444444444444,
219
+ "eval_recall_dnk": 0.9629629629629629,
220
+ "eval_recall_esp": 0.8846153846153846,
221
+ "eval_recall_est": 0.896551724137931,
222
+ "eval_recall_fra": 1.0,
223
+ "eval_recall_fvey": 1.0,
224
+ "eval_recall_gbr": 1.0,
225
+ "eval_recall_grc": 1.0,
226
+ "eval_recall_hrv": 0.9230769230769231,
227
+ "eval_recall_hun": 0.9615384615384616,
228
+ "eval_recall_isl": 1.0,
229
+ "eval_recall_ita": 1.0,
230
+ "eval_recall_jpn": 0.96,
231
+ "eval_recall_kor": 0.8571428571428571,
232
+ "eval_recall_ltu": 1.0,
233
+ "eval_recall_lux": 0.9,
234
+ "eval_recall_lva": 1.0,
235
+ "eval_recall_mkd": 0.9583333333333334,
236
+ "eval_recall_mne": 1.0,
237
+ "eval_recall_nato": 1.0,
238
+ "eval_recall_nld": 0.975609756097561,
239
+ "eval_recall_nor": 0.9166666666666666,
240
+ "eval_recall_nzl": 1.0,
241
+ "eval_recall_pol": 0.9705882352941176,
242
+ "eval_recall_prt": 1.0,
243
+ "eval_recall_rou": 0.9523809523809523,
244
+ "eval_recall_svk": 1.0,
245
+ "eval_recall_svn": 0.96,
246
+ "eval_recall_tur": 0.9047619047619048,
247
+ "eval_recall_ukr": 1.0,
248
+ "eval_recall_usa": 0.9411764705882353,
249
+ "eval_runtime": 49.6461,
250
+ "eval_samples_per_second": 12.106,
251
+ "eval_steps_per_second": 0.201,
252
+ "step": 64
253
+ },
254
+ {
255
+ "epoch": 3.0,
256
+ "eval_f1_alb": 0.16339869281045752,
257
+ "eval_f1_aus": 0.15584415584415584,
258
+ "eval_f1_bel": 0.13245033112582782,
259
+ "eval_f1_bgr": 0.19808306709265175,
260
+ "eval_f1_can": 0.2066869300911854,
261
+ "eval_f1_cze": 0.19808306709265175,
262
+ "eval_f1_deu": 0.11409395973154363,
263
+ "eval_f1_dnk": 0.16883116883116883,
264
+ "eval_f1_esp": 0.14838709677419354,
265
+ "eval_f1_est": 0.17252396166134185,
266
+ "eval_f1_fra": 0.19230769230769232,
267
+ "eval_f1_fvey": 0.30112359550561796,
268
+ "eval_f1_gbr": 0.21875,
269
+ "eval_f1_grc": 0.225,
270
+ "eval_f1_hrv": 0.1563517915309446,
271
+ "eval_f1_hun": 0.16129032258064516,
272
+ "eval_f1_isl": 0.1563517915309446,
273
+ "eval_f1_ita": 0.17891373801916932,
274
+ "eval_f1_jpn": 0.1563517915309446,
275
+ "eval_f1_kor": 0.1892744479495268,
276
+ "eval_f1_ltu": 0.19935691318327975,
277
+ "eval_f1_lux": 0.16927899686520376,
278
+ "eval_f1_lva": 0.18122977346278318,
279
+ "eval_f1_macro": 0.17693222466346978,
280
+ "eval_f1_micro": 0.1810762560571283,
281
+ "eval_f1_mkd": 0.15081967213114755,
282
+ "eval_f1_mne": 0.1758957654723127,
283
+ "eval_f1_nato": 0.32217573221757323,
284
+ "eval_f1_nld": 0.25,
285
+ "eval_f1_nor": 0.2082018927444795,
286
+ "eval_f1_nzl": 0.0945945945945946,
287
+ "eval_f1_pol": 0.2138364779874214,
288
+ "eval_f1_prt": 0.17532467532467533,
289
+ "eval_f1_rou": 0.132013201320132,
290
+ "eval_f1_svk": 0.1513157894736842,
291
+ "eval_f1_svn": 0.15737704918032788,
292
+ "eval_f1_tur": 0.12624584717607973,
293
+ "eval_f1_ukr": 0.1377049180327869,
294
+ "eval_f1_usa": 0.10702341137123746,
295
+ "eval_loss": 1.0499567985534668,
296
+ "eval_precision_alb": 0.08928571428571429,
297
+ "eval_precision_aus": 0.08450704225352113,
298
+ "eval_precision_bel": 0.0711743772241993,
299
+ "eval_precision_bgr": 0.1103202846975089,
300
+ "eval_precision_can": 0.11564625850340136,
301
+ "eval_precision_cze": 0.11151079136690648,
302
+ "eval_precision_deu": 0.060714285714285714,
303
+ "eval_precision_dnk": 0.09252669039145907,
304
+ "eval_precision_esp": 0.08098591549295775,
305
+ "eval_precision_est": 0.09507042253521127,
306
+ "eval_precision_fra": 0.10638297872340426,
307
+ "eval_precision_fvey": 0.17724867724867724,
308
+ "eval_precision_gbr": 0.12280701754385964,
309
+ "eval_precision_grc": 0.1267605633802817,
310
+ "eval_precision_hrv": 0.08540925266903915,
311
+ "eval_precision_hun": 0.0880281690140845,
312
+ "eval_precision_isl": 0.08480565371024736,
313
+ "eval_precision_ita": 0.09824561403508772,
314
+ "eval_precision_jpn": 0.0851063829787234,
315
+ "eval_precision_kor": 0.10638297872340426,
316
+ "eval_precision_ltu": 0.11071428571428571,
317
+ "eval_precision_lux": 0.09342560553633218,
318
+ "eval_precision_lva": 0.099644128113879,
319
+ "eval_precision_mkd": 0.08185053380782918,
320
+ "eval_precision_mne": 0.09642857142857143,
321
+ "eval_precision_nato": 0.19201995012468828,
322
+ "eval_precision_nld": 0.14336917562724014,
323
+ "eval_precision_nor": 0.11743772241992882,
324
+ "eval_precision_nzl": 0.0498220640569395,
325
+ "eval_precision_pol": 0.11971830985915492,
326
+ "eval_precision_prt": 0.09642857142857143,
327
+ "eval_precision_rou": 0.07092198581560284,
328
+ "eval_precision_svk": 0.08185053380782918,
329
+ "eval_precision_svn": 0.08571428571428572,
330
+ "eval_precision_tur": 0.06785714285714285,
331
+ "eval_precision_ukr": 0.07394366197183098,
332
+ "eval_precision_usa": 0.05673758865248227,
333
+ "eval_recall_alb": 0.9615384615384616,
334
+ "eval_recall_aus": 1.0,
335
+ "eval_recall_bel": 0.9523809523809523,
336
+ "eval_recall_bgr": 0.96875,
337
+ "eval_recall_can": 0.9714285714285714,
338
+ "eval_recall_cze": 0.8857142857142857,
339
+ "eval_recall_deu": 0.9444444444444444,
340
+ "eval_recall_dnk": 0.9629629629629629,
341
+ "eval_recall_esp": 0.8846153846153846,
342
+ "eval_recall_est": 0.9310344827586207,
343
+ "eval_recall_fra": 1.0,
344
+ "eval_recall_fvey": 1.0,
345
+ "eval_recall_gbr": 1.0,
346
+ "eval_recall_grc": 1.0,
347
+ "eval_recall_hrv": 0.9230769230769231,
348
+ "eval_recall_hun": 0.9615384615384616,
349
+ "eval_recall_isl": 1.0,
350
+ "eval_recall_ita": 1.0,
351
+ "eval_recall_jpn": 0.96,
352
+ "eval_recall_kor": 0.8571428571428571,
353
+ "eval_recall_ltu": 1.0,
354
+ "eval_recall_lux": 0.9,
355
+ "eval_recall_lva": 1.0,
356
+ "eval_recall_mkd": 0.9583333333333334,
357
+ "eval_recall_mne": 1.0,
358
+ "eval_recall_nato": 1.0,
359
+ "eval_recall_nld": 0.975609756097561,
360
+ "eval_recall_nor": 0.9166666666666666,
361
+ "eval_recall_nzl": 0.9333333333333333,
362
+ "eval_recall_pol": 1.0,
363
+ "eval_recall_prt": 0.9642857142857143,
364
+ "eval_recall_rou": 0.9523809523809523,
365
+ "eval_recall_svk": 1.0,
366
+ "eval_recall_svn": 0.96,
367
+ "eval_recall_tur": 0.9047619047619048,
368
+ "eval_recall_ukr": 1.0,
369
+ "eval_recall_usa": 0.9411764705882353,
370
+ "eval_runtime": 49.6549,
371
+ "eval_samples_per_second": 12.104,
372
+ "eval_steps_per_second": 0.201,
373
+ "step": 96
374
+ }
375
+ ],
376
+ "logging_steps": 500,
377
+ "max_steps": 96,
378
+ "num_input_tokens_seen": 0,
379
+ "num_train_epochs": 3,
380
+ "save_steps": 500,
381
+ "stateful_callbacks": {
382
+ "TrainerControl": {
383
+ "args": {
384
+ "should_epoch_stop": false,
385
+ "should_evaluate": false,
386
+ "should_log": false,
387
+ "should_save": true,
388
+ "should_training_stop": true
389
+ },
390
+ "attributes": {}
391
+ }
392
+ },
393
+ "total_flos": 5592287176704000.0,
394
+ "train_batch_size": 64,
395
+ "trial_name": null,
396
+ "trial_params": null
397
+ }
checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d65cca4581314c1f96e4f97e717d8e4e02243ef563580ff9adca255b397e0e4
3
+ size 5649
config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 1024,
9
+ "id2label": {
10
+ "0": "LABEL_0",
11
+ "1": "LABEL_1",
12
+ "2": "LABEL_2",
13
+ "3": "LABEL_3",
14
+ "4": "LABEL_4",
15
+ "5": "LABEL_5",
16
+ "6": "LABEL_6",
17
+ "7": "LABEL_7",
18
+ "8": "LABEL_8",
19
+ "9": "LABEL_9",
20
+ "10": "LABEL_10",
21
+ "11": "LABEL_11",
22
+ "12": "LABEL_12",
23
+ "13": "LABEL_13",
24
+ "14": "LABEL_14",
25
+ "15": "LABEL_15",
26
+ "16": "LABEL_16",
27
+ "17": "LABEL_17",
28
+ "18": "LABEL_18",
29
+ "19": "LABEL_19",
30
+ "20": "LABEL_20",
31
+ "21": "LABEL_21",
32
+ "22": "LABEL_22",
33
+ "23": "LABEL_23",
34
+ "24": "LABEL_24",
35
+ "25": "LABEL_25",
36
+ "26": "LABEL_26",
37
+ "27": "LABEL_27",
38
+ "28": "LABEL_28",
39
+ "29": "LABEL_29",
40
+ "30": "LABEL_30",
41
+ "31": "LABEL_31",
42
+ "32": "LABEL_32",
43
+ "33": "LABEL_33",
44
+ "34": "LABEL_34",
45
+ "35": "LABEL_35",
46
+ "36": "LABEL_36"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 4096,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_10": 10,
54
+ "LABEL_11": 11,
55
+ "LABEL_12": 12,
56
+ "LABEL_13": 13,
57
+ "LABEL_14": 14,
58
+ "LABEL_15": 15,
59
+ "LABEL_16": 16,
60
+ "LABEL_17": 17,
61
+ "LABEL_18": 18,
62
+ "LABEL_19": 19,
63
+ "LABEL_2": 2,
64
+ "LABEL_20": 20,
65
+ "LABEL_21": 21,
66
+ "LABEL_22": 22,
67
+ "LABEL_23": 23,
68
+ "LABEL_24": 24,
69
+ "LABEL_25": 25,
70
+ "LABEL_26": 26,
71
+ "LABEL_27": 27,
72
+ "LABEL_28": 28,
73
+ "LABEL_29": 29,
74
+ "LABEL_3": 3,
75
+ "LABEL_30": 30,
76
+ "LABEL_31": 31,
77
+ "LABEL_32": 32,
78
+ "LABEL_33": 33,
79
+ "LABEL_34": 34,
80
+ "LABEL_35": 35,
81
+ "LABEL_36": 36,
82
+ "LABEL_4": 4,
83
+ "LABEL_5": 5,
84
+ "LABEL_6": 6,
85
+ "LABEL_7": 7,
86
+ "LABEL_8": 8,
87
+ "LABEL_9": 9
88
+ },
89
+ "layer_norm_eps": 1e-07,
90
+ "legacy": true,
91
+ "max_position_embeddings": 512,
92
+ "max_relative_positions": -1,
93
+ "model_type": "deberta-v2",
94
+ "norm_rel_ebd": "layer_norm",
95
+ "num_attention_heads": 16,
96
+ "num_hidden_layers": 24,
97
+ "pad_token_id": 0,
98
+ "pooler_dropout": 0,
99
+ "pooler_hidden_act": "gelu",
100
+ "pooler_hidden_size": 1024,
101
+ "pos_att_type": [
102
+ "p2c",
103
+ "c2p"
104
+ ],
105
+ "position_biased_input": false,
106
+ "position_buckets": 256,
107
+ "problem_type": "multi_label_classification",
108
+ "relative_attention": true,
109
+ "share_att_key": true,
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.52.4",
112
+ "type_vocab_size": 0,
113
+ "vocab_size": 128100
114
+ }
events.out.tfevents.1752729654.hackathon-ml-tagging.475106.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf63f9bfabb25a7c0a4ff6c8d24adc6ca7f6c134a795b8298fa3ef4227e66879
3
+ size 25607
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cafd28c690b6561f4755abd3e2a2ccf2578e6ae7d0634264ad24ee840fb7ddf
3
+ size 1740447956
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d65cca4581314c1f96e4f97e717d8e4e02243ef563580ff9adca255b397e0e4
3
+ size 5649