ykerido commited on
Commit
ec15e09
·
verified ·
1 Parent(s): 778f220

Upload folder using huggingface_hub

Browse files
category_mapping.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"category_to_idx": {"biology": 0, "business": 1, "chemistry": 2, "computer science": 3, "economics": 4, "engineering": 5, "health": 6, "history": 7, "law": 8, "math": 9, "other": 10, "philosophy": 11, "physics": 12, "psychology": 13}, "idx_to_category": {"0": "biology", "1": "business", "2": "chemistry", "3": "computer science", "4": "economics", "5": "engineering", "6": "health", "7": "history", "8": "law", "9": "math", "10": "other", "11": "philosophy", "12": "physics", "13": "psychology"}}
checkpoint-1110/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "biology",
25
+ "1": "business",
26
+ "2": "chemistry",
27
+ "3": "computer science",
28
+ "4": "economics",
29
+ "5": "engineering",
30
+ "6": "health",
31
+ "7": "history",
32
+ "8": "law",
33
+ "9": "math",
34
+ "10": "other",
35
+ "11": "philosophy",
36
+ "12": "physics",
37
+ "13": "psychology"
38
+ },
39
+ "initializer_cutoff_factor": 2.0,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 1152,
42
+ "label2id": {
43
+ "biology": 0,
44
+ "business": 1,
45
+ "chemistry": 2,
46
+ "computer science": 3,
47
+ "economics": 4,
48
+ "engineering": 5,
49
+ "health": 6,
50
+ "history": 7,
51
+ "law": 8,
52
+ "math": 9,
53
+ "other": 10,
54
+ "philosophy": 11,
55
+ "physics": 12,
56
+ "psychology": 13
57
+ },
58
+ "layer_norm_eps": 1e-05,
59
+ "local_attention": 128,
60
+ "local_rope_theta": 10000.0,
61
+ "max_position_embeddings": 8192,
62
+ "mlp_bias": false,
63
+ "mlp_dropout": 0.0,
64
+ "model_type": "modernbert",
65
+ "norm_bias": false,
66
+ "norm_eps": 1e-05,
67
+ "num_attention_heads": 12,
68
+ "num_hidden_layers": 22,
69
+ "pad_token_id": 50283,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "single_label_classification",
72
+ "repad_logits_with_grad": false,
73
+ "sep_token_id": 50282,
74
+ "sparse_pred_ignore_index": -100,
75
+ "sparse_prediction": false,
76
+ "transformers_version": "4.57.3",
77
+ "vocab_size": 50368
78
+ }
checkpoint-1110/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91746e4d899814001dc16d83f68a649e671d238167815a953ba97da9e7d2e4e6
3
+ size 598476704
checkpoint-1110/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4682d90d990a38cdf3973fc69ac2760e8c1460ddf9d68009b6780e285d35cd0f
3
+ size 1197043531
checkpoint-1110/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
3
+ size 14645
checkpoint-1110/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e280d02640415758dd1722f1dcb37d06550ee65f676e3ec9b0ba6825cc251ab8
3
+ size 1383
checkpoint-1110/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949bb9828c6046ac03b6b92a4af72518e3c0d55ed7954ac5b2456d65807e05d2
3
+ size 1465
checkpoint-1110/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1110,
3
+ "best_metric": 0.8585132130752519,
4
+ "best_model_checkpoint": "category_classifier_modernbert-base_model/checkpoint-1110",
5
+ "epoch": 2.0,
6
+ "eval_steps": 50,
7
+ "global_step": 1110,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.09009009009009009,
14
+ "grad_norm": 160.01605224609375,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 5.1781,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.18018018018018017,
21
+ "grad_norm": 158.0070343017578,
22
+ "learning_rate": 1.98e-05,
23
+ "loss": 2.5845,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.2702702702702703,
28
+ "grad_norm": 136.94371032714844,
29
+ "learning_rate": 1.9373801916932908e-05,
30
+ "loss": 1.736,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.36036036036036034,
35
+ "grad_norm": 92.8090591430664,
36
+ "learning_rate": 1.8734824281150162e-05,
37
+ "loss": 1.7221,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.45045045045045046,
42
+ "grad_norm": 63.52509689331055,
43
+ "learning_rate": 1.8095846645367413e-05,
44
+ "loss": 1.4292,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.5405405405405406,
49
+ "grad_norm": 159.69549560546875,
50
+ "learning_rate": 1.7456869009584666e-05,
51
+ "loss": 1.3905,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.6306306306306306,
56
+ "grad_norm": 93.9480209350586,
57
+ "learning_rate": 1.6817891373801917e-05,
58
+ "loss": 1.2243,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.7207207207207207,
63
+ "grad_norm": 86.2663803100586,
64
+ "learning_rate": 1.617891373801917e-05,
65
+ "loss": 1.3676,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.8108108108108109,
70
+ "grad_norm": 49.086673736572266,
71
+ "learning_rate": 1.5539936102236425e-05,
72
+ "loss": 1.2133,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.9009009009009009,
77
+ "grad_norm": 87.30990600585938,
78
+ "learning_rate": 1.4900958466453675e-05,
79
+ "loss": 1.2641,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.990990990990991,
84
+ "grad_norm": 95.27666473388672,
85
+ "learning_rate": 1.4261980830670927e-05,
86
+ "loss": 1.0439,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 1.0,
91
+ "eval_accuracy": 0.8050446663163426,
92
+ "eval_f1": 0.8029670816069686,
93
+ "eval_loss": 0.5830321907997131,
94
+ "eval_runtime": 30.3014,
95
+ "eval_samples_per_second": 62.802,
96
+ "eval_steps_per_second": 7.854,
97
+ "step": 555
98
+ },
99
+ {
100
+ "epoch": 1.0810810810810811,
101
+ "grad_norm": 37.04153823852539,
102
+ "learning_rate": 1.362300319488818e-05,
103
+ "loss": 0.7562,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 1.1711711711711712,
108
+ "grad_norm": 69.8899154663086,
109
+ "learning_rate": 1.2984025559105433e-05,
110
+ "loss": 0.5805,
111
+ "step": 650
112
+ },
113
+ {
114
+ "epoch": 1.2612612612612613,
115
+ "grad_norm": 44.667274475097656,
116
+ "learning_rate": 1.2345047923322684e-05,
117
+ "loss": 0.6968,
118
+ "step": 700
119
+ },
120
+ {
121
+ "epoch": 1.3513513513513513,
122
+ "grad_norm": 50.10476303100586,
123
+ "learning_rate": 1.1706070287539936e-05,
124
+ "loss": 0.5709,
125
+ "step": 750
126
+ },
127
+ {
128
+ "epoch": 1.4414414414414414,
129
+ "grad_norm": 68.5858154296875,
130
+ "learning_rate": 1.106709265175719e-05,
131
+ "loss": 0.7132,
132
+ "step": 800
133
+ },
134
+ {
135
+ "epoch": 1.5315315315315314,
136
+ "grad_norm": 58.212669372558594,
137
+ "learning_rate": 1.0428115015974442e-05,
138
+ "loss": 0.5982,
139
+ "step": 850
140
+ },
141
+ {
142
+ "epoch": 1.6216216216216215,
143
+ "grad_norm": 375.9144287109375,
144
+ "learning_rate": 9.789137380191694e-06,
145
+ "loss": 0.6555,
146
+ "step": 900
147
+ },
148
+ {
149
+ "epoch": 1.7117117117117115,
150
+ "grad_norm": 68.3332290649414,
151
+ "learning_rate": 9.150159744408946e-06,
152
+ "loss": 0.5177,
153
+ "step": 950
154
+ },
155
+ {
156
+ "epoch": 1.8018018018018018,
157
+ "grad_norm": 52.12598419189453,
158
+ "learning_rate": 8.511182108626199e-06,
159
+ "loss": 0.6234,
160
+ "step": 1000
161
+ },
162
+ {
163
+ "epoch": 1.8918918918918919,
164
+ "grad_norm": 26.67477798461914,
165
+ "learning_rate": 7.87220447284345e-06,
166
+ "loss": 0.5854,
167
+ "step": 1050
168
+ },
169
+ {
170
+ "epoch": 1.981981981981982,
171
+ "grad_norm": 43.53692626953125,
172
+ "learning_rate": 7.233226837060704e-06,
173
+ "loss": 0.4677,
174
+ "step": 1100
175
+ },
176
+ {
177
+ "epoch": 2.0,
178
+ "eval_accuracy": 0.8586442459274829,
179
+ "eval_f1": 0.8585132130752519,
180
+ "eval_loss": 0.5112260580062866,
181
+ "eval_runtime": 24.6052,
182
+ "eval_samples_per_second": 77.341,
183
+ "eval_steps_per_second": 9.673,
184
+ "step": 1110
185
+ }
186
+ ],
187
+ "logging_steps": 50,
188
+ "max_steps": 1665,
189
+ "num_input_tokens_seen": 0,
190
+ "num_train_epochs": 3,
191
+ "save_steps": 500,
192
+ "stateful_callbacks": {
193
+ "TrainerControl": {
194
+ "args": {
195
+ "should_epoch_stop": false,
196
+ "should_evaluate": false,
197
+ "should_log": false,
198
+ "should_save": true,
199
+ "should_training_stop": false
200
+ },
201
+ "attributes": {}
202
+ }
203
+ },
204
+ "total_flos": 6051681240723456.0,
205
+ "train_batch_size": 8,
206
+ "trial_name": null,
207
+ "trial_params": null
208
+ }
checkpoint-1110/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f26352724d0286fdb14af605d7ef61c2d457bcd4fd485040cb450a11756f8a
3
+ size 5841
checkpoint-1665/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "biology",
25
+ "1": "business",
26
+ "2": "chemistry",
27
+ "3": "computer science",
28
+ "4": "economics",
29
+ "5": "engineering",
30
+ "6": "health",
31
+ "7": "history",
32
+ "8": "law",
33
+ "9": "math",
34
+ "10": "other",
35
+ "11": "philosophy",
36
+ "12": "physics",
37
+ "13": "psychology"
38
+ },
39
+ "initializer_cutoff_factor": 2.0,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 1152,
42
+ "label2id": {
43
+ "biology": 0,
44
+ "business": 1,
45
+ "chemistry": 2,
46
+ "computer science": 3,
47
+ "economics": 4,
48
+ "engineering": 5,
49
+ "health": 6,
50
+ "history": 7,
51
+ "law": 8,
52
+ "math": 9,
53
+ "other": 10,
54
+ "philosophy": 11,
55
+ "physics": 12,
56
+ "psychology": 13
57
+ },
58
+ "layer_norm_eps": 1e-05,
59
+ "local_attention": 128,
60
+ "local_rope_theta": 10000.0,
61
+ "max_position_embeddings": 8192,
62
+ "mlp_bias": false,
63
+ "mlp_dropout": 0.0,
64
+ "model_type": "modernbert",
65
+ "norm_bias": false,
66
+ "norm_eps": 1e-05,
67
+ "num_attention_heads": 12,
68
+ "num_hidden_layers": 22,
69
+ "pad_token_id": 50283,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "single_label_classification",
72
+ "repad_logits_with_grad": false,
73
+ "sep_token_id": 50282,
74
+ "sparse_pred_ignore_index": -100,
75
+ "sparse_prediction": false,
76
+ "transformers_version": "4.57.3",
77
+ "vocab_size": 50368
78
+ }
checkpoint-1665/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9555a6dd1c54c7e22ad11b783966a0667dcb22c8b82ff71bd5390a3c9427ce7c
3
+ size 598476704
checkpoint-1665/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50fff79c2b4e60595361b6c906807fd0c5843573e2f66a8c6dcd46f66c43d51a
3
+ size 1197043531
checkpoint-1665/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
3
+ size 14645
checkpoint-1665/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db189fb5f4cfe7a6763bd3de947569b4c42786bbae5a8648f126c8b25f6131ea
3
+ size 1383
checkpoint-1665/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f0eb4ff7c5d7df08779819bb09ed2687d78b29eda46165188c2938a02b71182
3
+ size 1465
checkpoint-1665/trainer_state.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1665,
3
+ "best_metric": 0.8706692176592262,
4
+ "best_model_checkpoint": "category_classifier_modernbert-base_model/checkpoint-1665",
5
+ "epoch": 3.0,
6
+ "eval_steps": 50,
7
+ "global_step": 1665,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.09009009009009009,
14
+ "grad_norm": 160.01605224609375,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 5.1781,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.18018018018018017,
21
+ "grad_norm": 158.0070343017578,
22
+ "learning_rate": 1.98e-05,
23
+ "loss": 2.5845,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.2702702702702703,
28
+ "grad_norm": 136.94371032714844,
29
+ "learning_rate": 1.9373801916932908e-05,
30
+ "loss": 1.736,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.36036036036036034,
35
+ "grad_norm": 92.8090591430664,
36
+ "learning_rate": 1.8734824281150162e-05,
37
+ "loss": 1.7221,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.45045045045045046,
42
+ "grad_norm": 63.52509689331055,
43
+ "learning_rate": 1.8095846645367413e-05,
44
+ "loss": 1.4292,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.5405405405405406,
49
+ "grad_norm": 159.69549560546875,
50
+ "learning_rate": 1.7456869009584666e-05,
51
+ "loss": 1.3905,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.6306306306306306,
56
+ "grad_norm": 93.9480209350586,
57
+ "learning_rate": 1.6817891373801917e-05,
58
+ "loss": 1.2243,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.7207207207207207,
63
+ "grad_norm": 86.2663803100586,
64
+ "learning_rate": 1.617891373801917e-05,
65
+ "loss": 1.3676,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.8108108108108109,
70
+ "grad_norm": 49.086673736572266,
71
+ "learning_rate": 1.5539936102236425e-05,
72
+ "loss": 1.2133,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.9009009009009009,
77
+ "grad_norm": 87.30990600585938,
78
+ "learning_rate": 1.4900958466453675e-05,
79
+ "loss": 1.2641,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.990990990990991,
84
+ "grad_norm": 95.27666473388672,
85
+ "learning_rate": 1.4261980830670927e-05,
86
+ "loss": 1.0439,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 1.0,
91
+ "eval_accuracy": 0.8050446663163426,
92
+ "eval_f1": 0.8029670816069686,
93
+ "eval_loss": 0.5830321907997131,
94
+ "eval_runtime": 30.3014,
95
+ "eval_samples_per_second": 62.802,
96
+ "eval_steps_per_second": 7.854,
97
+ "step": 555
98
+ },
99
+ {
100
+ "epoch": 1.0810810810810811,
101
+ "grad_norm": 37.04153823852539,
102
+ "learning_rate": 1.362300319488818e-05,
103
+ "loss": 0.7562,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 1.1711711711711712,
108
+ "grad_norm": 69.8899154663086,
109
+ "learning_rate": 1.2984025559105433e-05,
110
+ "loss": 0.5805,
111
+ "step": 650
112
+ },
113
+ {
114
+ "epoch": 1.2612612612612613,
115
+ "grad_norm": 44.667274475097656,
116
+ "learning_rate": 1.2345047923322684e-05,
117
+ "loss": 0.6968,
118
+ "step": 700
119
+ },
120
+ {
121
+ "epoch": 1.3513513513513513,
122
+ "grad_norm": 50.10476303100586,
123
+ "learning_rate": 1.1706070287539936e-05,
124
+ "loss": 0.5709,
125
+ "step": 750
126
+ },
127
+ {
128
+ "epoch": 1.4414414414414414,
129
+ "grad_norm": 68.5858154296875,
130
+ "learning_rate": 1.106709265175719e-05,
131
+ "loss": 0.7132,
132
+ "step": 800
133
+ },
134
+ {
135
+ "epoch": 1.5315315315315314,
136
+ "grad_norm": 58.212669372558594,
137
+ "learning_rate": 1.0428115015974442e-05,
138
+ "loss": 0.5982,
139
+ "step": 850
140
+ },
141
+ {
142
+ "epoch": 1.6216216216216215,
143
+ "grad_norm": 375.9144287109375,
144
+ "learning_rate": 9.789137380191694e-06,
145
+ "loss": 0.6555,
146
+ "step": 900
147
+ },
148
+ {
149
+ "epoch": 1.7117117117117115,
150
+ "grad_norm": 68.3332290649414,
151
+ "learning_rate": 9.150159744408946e-06,
152
+ "loss": 0.5177,
153
+ "step": 950
154
+ },
155
+ {
156
+ "epoch": 1.8018018018018018,
157
+ "grad_norm": 52.12598419189453,
158
+ "learning_rate": 8.511182108626199e-06,
159
+ "loss": 0.6234,
160
+ "step": 1000
161
+ },
162
+ {
163
+ "epoch": 1.8918918918918919,
164
+ "grad_norm": 26.67477798461914,
165
+ "learning_rate": 7.87220447284345e-06,
166
+ "loss": 0.5854,
167
+ "step": 1050
168
+ },
169
+ {
170
+ "epoch": 1.981981981981982,
171
+ "grad_norm": 43.53692626953125,
172
+ "learning_rate": 7.233226837060704e-06,
173
+ "loss": 0.4677,
174
+ "step": 1100
175
+ },
176
+ {
177
+ "epoch": 2.0,
178
+ "eval_accuracy": 0.8586442459274829,
179
+ "eval_f1": 0.8585132130752519,
180
+ "eval_loss": 0.5112260580062866,
181
+ "eval_runtime": 24.6052,
182
+ "eval_samples_per_second": 77.341,
183
+ "eval_steps_per_second": 9.673,
184
+ "step": 1110
185
+ },
186
+ {
187
+ "epoch": 2.0720720720720722,
188
+ "grad_norm": 21.199968338012695,
189
+ "learning_rate": 6.594249201277956e-06,
190
+ "loss": 0.2489,
191
+ "step": 1150
192
+ },
193
+ {
194
+ "epoch": 2.1621621621621623,
195
+ "grad_norm": 14.63625717163086,
196
+ "learning_rate": 5.955271565495209e-06,
197
+ "loss": 0.1797,
198
+ "step": 1200
199
+ },
200
+ {
201
+ "epoch": 2.2522522522522523,
202
+ "grad_norm": 53.242008209228516,
203
+ "learning_rate": 5.31629392971246e-06,
204
+ "loss": 0.2019,
205
+ "step": 1250
206
+ },
207
+ {
208
+ "epoch": 2.3423423423423424,
209
+ "grad_norm": 5.628056049346924,
210
+ "learning_rate": 4.6773162939297125e-06,
211
+ "loss": 0.1491,
212
+ "step": 1300
213
+ },
214
+ {
215
+ "epoch": 2.4324324324324325,
216
+ "grad_norm": 58.54233169555664,
217
+ "learning_rate": 4.0383386581469655e-06,
218
+ "loss": 0.1767,
219
+ "step": 1350
220
+ },
221
+ {
222
+ "epoch": 2.5225225225225225,
223
+ "grad_norm": 16.474857330322266,
224
+ "learning_rate": 3.3993610223642177e-06,
225
+ "loss": 0.1203,
226
+ "step": 1400
227
+ },
228
+ {
229
+ "epoch": 2.6126126126126126,
230
+ "grad_norm": 43.91135025024414,
231
+ "learning_rate": 2.76038338658147e-06,
232
+ "loss": 0.1734,
233
+ "step": 1450
234
+ },
235
+ {
236
+ "epoch": 2.7027027027027026,
237
+ "grad_norm": 12.281766891479492,
238
+ "learning_rate": 2.1214057507987225e-06,
239
+ "loss": 0.172,
240
+ "step": 1500
241
+ },
242
+ {
243
+ "epoch": 2.7927927927927927,
244
+ "grad_norm": 13.688041687011719,
245
+ "learning_rate": 1.4824281150159744e-06,
246
+ "loss": 0.2202,
247
+ "step": 1550
248
+ },
249
+ {
250
+ "epoch": 2.8828828828828827,
251
+ "grad_norm": 1.5469253063201904,
252
+ "learning_rate": 8.434504792332269e-07,
253
+ "loss": 0.1596,
254
+ "step": 1600
255
+ },
256
+ {
257
+ "epoch": 2.972972972972973,
258
+ "grad_norm": 59.35817337036133,
259
+ "learning_rate": 2.0447284345047925e-07,
260
+ "loss": 0.165,
261
+ "step": 1650
262
+ },
263
+ {
264
+ "epoch": 3.0,
265
+ "eval_accuracy": 0.8707304256437205,
266
+ "eval_f1": 0.8706692176592262,
267
+ "eval_loss": 0.5725481510162354,
268
+ "eval_runtime": 24.6542,
269
+ "eval_samples_per_second": 77.188,
270
+ "eval_steps_per_second": 9.654,
271
+ "step": 1665
272
+ }
273
+ ],
274
+ "logging_steps": 50,
275
+ "max_steps": 1665,
276
+ "num_input_tokens_seen": 0,
277
+ "num_train_epochs": 3,
278
+ "save_steps": 500,
279
+ "stateful_callbacks": {
280
+ "TrainerControl": {
281
+ "args": {
282
+ "should_epoch_stop": false,
283
+ "should_evaluate": false,
284
+ "should_log": false,
285
+ "should_save": true,
286
+ "should_training_stop": true
287
+ },
288
+ "attributes": {}
289
+ }
290
+ },
291
+ "total_flos": 9077521861085184.0,
292
+ "train_batch_size": 8,
293
+ "trial_name": null,
294
+ "trial_params": null
295
+ }
checkpoint-1665/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f26352724d0286fdb14af605d7ef61c2d457bcd4fd485040cb450a11756f8a
3
+ size 5841
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "biology",
24
+ "1": "business",
25
+ "2": "chemistry",
26
+ "3": "computer science",
27
+ "4": "economics",
28
+ "5": "engineering",
29
+ "6": "health",
30
+ "7": "history",
31
+ "8": "law",
32
+ "9": "math",
33
+ "10": "other",
34
+ "11": "philosophy",
35
+ "12": "physics",
36
+ "13": "psychology"
37
+ },
38
+ "initializer_cutoff_factor": 2.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 1152,
41
+ "label2id": {
42
+ "biology": 0,
43
+ "business": 1,
44
+ "chemistry": 2,
45
+ "computer science": 3,
46
+ "economics": 4,
47
+ "engineering": 5,
48
+ "health": 6,
49
+ "history": 7,
50
+ "law": 8,
51
+ "math": 9,
52
+ "other": 10,
53
+ "philosophy": 11,
54
+ "physics": 12,
55
+ "psychology": 13
56
+ },
57
+ "layer_norm_eps": 1e-05,
58
+ "local_attention": 128,
59
+ "local_rope_theta": 10000.0,
60
+ "max_position_embeddings": 8192,
61
+ "mlp_bias": false,
62
+ "mlp_dropout": 0.0,
63
+ "model_type": "modernbert",
64
+ "norm_bias": false,
65
+ "norm_eps": 1e-05,
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 22,
68
+ "pad_token_id": 50283,
69
+ "position_embedding_type": "absolute",
70
+ "problem_type": "single_label_classification",
71
+ "repad_logits_with_grad": false,
72
+ "sep_token_id": 50282,
73
+ "sparse_pred_ignore_index": -100,
74
+ "sparse_prediction": false,
75
+ "transformers_version": "4.57.3",
76
+ "vocab_size": 50368,
77
+ "hidden_act": "gelu",
78
+ "hidden_dropout_prob": 0.0,
79
+ "type_vocab_size": 2,
80
+ "torch_dtype": "float32"
81
+ }
evaluation_results.json ADDED
@@ -0,0 +1,654 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "validation_accuracy": 0.8702049395691014,
3
+ "test_accuracy": 0.8586442459274829,
4
+ "validation_report": {
5
+ "biology": {
6
+ "precision": 0.8421052631578947,
7
+ "recall": 0.8571428571428571,
8
+ "f1-score": 0.8495575221238938,
9
+ "support": 112.0
10
+ },
11
+ "business": {
12
+ "precision": 0.8770491803278688,
13
+ "recall": 0.8699186991869918,
14
+ "f1-score": 0.8734693877551021,
15
+ "support": 123.0
16
+ },
17
+ "chemistry": {
18
+ "precision": 0.8461538461538461,
19
+ "recall": 0.8171428571428572,
20
+ "f1-score": 0.8313953488372093,
21
+ "support": 175.0
22
+ },
23
+ "computer science": {
24
+ "precision": 0.8461538461538461,
25
+ "recall": 0.8333333333333334,
26
+ "f1-score": 0.8396946564885496,
27
+ "support": 66.0
28
+ },
29
+ "economics": {
30
+ "precision": 0.8592592592592593,
31
+ "recall": 0.8854961832061069,
32
+ "f1-score": 0.8721804511278195,
33
+ "support": 131.0
34
+ },
35
+ "engineering": {
36
+ "precision": 0.875,
37
+ "recall": 0.84,
38
+ "f1-score": 0.8571428571428571,
39
+ "support": 150.0
40
+ },
41
+ "health": {
42
+ "precision": 0.8409090909090909,
43
+ "recall": 0.8671875,
44
+ "f1-score": 0.8538461538461538,
45
+ "support": 128.0
46
+ },
47
+ "history": {
48
+ "precision": 0.95,
49
+ "recall": 0.9344262295081968,
50
+ "f1-score": 0.9421487603305785,
51
+ "support": 61.0
52
+ },
53
+ "law": {
54
+ "precision": 0.9704142011834319,
55
+ "recall": 0.9704142011834319,
56
+ "f1-score": 0.9704142011834319,
57
+ "support": 169.0
58
+ },
59
+ "math": {
60
+ "precision": 0.8995215311004785,
61
+ "recall": 0.9082125603864735,
62
+ "f1-score": 0.9038461538461539,
63
+ "support": 207.0
64
+ },
65
+ "other": {
66
+ "precision": 0.8324022346368715,
67
+ "recall": 0.8370786516853933,
68
+ "f1-score": 0.834733893557423,
69
+ "support": 178.0
70
+ },
71
+ "philosophy": {
72
+ "precision": 0.8333333333333334,
73
+ "recall": 0.8860759493670886,
74
+ "f1-score": 0.8588957055214724,
75
+ "support": 79.0
76
+ },
77
+ "physics": {
78
+ "precision": 0.8585858585858586,
79
+ "recall": 0.85,
80
+ "f1-score": 0.8542713567839196,
81
+ "support": 200.0
82
+ },
83
+ "psychology": {
84
+ "precision": 0.8455284552845529,
85
+ "recall": 0.8387096774193549,
86
+ "f1-score": 0.8421052631578947,
87
+ "support": 124.0
88
+ },
89
+ "accuracy": 0.8702049395691014,
90
+ "macro avg": {
91
+ "precision": 0.8697440071490238,
92
+ "recall": 0.8710813356830059,
93
+ "f1-score": 0.8702644079787473,
94
+ "support": 1903.0
95
+ },
96
+ "weighted avg": {
97
+ "precision": 0.8703519865398671,
98
+ "recall": 0.8702049395691014,
99
+ "f1-score": 0.8701516195018865,
100
+ "support": 1903.0
101
+ }
102
+ },
103
+ "test_report": {
104
+ "biology": {
105
+ "precision": 0.8611111111111112,
106
+ "recall": 0.8303571428571429,
107
+ "f1-score": 0.8454545454545455,
108
+ "support": 112.0
109
+ },
110
+ "business": {
111
+ "precision": 0.8780487804878049,
112
+ "recall": 0.8780487804878049,
113
+ "f1-score": 0.8780487804878049,
114
+ "support": 123.0
115
+ },
116
+ "chemistry": {
117
+ "precision": 0.7978142076502732,
118
+ "recall": 0.8390804597701149,
119
+ "f1-score": 0.8179271708683473,
120
+ "support": 174.0
121
+ },
122
+ "computer science": {
123
+ "precision": 0.8636363636363636,
124
+ "recall": 0.8636363636363636,
125
+ "f1-score": 0.8636363636363636,
126
+ "support": 66.0
127
+ },
128
+ "economics": {
129
+ "precision": 0.8692307692307693,
130
+ "recall": 0.8625954198473282,
131
+ "f1-score": 0.8659003831417624,
132
+ "support": 131.0
133
+ },
134
+ "engineering": {
135
+ "precision": 0.8523489932885906,
136
+ "recall": 0.8466666666666667,
137
+ "f1-score": 0.8494983277591973,
138
+ "support": 150.0
139
+ },
140
+ "health": {
141
+ "precision": 0.873015873015873,
142
+ "recall": 0.8661417322834646,
143
+ "f1-score": 0.8695652173913043,
144
+ "support": 127.0
145
+ },
146
+ "history": {
147
+ "precision": 0.9661016949152542,
148
+ "recall": 0.9193548387096774,
149
+ "f1-score": 0.9421487603305785,
150
+ "support": 62.0
151
+ },
152
+ "law": {
153
+ "precision": 0.9649122807017544,
154
+ "recall": 0.9705882352941176,
155
+ "f1-score": 0.967741935483871,
156
+ "support": 170.0
157
+ },
158
+ "math": {
159
+ "precision": 0.8878504672897196,
160
+ "recall": 0.9178743961352657,
161
+ "f1-score": 0.9026128266033254,
162
+ "support": 207.0
163
+ },
164
+ "other": {
165
+ "precision": 0.8641975308641975,
166
+ "recall": 0.7865168539325843,
167
+ "f1-score": 0.8235294117647058,
168
+ "support": 178.0
169
+ },
170
+ "philosophy": {
171
+ "precision": 0.8131868131868132,
172
+ "recall": 0.925,
173
+ "f1-score": 0.8654970760233918,
174
+ "support": 80.0
175
+ },
176
+ "physics": {
177
+ "precision": 0.803030303030303,
178
+ "recall": 0.7989949748743719,
179
+ "f1-score": 0.801007556675063,
180
+ "support": 199.0
181
+ },
182
+ "psychology": {
183
+ "precision": 0.7723577235772358,
184
+ "recall": 0.7661290322580645,
185
+ "f1-score": 0.7692307692307693,
186
+ "support": 124.0
187
+ },
188
+ "accuracy": 0.8586442459274829,
189
+ "macro avg": {
190
+ "precision": 0.8619173508561474,
191
+ "recall": 0.8622132069109263,
192
+ "f1-score": 0.8615570803465022,
193
+ "support": 1903.0
194
+ },
195
+ "weighted avg": {
196
+ "precision": 0.859187937635062,
197
+ "recall": 0.8586442459274829,
198
+ "f1-score": 0.85847926779019,
199
+ "support": 1903.0
200
+ }
201
+ },
202
+ "validation_confusion_matrix": [
203
+ [
204
+ 96,
205
+ 1,
206
+ 1,
207
+ 0,
208
+ 3,
209
+ 0,
210
+ 7,
211
+ 1,
212
+ 0,
213
+ 1,
214
+ 1,
215
+ 0,
216
+ 0,
217
+ 1
218
+ ],
219
+ [
220
+ 0,
221
+ 107,
222
+ 1,
223
+ 1,
224
+ 6,
225
+ 0,
226
+ 0,
227
+ 0,
228
+ 0,
229
+ 2,
230
+ 0,
231
+ 4,
232
+ 0,
233
+ 2
234
+ ],
235
+ [
236
+ 2,
237
+ 0,
238
+ 143,
239
+ 0,
240
+ 0,
241
+ 9,
242
+ 2,
243
+ 0,
244
+ 0,
245
+ 3,
246
+ 3,
247
+ 1,
248
+ 12,
249
+ 0
250
+ ],
251
+ [
252
+ 2,
253
+ 0,
254
+ 0,
255
+ 55,
256
+ 0,
257
+ 1,
258
+ 0,
259
+ 0,
260
+ 0,
261
+ 6,
262
+ 1,
263
+ 0,
264
+ 1,
265
+ 0
266
+ ],
267
+ [
268
+ 1,
269
+ 5,
270
+ 0,
271
+ 0,
272
+ 116,
273
+ 0,
274
+ 0,
275
+ 0,
276
+ 0,
277
+ 1,
278
+ 3,
279
+ 2,
280
+ 0,
281
+ 3
282
+ ],
283
+ [
284
+ 0,
285
+ 0,
286
+ 6,
287
+ 6,
288
+ 0,
289
+ 126,
290
+ 1,
291
+ 0,
292
+ 0,
293
+ 2,
294
+ 0,
295
+ 0,
296
+ 9,
297
+ 0
298
+ ],
299
+ [
300
+ 6,
301
+ 0,
302
+ 1,
303
+ 0,
304
+ 1,
305
+ 1,
306
+ 111,
307
+ 0,
308
+ 1,
309
+ 0,
310
+ 2,
311
+ 0,
312
+ 0,
313
+ 5
314
+ ],
315
+ [
316
+ 1,
317
+ 0,
318
+ 0,
319
+ 0,
320
+ 0,
321
+ 0,
322
+ 0,
323
+ 57,
324
+ 1,
325
+ 0,
326
+ 2,
327
+ 0,
328
+ 0,
329
+ 0
330
+ ],
331
+ [
332
+ 0,
333
+ 1,
334
+ 0,
335
+ 0,
336
+ 0,
337
+ 0,
338
+ 0,
339
+ 0,
340
+ 164,
341
+ 0,
342
+ 2,
343
+ 2,
344
+ 0,
345
+ 0
346
+ ],
347
+ [
348
+ 1,
349
+ 2,
350
+ 0,
351
+ 1,
352
+ 1,
353
+ 1,
354
+ 1,
355
+ 0,
356
+ 0,
357
+ 188,
358
+ 4,
359
+ 0,
360
+ 5,
361
+ 3
362
+ ],
363
+ [
364
+ 2,
365
+ 4,
366
+ 0,
367
+ 1,
368
+ 6,
369
+ 0,
370
+ 4,
371
+ 0,
372
+ 3,
373
+ 0,
374
+ 149,
375
+ 4,
376
+ 1,
377
+ 4
378
+ ],
379
+ [
380
+ 1,
381
+ 1,
382
+ 0,
383
+ 0,
384
+ 0,
385
+ 0,
386
+ 0,
387
+ 2,
388
+ 0,
389
+ 0,
390
+ 4,
391
+ 70,
392
+ 0,
393
+ 1
394
+ ],
395
+ [
396
+ 1,
397
+ 0,
398
+ 17,
399
+ 0,
400
+ 1,
401
+ 5,
402
+ 0,
403
+ 0,
404
+ 0,
405
+ 4,
406
+ 2,
407
+ 0,
408
+ 170,
409
+ 0
410
+ ],
411
+ [
412
+ 1,
413
+ 1,
414
+ 0,
415
+ 1,
416
+ 1,
417
+ 1,
418
+ 6,
419
+ 0,
420
+ 0,
421
+ 2,
422
+ 6,
423
+ 1,
424
+ 0,
425
+ 104
426
+ ]
427
+ ],
428
+ "test_confusion_matrix": [
429
+ [
430
+ 93,
431
+ 0,
432
+ 1,
433
+ 0,
434
+ 2,
435
+ 1,
436
+ 9,
437
+ 0,
438
+ 0,
439
+ 1,
440
+ 2,
441
+ 0,
442
+ 0,
443
+ 3
444
+ ],
445
+ [
446
+ 0,
447
+ 108,
448
+ 1,
449
+ 0,
450
+ 4,
451
+ 0,
452
+ 0,
453
+ 0,
454
+ 1,
455
+ 1,
456
+ 1,
457
+ 2,
458
+ 1,
459
+ 4
460
+ ],
461
+ [
462
+ 1,
463
+ 0,
464
+ 146,
465
+ 0,
466
+ 0,
467
+ 6,
468
+ 0,
469
+ 0,
470
+ 0,
471
+ 4,
472
+ 0,
473
+ 0,
474
+ 16,
475
+ 1
476
+ ],
477
+ [
478
+ 0,
479
+ 0,
480
+ 0,
481
+ 57,
482
+ 1,
483
+ 2,
484
+ 0,
485
+ 0,
486
+ 0,
487
+ 5,
488
+ 0,
489
+ 0,
490
+ 0,
491
+ 1
492
+ ],
493
+ [
494
+ 0,
495
+ 6,
496
+ 0,
497
+ 1,
498
+ 113,
499
+ 0,
500
+ 0,
501
+ 1,
502
+ 1,
503
+ 1,
504
+ 7,
505
+ 0,
506
+ 0,
507
+ 1
508
+ ],
509
+ [
510
+ 2,
511
+ 0,
512
+ 10,
513
+ 2,
514
+ 0,
515
+ 127,
516
+ 0,
517
+ 0,
518
+ 0,
519
+ 2,
520
+ 0,
521
+ 0,
522
+ 7,
523
+ 0
524
+ ],
525
+ [
526
+ 4,
527
+ 0,
528
+ 0,
529
+ 0,
530
+ 1,
531
+ 0,
532
+ 110,
533
+ 0,
534
+ 0,
535
+ 1,
536
+ 3,
537
+ 0,
538
+ 1,
539
+ 7
540
+ ],
541
+ [
542
+ 2,
543
+ 0,
544
+ 0,
545
+ 0,
546
+ 0,
547
+ 0,
548
+ 0,
549
+ 57,
550
+ 0,
551
+ 0,
552
+ 1,
553
+ 2,
554
+ 0,
555
+ 0
556
+ ],
557
+ [
558
+ 0,
559
+ 0,
560
+ 0,
561
+ 0,
562
+ 0,
563
+ 0,
564
+ 0,
565
+ 0,
566
+ 165,
567
+ 0,
568
+ 0,
569
+ 4,
570
+ 0,
571
+ 1
572
+ ],
573
+ [
574
+ 0,
575
+ 2,
576
+ 1,
577
+ 3,
578
+ 0,
579
+ 0,
580
+ 1,
581
+ 0,
582
+ 0,
583
+ 190,
584
+ 0,
585
+ 0,
586
+ 5,
587
+ 5
588
+ ],
589
+ [
590
+ 1,
591
+ 6,
592
+ 0,
593
+ 1,
594
+ 6,
595
+ 0,
596
+ 3,
597
+ 0,
598
+ 1,
599
+ 5,
600
+ 140,
601
+ 7,
602
+ 6,
603
+ 2
604
+ ],
605
+ [
606
+ 0,
607
+ 0,
608
+ 0,
609
+ 0,
610
+ 1,
611
+ 0,
612
+ 0,
613
+ 0,
614
+ 1,
615
+ 0,
616
+ 1,
617
+ 74,
618
+ 0,
619
+ 3
620
+ ],
621
+ [
622
+ 0,
623
+ 0,
624
+ 24,
625
+ 0,
626
+ 1,
627
+ 10,
628
+ 0,
629
+ 1,
630
+ 0,
631
+ 3,
632
+ 1,
633
+ 0,
634
+ 159,
635
+ 0
636
+ ],
637
+ [
638
+ 5,
639
+ 1,
640
+ 0,
641
+ 2,
642
+ 1,
643
+ 3,
644
+ 3,
645
+ 0,
646
+ 2,
647
+ 1,
648
+ 6,
649
+ 2,
650
+ 3,
651
+ 95
652
+ ]
653
+ ]
654
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9555a6dd1c54c7e22ad11b783966a0667dcb22c8b82ff71bd5390a3c9427ce7c
3
+ size 598476704
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f26352724d0286fdb14af605d7ef61c2d457bcd4fd485040cb450a11756f8a
3
+ size 5841