Training in progress, epoch 1
Browse files- config.json +327 -0
- model.safetensors +3 -0
- runs/Jul09_16-45-39_170defa71826/events.out.tfevents.1752079551.170defa71826.1791.0 +3 -0
- runs/Jul09_17-03-20_170defa71826/events.out.tfevents.1752080601.170defa71826.15192.0 +3 -0
- runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082643.170defa71826.15192.1 +3 -0
- runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082678.170defa71826.15192.2 +3 -0
- runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082738.170defa71826.15192.3 +3 -0
- runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082763.170defa71826.15192.4 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,327 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "tasksource/ModernBERT-base-nli",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ModernBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 50281,
|
| 9 |
+
"classifier_activation": "gelu",
|
| 10 |
+
"classifier_bias": false,
|
| 11 |
+
"classifier_dropout": 0.0,
|
| 12 |
+
"classifier_pooling": "mean",
|
| 13 |
+
"classifiers_size": [
|
| 14 |
+
3,
|
| 15 |
+
2,
|
| 16 |
+
2,
|
| 17 |
+
2,
|
| 18 |
+
2,
|
| 19 |
+
2,
|
| 20 |
+
1,
|
| 21 |
+
2,
|
| 22 |
+
3,
|
| 23 |
+
2,
|
| 24 |
+
2,
|
| 25 |
+
2,
|
| 26 |
+
3,
|
| 27 |
+
3,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
3,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
6,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2,
|
| 44 |
+
2,
|
| 45 |
+
2,
|
| 46 |
+
3,
|
| 47 |
+
3,
|
| 48 |
+
3,
|
| 49 |
+
3,
|
| 50 |
+
3,
|
| 51 |
+
3,
|
| 52 |
+
3,
|
| 53 |
+
2,
|
| 54 |
+
2,
|
| 55 |
+
2,
|
| 56 |
+
2,
|
| 57 |
+
3,
|
| 58 |
+
3,
|
| 59 |
+
3,
|
| 60 |
+
3,
|
| 61 |
+
3,
|
| 62 |
+
3,
|
| 63 |
+
3,
|
| 64 |
+
3,
|
| 65 |
+
2,
|
| 66 |
+
2,
|
| 67 |
+
2,
|
| 68 |
+
2,
|
| 69 |
+
2,
|
| 70 |
+
2,
|
| 71 |
+
16,
|
| 72 |
+
100,
|
| 73 |
+
13,
|
| 74 |
+
100,
|
| 75 |
+
8,
|
| 76 |
+
3,
|
| 77 |
+
3,
|
| 78 |
+
2,
|
| 79 |
+
3,
|
| 80 |
+
2,
|
| 81 |
+
4,
|
| 82 |
+
3,
|
| 83 |
+
2,
|
| 84 |
+
3,
|
| 85 |
+
2,
|
| 86 |
+
2,
|
| 87 |
+
2,
|
| 88 |
+
2,
|
| 89 |
+
2,
|
| 90 |
+
3,
|
| 91 |
+
2,
|
| 92 |
+
3,
|
| 93 |
+
2,
|
| 94 |
+
4,
|
| 95 |
+
3,
|
| 96 |
+
3,
|
| 97 |
+
3,
|
| 98 |
+
2,
|
| 99 |
+
3,
|
| 100 |
+
1,
|
| 101 |
+
2,
|
| 102 |
+
2,
|
| 103 |
+
3,
|
| 104 |
+
13,
|
| 105 |
+
2,
|
| 106 |
+
2,
|
| 107 |
+
3,
|
| 108 |
+
2,
|
| 109 |
+
2,
|
| 110 |
+
3,
|
| 111 |
+
3,
|
| 112 |
+
3,
|
| 113 |
+
3,
|
| 114 |
+
2,
|
| 115 |
+
3,
|
| 116 |
+
3,
|
| 117 |
+
2,
|
| 118 |
+
3,
|
| 119 |
+
2,
|
| 120 |
+
2,
|
| 121 |
+
2,
|
| 122 |
+
2,
|
| 123 |
+
2,
|
| 124 |
+
3,
|
| 125 |
+
4,
|
| 126 |
+
3,
|
| 127 |
+
3,
|
| 128 |
+
2,
|
| 129 |
+
2,
|
| 130 |
+
3,
|
| 131 |
+
3,
|
| 132 |
+
2,
|
| 133 |
+
2,
|
| 134 |
+
2,
|
| 135 |
+
2,
|
| 136 |
+
2,
|
| 137 |
+
4,
|
| 138 |
+
3,
|
| 139 |
+
2,
|
| 140 |
+
2,
|
| 141 |
+
2,
|
| 142 |
+
3,
|
| 143 |
+
3,
|
| 144 |
+
3,
|
| 145 |
+
2,
|
| 146 |
+
3
|
| 147 |
+
],
|
| 148 |
+
"cls_token_id": 50281,
|
| 149 |
+
"decoder_bias": true,
|
| 150 |
+
"deterministic_flash_attn": false,
|
| 151 |
+
"embedding_dropout": 0.0,
|
| 152 |
+
"eos_token_id": 50282,
|
| 153 |
+
"global_attn_every_n_layers": 3,
|
| 154 |
+
"global_rope_theta": 160000.0,
|
| 155 |
+
"gradient_checkpointing": false,
|
| 156 |
+
"hidden_activation": "gelu",
|
| 157 |
+
"hidden_size": 768,
|
| 158 |
+
"id2label": {
|
| 159 |
+
"0": "entailment",
|
| 160 |
+
"1": "neutral",
|
| 161 |
+
"2": "contradiction"
|
| 162 |
+
},
|
| 163 |
+
"initializer_cutoff_factor": 2.0,
|
| 164 |
+
"initializer_range": 0.02,
|
| 165 |
+
"intermediate_size": 1152,
|
| 166 |
+
"label2id": {
|
| 167 |
+
"contradiction": "2",
|
| 168 |
+
"entailment": "0",
|
| 169 |
+
"neutral": "1"
|
| 170 |
+
},
|
| 171 |
+
"layer_norm_eps": 1e-05,
|
| 172 |
+
"local_attention": 128,
|
| 173 |
+
"local_rope_theta": 10000.0,
|
| 174 |
+
"max_position_embeddings": 2048,
|
| 175 |
+
"mlp_bias": false,
|
| 176 |
+
"mlp_dropout": 0.0,
|
| 177 |
+
"model_type": "modernbert",
|
| 178 |
+
"norm_bias": false,
|
| 179 |
+
"norm_eps": 1e-05,
|
| 180 |
+
"num_attention_heads": 12,
|
| 181 |
+
"num_hidden_layers": 22,
|
| 182 |
+
"pad_token_id": 50283,
|
| 183 |
+
"position_embedding_type": "absolute",
|
| 184 |
+
"problem_type": "single_label_classification",
|
| 185 |
+
"reference_compile": true,
|
| 186 |
+
"sep_token_id": 50282,
|
| 187 |
+
"sparse_pred_ignore_index": -100,
|
| 188 |
+
"sparse_prediction": false,
|
| 189 |
+
"tasks": [
|
| 190 |
+
"glue/mnli",
|
| 191 |
+
"glue/qnli",
|
| 192 |
+
"glue/rte",
|
| 193 |
+
"glue/wnli",
|
| 194 |
+
"glue/mrpc",
|
| 195 |
+
"glue/qqp",
|
| 196 |
+
"glue/stsb",
|
| 197 |
+
"super_glue/boolq",
|
| 198 |
+
"super_glue/cb",
|
| 199 |
+
"super_glue/multirc",
|
| 200 |
+
"super_glue/wic",
|
| 201 |
+
"super_glue/axg",
|
| 202 |
+
"anli/a1",
|
| 203 |
+
"anli/a2",
|
| 204 |
+
"anli/a3",
|
| 205 |
+
"sick/label",
|
| 206 |
+
"sick/entailment_AB",
|
| 207 |
+
"snli",
|
| 208 |
+
"scitail/snli_format",
|
| 209 |
+
"hans",
|
| 210 |
+
"WANLI",
|
| 211 |
+
"recast/recast_ner",
|
| 212 |
+
"recast/recast_sentiment",
|
| 213 |
+
"recast/recast_verbnet",
|
| 214 |
+
"recast/recast_megaveridicality",
|
| 215 |
+
"recast/recast_verbcorner",
|
| 216 |
+
"recast/recast_kg_relations",
|
| 217 |
+
"recast/recast_factuality",
|
| 218 |
+
"recast/recast_puns",
|
| 219 |
+
"probability_words_nli/reasoning_1hop",
|
| 220 |
+
"probability_words_nli/usnli",
|
| 221 |
+
"probability_words_nli/reasoning_2hop",
|
| 222 |
+
"nan-nli",
|
| 223 |
+
"nli_fever",
|
| 224 |
+
"breaking_nli",
|
| 225 |
+
"conj_nli",
|
| 226 |
+
"fracas",
|
| 227 |
+
"dialogue_nli",
|
| 228 |
+
"mpe",
|
| 229 |
+
"dnc",
|
| 230 |
+
"recast_white/fnplus",
|
| 231 |
+
"recast_white/sprl",
|
| 232 |
+
"recast_white/dpr",
|
| 233 |
+
"robust_nli/IS_CS",
|
| 234 |
+
"robust_nli/LI_LI",
|
| 235 |
+
"robust_nli/ST_WO",
|
| 236 |
+
"robust_nli/PI_SP",
|
| 237 |
+
"robust_nli/PI_CD",
|
| 238 |
+
"robust_nli/ST_SE",
|
| 239 |
+
"robust_nli/ST_NE",
|
| 240 |
+
"robust_nli/ST_LM",
|
| 241 |
+
"robust_nli_is_sd",
|
| 242 |
+
"robust_nli_li_ts",
|
| 243 |
+
"add_one_rte",
|
| 244 |
+
"paws/labeled_final",
|
| 245 |
+
"glue/cola",
|
| 246 |
+
"glue/sst2",
|
| 247 |
+
"pragmeval/pdtb",
|
| 248 |
+
"lex_glue/eurlex",
|
| 249 |
+
"lex_glue/scotus",
|
| 250 |
+
"lex_glue/ledgar",
|
| 251 |
+
"lex_glue/unfair_tos",
|
| 252 |
+
"dynasent/dynabench.dynasent.r1.all/r1",
|
| 253 |
+
"dynasent/dynabench.dynasent.r2.all/r2",
|
| 254 |
+
"cycic_classification",
|
| 255 |
+
"lingnli",
|
| 256 |
+
"monotonicity-entailment",
|
| 257 |
+
"scinli",
|
| 258 |
+
"naturallogic",
|
| 259 |
+
"dynahate",
|
| 260 |
+
"syntactic-augmentation-nli",
|
| 261 |
+
"autotnli",
|
| 262 |
+
"defeasible-nli/atomic",
|
| 263 |
+
"defeasible-nli/snli",
|
| 264 |
+
"help-nli",
|
| 265 |
+
"nli-veridicality-transitivity",
|
| 266 |
+
"lonli",
|
| 267 |
+
"dadc-limit-nli",
|
| 268 |
+
"folio",
|
| 269 |
+
"tomi-nli",
|
| 270 |
+
"puzzte",
|
| 271 |
+
"temporal-nli",
|
| 272 |
+
"counterfactually-augmented-snli",
|
| 273 |
+
"cnli",
|
| 274 |
+
"boolq-natural-perturbations",
|
| 275 |
+
"equate",
|
| 276 |
+
"chaos-mnli-ambiguity",
|
| 277 |
+
"logiqa-2.0-nli",
|
| 278 |
+
"mindgames",
|
| 279 |
+
"ConTRoL-nli",
|
| 280 |
+
"logical-fallacy",
|
| 281 |
+
"cladder",
|
| 282 |
+
"conceptrules_v2",
|
| 283 |
+
"zero-shot-label-nli",
|
| 284 |
+
"scone",
|
| 285 |
+
"monli",
|
| 286 |
+
"SpaceNLI",
|
| 287 |
+
"propsegment/nli",
|
| 288 |
+
"FLD.v2/default",
|
| 289 |
+
"FLD.v2/star",
|
| 290 |
+
"SDOH-NLI",
|
| 291 |
+
"scifact_entailment",
|
| 292 |
+
"AdjectiveScaleProbe-nli",
|
| 293 |
+
"resnli",
|
| 294 |
+
"semantic_fragments_nli",
|
| 295 |
+
"dataset_train_nli",
|
| 296 |
+
"nlgraph",
|
| 297 |
+
"ruletaker",
|
| 298 |
+
"PARARULE-Plus",
|
| 299 |
+
"logical-entailment",
|
| 300 |
+
"nope",
|
| 301 |
+
"LogicNLI",
|
| 302 |
+
"contract-nli/contractnli_a/seg",
|
| 303 |
+
"contract-nli/contractnli_b/full",
|
| 304 |
+
"nli4ct_semeval2024",
|
| 305 |
+
"biosift-nli",
|
| 306 |
+
"SIGA-nli",
|
| 307 |
+
"FOL-nli",
|
| 308 |
+
"doc-nli",
|
| 309 |
+
"mctest-nli",
|
| 310 |
+
"natural-language-satisfiability",
|
| 311 |
+
"idioms-nli",
|
| 312 |
+
"lifecycle-entailment",
|
| 313 |
+
"MSciNLI",
|
| 314 |
+
"hover-3way/nli",
|
| 315 |
+
"seahorse_summarization_evaluation",
|
| 316 |
+
"missing-item-prediction/contrastive",
|
| 317 |
+
"Pol_NLI",
|
| 318 |
+
"synthetic-retrieval-NLI/count",
|
| 319 |
+
"synthetic-retrieval-NLI/position",
|
| 320 |
+
"synthetic-retrieval-NLI/binary",
|
| 321 |
+
"babi_nli",
|
| 322 |
+
"gen_debiased_nli"
|
| 323 |
+
],
|
| 324 |
+
"torch_dtype": "float16",
|
| 325 |
+
"transformers_version": "4.48.0.dev0",
|
| 326 |
+
"vocab_size": 50368
|
| 327 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e14f48fcfbc6f3b13c71d055ca9f37c3e1456b1d16cb4b9f1e83d43f0f61e1d7
|
| 3 |
+
size 299228486
|
runs/Jul09_16-45-39_170defa71826/events.out.tfevents.1752079551.170defa71826.1791.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15ad6ed946da92508098dc890a3795955598c1f9763cb4f674c11d9b262c0933
|
| 3 |
+
size 12466
|
runs/Jul09_17-03-20_170defa71826/events.out.tfevents.1752080601.170defa71826.15192.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e74667b6f2d52b07869db5376a17dce202aa951b7b11d696817ca358d92df5da
|
| 3 |
+
size 19788
|
runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082643.170defa71826.15192.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bba78d46d9156993d42dd021473a2dee796c775a9b4463ae6d813c8a49fd7d1
|
| 3 |
+
size 9938
|
runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082678.170defa71826.15192.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ce09a3e004559d50de80b68b8673217e8ffd229a09011d89be254a4b29beea4
|
| 3 |
+
size 9938
|
runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082738.170defa71826.15192.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d83b22ee0d6b71e7b9c91e9cc378ca9bc79ef03a2d16309dd3e0ebb8f7a972d
|
| 3 |
+
size 9938
|
runs/Jul09_17-37-15_170defa71826/events.out.tfevents.1752082763.170defa71826.15192.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fccc7cdeca1e34918aee4c339c824c87bddef59315b32ba8b02a048b3986faff
|
| 3 |
+
size 126780
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65bd28319d282c8149dd04becc2bcfb08fab70c958fba3a0ce87539d3e964c8a
|
| 3 |
+
size 5368
|