Upload folder using huggingface_hub
Browse files- config.json +266 -0
- label_encoder.joblib +3 -0
- model.safetensors +3 -0
- results/checkpoint-411/config.json +266 -0
- results/checkpoint-411/model.safetensors +3 -0
- results/checkpoint-411/optimizer.pt +3 -0
- results/checkpoint-411/rng_state.pth +3 -0
- results/checkpoint-411/scheduler.pt +3 -0
- results/checkpoint-411/trainer_state.json +337 -0
- results/checkpoint-411/training_args.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4",
|
| 16 |
+
"5": "LABEL_5",
|
| 17 |
+
"6": "LABEL_6",
|
| 18 |
+
"7": "LABEL_7",
|
| 19 |
+
"8": "LABEL_8",
|
| 20 |
+
"9": "LABEL_9",
|
| 21 |
+
"10": "LABEL_10",
|
| 22 |
+
"11": "LABEL_11",
|
| 23 |
+
"12": "LABEL_12",
|
| 24 |
+
"13": "LABEL_13",
|
| 25 |
+
"14": "LABEL_14",
|
| 26 |
+
"15": "LABEL_15",
|
| 27 |
+
"16": "LABEL_16",
|
| 28 |
+
"17": "LABEL_17",
|
| 29 |
+
"18": "LABEL_18",
|
| 30 |
+
"19": "LABEL_19",
|
| 31 |
+
"20": "LABEL_20",
|
| 32 |
+
"21": "LABEL_21",
|
| 33 |
+
"22": "LABEL_22",
|
| 34 |
+
"23": "LABEL_23",
|
| 35 |
+
"24": "LABEL_24",
|
| 36 |
+
"25": "LABEL_25",
|
| 37 |
+
"26": "LABEL_26",
|
| 38 |
+
"27": "LABEL_27",
|
| 39 |
+
"28": "LABEL_28",
|
| 40 |
+
"29": "LABEL_29",
|
| 41 |
+
"30": "LABEL_30",
|
| 42 |
+
"31": "LABEL_31",
|
| 43 |
+
"32": "LABEL_32",
|
| 44 |
+
"33": "LABEL_33",
|
| 45 |
+
"34": "LABEL_34",
|
| 46 |
+
"35": "LABEL_35",
|
| 47 |
+
"36": "LABEL_36",
|
| 48 |
+
"37": "LABEL_37",
|
| 49 |
+
"38": "LABEL_38",
|
| 50 |
+
"39": "LABEL_39",
|
| 51 |
+
"40": "LABEL_40",
|
| 52 |
+
"41": "LABEL_41",
|
| 53 |
+
"42": "LABEL_42",
|
| 54 |
+
"43": "LABEL_43",
|
| 55 |
+
"44": "LABEL_44",
|
| 56 |
+
"45": "LABEL_45",
|
| 57 |
+
"46": "LABEL_46",
|
| 58 |
+
"47": "LABEL_47",
|
| 59 |
+
"48": "LABEL_48",
|
| 60 |
+
"49": "LABEL_49",
|
| 61 |
+
"50": "LABEL_50",
|
| 62 |
+
"51": "LABEL_51",
|
| 63 |
+
"52": "LABEL_52",
|
| 64 |
+
"53": "LABEL_53",
|
| 65 |
+
"54": "LABEL_54",
|
| 66 |
+
"55": "LABEL_55",
|
| 67 |
+
"56": "LABEL_56",
|
| 68 |
+
"57": "LABEL_57",
|
| 69 |
+
"58": "LABEL_58",
|
| 70 |
+
"59": "LABEL_59",
|
| 71 |
+
"60": "LABEL_60",
|
| 72 |
+
"61": "LABEL_61",
|
| 73 |
+
"62": "LABEL_62",
|
| 74 |
+
"63": "LABEL_63",
|
| 75 |
+
"64": "LABEL_64",
|
| 76 |
+
"65": "LABEL_65",
|
| 77 |
+
"66": "LABEL_66",
|
| 78 |
+
"67": "LABEL_67",
|
| 79 |
+
"68": "LABEL_68",
|
| 80 |
+
"69": "LABEL_69",
|
| 81 |
+
"70": "LABEL_70",
|
| 82 |
+
"71": "LABEL_71",
|
| 83 |
+
"72": "LABEL_72",
|
| 84 |
+
"73": "LABEL_73",
|
| 85 |
+
"74": "LABEL_74",
|
| 86 |
+
"75": "LABEL_75",
|
| 87 |
+
"76": "LABEL_76",
|
| 88 |
+
"77": "LABEL_77",
|
| 89 |
+
"78": "LABEL_78",
|
| 90 |
+
"79": "LABEL_79",
|
| 91 |
+
"80": "LABEL_80",
|
| 92 |
+
"81": "LABEL_81",
|
| 93 |
+
"82": "LABEL_82",
|
| 94 |
+
"83": "LABEL_83",
|
| 95 |
+
"84": "LABEL_84",
|
| 96 |
+
"85": "LABEL_85",
|
| 97 |
+
"86": "LABEL_86",
|
| 98 |
+
"87": "LABEL_87",
|
| 99 |
+
"88": "LABEL_88",
|
| 100 |
+
"89": "LABEL_89",
|
| 101 |
+
"90": "LABEL_90",
|
| 102 |
+
"91": "LABEL_91",
|
| 103 |
+
"92": "LABEL_92",
|
| 104 |
+
"93": "LABEL_93",
|
| 105 |
+
"94": "LABEL_94",
|
| 106 |
+
"95": "LABEL_95",
|
| 107 |
+
"96": "LABEL_96",
|
| 108 |
+
"97": "LABEL_97",
|
| 109 |
+
"98": "LABEL_98",
|
| 110 |
+
"99": "LABEL_99",
|
| 111 |
+
"100": "LABEL_100",
|
| 112 |
+
"101": "LABEL_101",
|
| 113 |
+
"102": "LABEL_102",
|
| 114 |
+
"103": "LABEL_103",
|
| 115 |
+
"104": "LABEL_104",
|
| 116 |
+
"105": "LABEL_105",
|
| 117 |
+
"106": "LABEL_106",
|
| 118 |
+
"107": "LABEL_107",
|
| 119 |
+
"108": "LABEL_108",
|
| 120 |
+
"109": "LABEL_109",
|
| 121 |
+
"110": "LABEL_110",
|
| 122 |
+
"111": "LABEL_111",
|
| 123 |
+
"112": "LABEL_112",
|
| 124 |
+
"113": "LABEL_113",
|
| 125 |
+
"114": "LABEL_114",
|
| 126 |
+
"115": "LABEL_115",
|
| 127 |
+
"116": "LABEL_116",
|
| 128 |
+
"117": "LABEL_117",
|
| 129 |
+
"118": "LABEL_118"
|
| 130 |
+
},
|
| 131 |
+
"initializer_range": 0.02,
|
| 132 |
+
"label2id": {
|
| 133 |
+
"LABEL_0": 0,
|
| 134 |
+
"LABEL_1": 1,
|
| 135 |
+
"LABEL_10": 10,
|
| 136 |
+
"LABEL_100": 100,
|
| 137 |
+
"LABEL_101": 101,
|
| 138 |
+
"LABEL_102": 102,
|
| 139 |
+
"LABEL_103": 103,
|
| 140 |
+
"LABEL_104": 104,
|
| 141 |
+
"LABEL_105": 105,
|
| 142 |
+
"LABEL_106": 106,
|
| 143 |
+
"LABEL_107": 107,
|
| 144 |
+
"LABEL_108": 108,
|
| 145 |
+
"LABEL_109": 109,
|
| 146 |
+
"LABEL_11": 11,
|
| 147 |
+
"LABEL_110": 110,
|
| 148 |
+
"LABEL_111": 111,
|
| 149 |
+
"LABEL_112": 112,
|
| 150 |
+
"LABEL_113": 113,
|
| 151 |
+
"LABEL_114": 114,
|
| 152 |
+
"LABEL_115": 115,
|
| 153 |
+
"LABEL_116": 116,
|
| 154 |
+
"LABEL_117": 117,
|
| 155 |
+
"LABEL_118": 118,
|
| 156 |
+
"LABEL_12": 12,
|
| 157 |
+
"LABEL_13": 13,
|
| 158 |
+
"LABEL_14": 14,
|
| 159 |
+
"LABEL_15": 15,
|
| 160 |
+
"LABEL_16": 16,
|
| 161 |
+
"LABEL_17": 17,
|
| 162 |
+
"LABEL_18": 18,
|
| 163 |
+
"LABEL_19": 19,
|
| 164 |
+
"LABEL_2": 2,
|
| 165 |
+
"LABEL_20": 20,
|
| 166 |
+
"LABEL_21": 21,
|
| 167 |
+
"LABEL_22": 22,
|
| 168 |
+
"LABEL_23": 23,
|
| 169 |
+
"LABEL_24": 24,
|
| 170 |
+
"LABEL_25": 25,
|
| 171 |
+
"LABEL_26": 26,
|
| 172 |
+
"LABEL_27": 27,
|
| 173 |
+
"LABEL_28": 28,
|
| 174 |
+
"LABEL_29": 29,
|
| 175 |
+
"LABEL_3": 3,
|
| 176 |
+
"LABEL_30": 30,
|
| 177 |
+
"LABEL_31": 31,
|
| 178 |
+
"LABEL_32": 32,
|
| 179 |
+
"LABEL_33": 33,
|
| 180 |
+
"LABEL_34": 34,
|
| 181 |
+
"LABEL_35": 35,
|
| 182 |
+
"LABEL_36": 36,
|
| 183 |
+
"LABEL_37": 37,
|
| 184 |
+
"LABEL_38": 38,
|
| 185 |
+
"LABEL_39": 39,
|
| 186 |
+
"LABEL_4": 4,
|
| 187 |
+
"LABEL_40": 40,
|
| 188 |
+
"LABEL_41": 41,
|
| 189 |
+
"LABEL_42": 42,
|
| 190 |
+
"LABEL_43": 43,
|
| 191 |
+
"LABEL_44": 44,
|
| 192 |
+
"LABEL_45": 45,
|
| 193 |
+
"LABEL_46": 46,
|
| 194 |
+
"LABEL_47": 47,
|
| 195 |
+
"LABEL_48": 48,
|
| 196 |
+
"LABEL_49": 49,
|
| 197 |
+
"LABEL_5": 5,
|
| 198 |
+
"LABEL_50": 50,
|
| 199 |
+
"LABEL_51": 51,
|
| 200 |
+
"LABEL_52": 52,
|
| 201 |
+
"LABEL_53": 53,
|
| 202 |
+
"LABEL_54": 54,
|
| 203 |
+
"LABEL_55": 55,
|
| 204 |
+
"LABEL_56": 56,
|
| 205 |
+
"LABEL_57": 57,
|
| 206 |
+
"LABEL_58": 58,
|
| 207 |
+
"LABEL_59": 59,
|
| 208 |
+
"LABEL_6": 6,
|
| 209 |
+
"LABEL_60": 60,
|
| 210 |
+
"LABEL_61": 61,
|
| 211 |
+
"LABEL_62": 62,
|
| 212 |
+
"LABEL_63": 63,
|
| 213 |
+
"LABEL_64": 64,
|
| 214 |
+
"LABEL_65": 65,
|
| 215 |
+
"LABEL_66": 66,
|
| 216 |
+
"LABEL_67": 67,
|
| 217 |
+
"LABEL_68": 68,
|
| 218 |
+
"LABEL_69": 69,
|
| 219 |
+
"LABEL_7": 7,
|
| 220 |
+
"LABEL_70": 70,
|
| 221 |
+
"LABEL_71": 71,
|
| 222 |
+
"LABEL_72": 72,
|
| 223 |
+
"LABEL_73": 73,
|
| 224 |
+
"LABEL_74": 74,
|
| 225 |
+
"LABEL_75": 75,
|
| 226 |
+
"LABEL_76": 76,
|
| 227 |
+
"LABEL_77": 77,
|
| 228 |
+
"LABEL_78": 78,
|
| 229 |
+
"LABEL_79": 79,
|
| 230 |
+
"LABEL_8": 8,
|
| 231 |
+
"LABEL_80": 80,
|
| 232 |
+
"LABEL_81": 81,
|
| 233 |
+
"LABEL_82": 82,
|
| 234 |
+
"LABEL_83": 83,
|
| 235 |
+
"LABEL_84": 84,
|
| 236 |
+
"LABEL_85": 85,
|
| 237 |
+
"LABEL_86": 86,
|
| 238 |
+
"LABEL_87": 87,
|
| 239 |
+
"LABEL_88": 88,
|
| 240 |
+
"LABEL_89": 89,
|
| 241 |
+
"LABEL_9": 9,
|
| 242 |
+
"LABEL_90": 90,
|
| 243 |
+
"LABEL_91": 91,
|
| 244 |
+
"LABEL_92": 92,
|
| 245 |
+
"LABEL_93": 93,
|
| 246 |
+
"LABEL_94": 94,
|
| 247 |
+
"LABEL_95": 95,
|
| 248 |
+
"LABEL_96": 96,
|
| 249 |
+
"LABEL_97": 97,
|
| 250 |
+
"LABEL_98": 98,
|
| 251 |
+
"LABEL_99": 99
|
| 252 |
+
},
|
| 253 |
+
"max_position_embeddings": 512,
|
| 254 |
+
"model_type": "distilbert",
|
| 255 |
+
"n_heads": 12,
|
| 256 |
+
"n_layers": 6,
|
| 257 |
+
"pad_token_id": 0,
|
| 258 |
+
"problem_type": "single_label_classification",
|
| 259 |
+
"qa_dropout": 0.1,
|
| 260 |
+
"seq_classif_dropout": 0.2,
|
| 261 |
+
"sinusoidal_pos_embds": false,
|
| 262 |
+
"tie_weights_": true,
|
| 263 |
+
"torch_dtype": "float32",
|
| 264 |
+
"transformers_version": "4.55.2",
|
| 265 |
+
"vocab_size": 30522
|
| 266 |
+
}
|
label_encoder.joblib
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f067c5d3021dc4624d9e1d9625d516cddb3642bf21985499bd890414092ce1d
|
| 3 |
+
size 3471
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c48fbc496e666bce9c5e8a5100c84963fcf87e35c510a94accb9cc1eaa4df63c
|
| 3 |
+
size 268192468
|
results/checkpoint-411/config.json
ADDED
|
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4",
|
| 16 |
+
"5": "LABEL_5",
|
| 17 |
+
"6": "LABEL_6",
|
| 18 |
+
"7": "LABEL_7",
|
| 19 |
+
"8": "LABEL_8",
|
| 20 |
+
"9": "LABEL_9",
|
| 21 |
+
"10": "LABEL_10",
|
| 22 |
+
"11": "LABEL_11",
|
| 23 |
+
"12": "LABEL_12",
|
| 24 |
+
"13": "LABEL_13",
|
| 25 |
+
"14": "LABEL_14",
|
| 26 |
+
"15": "LABEL_15",
|
| 27 |
+
"16": "LABEL_16",
|
| 28 |
+
"17": "LABEL_17",
|
| 29 |
+
"18": "LABEL_18",
|
| 30 |
+
"19": "LABEL_19",
|
| 31 |
+
"20": "LABEL_20",
|
| 32 |
+
"21": "LABEL_21",
|
| 33 |
+
"22": "LABEL_22",
|
| 34 |
+
"23": "LABEL_23",
|
| 35 |
+
"24": "LABEL_24",
|
| 36 |
+
"25": "LABEL_25",
|
| 37 |
+
"26": "LABEL_26",
|
| 38 |
+
"27": "LABEL_27",
|
| 39 |
+
"28": "LABEL_28",
|
| 40 |
+
"29": "LABEL_29",
|
| 41 |
+
"30": "LABEL_30",
|
| 42 |
+
"31": "LABEL_31",
|
| 43 |
+
"32": "LABEL_32",
|
| 44 |
+
"33": "LABEL_33",
|
| 45 |
+
"34": "LABEL_34",
|
| 46 |
+
"35": "LABEL_35",
|
| 47 |
+
"36": "LABEL_36",
|
| 48 |
+
"37": "LABEL_37",
|
| 49 |
+
"38": "LABEL_38",
|
| 50 |
+
"39": "LABEL_39",
|
| 51 |
+
"40": "LABEL_40",
|
| 52 |
+
"41": "LABEL_41",
|
| 53 |
+
"42": "LABEL_42",
|
| 54 |
+
"43": "LABEL_43",
|
| 55 |
+
"44": "LABEL_44",
|
| 56 |
+
"45": "LABEL_45",
|
| 57 |
+
"46": "LABEL_46",
|
| 58 |
+
"47": "LABEL_47",
|
| 59 |
+
"48": "LABEL_48",
|
| 60 |
+
"49": "LABEL_49",
|
| 61 |
+
"50": "LABEL_50",
|
| 62 |
+
"51": "LABEL_51",
|
| 63 |
+
"52": "LABEL_52",
|
| 64 |
+
"53": "LABEL_53",
|
| 65 |
+
"54": "LABEL_54",
|
| 66 |
+
"55": "LABEL_55",
|
| 67 |
+
"56": "LABEL_56",
|
| 68 |
+
"57": "LABEL_57",
|
| 69 |
+
"58": "LABEL_58",
|
| 70 |
+
"59": "LABEL_59",
|
| 71 |
+
"60": "LABEL_60",
|
| 72 |
+
"61": "LABEL_61",
|
| 73 |
+
"62": "LABEL_62",
|
| 74 |
+
"63": "LABEL_63",
|
| 75 |
+
"64": "LABEL_64",
|
| 76 |
+
"65": "LABEL_65",
|
| 77 |
+
"66": "LABEL_66",
|
| 78 |
+
"67": "LABEL_67",
|
| 79 |
+
"68": "LABEL_68",
|
| 80 |
+
"69": "LABEL_69",
|
| 81 |
+
"70": "LABEL_70",
|
| 82 |
+
"71": "LABEL_71",
|
| 83 |
+
"72": "LABEL_72",
|
| 84 |
+
"73": "LABEL_73",
|
| 85 |
+
"74": "LABEL_74",
|
| 86 |
+
"75": "LABEL_75",
|
| 87 |
+
"76": "LABEL_76",
|
| 88 |
+
"77": "LABEL_77",
|
| 89 |
+
"78": "LABEL_78",
|
| 90 |
+
"79": "LABEL_79",
|
| 91 |
+
"80": "LABEL_80",
|
| 92 |
+
"81": "LABEL_81",
|
| 93 |
+
"82": "LABEL_82",
|
| 94 |
+
"83": "LABEL_83",
|
| 95 |
+
"84": "LABEL_84",
|
| 96 |
+
"85": "LABEL_85",
|
| 97 |
+
"86": "LABEL_86",
|
| 98 |
+
"87": "LABEL_87",
|
| 99 |
+
"88": "LABEL_88",
|
| 100 |
+
"89": "LABEL_89",
|
| 101 |
+
"90": "LABEL_90",
|
| 102 |
+
"91": "LABEL_91",
|
| 103 |
+
"92": "LABEL_92",
|
| 104 |
+
"93": "LABEL_93",
|
| 105 |
+
"94": "LABEL_94",
|
| 106 |
+
"95": "LABEL_95",
|
| 107 |
+
"96": "LABEL_96",
|
| 108 |
+
"97": "LABEL_97",
|
| 109 |
+
"98": "LABEL_98",
|
| 110 |
+
"99": "LABEL_99",
|
| 111 |
+
"100": "LABEL_100",
|
| 112 |
+
"101": "LABEL_101",
|
| 113 |
+
"102": "LABEL_102",
|
| 114 |
+
"103": "LABEL_103",
|
| 115 |
+
"104": "LABEL_104",
|
| 116 |
+
"105": "LABEL_105",
|
| 117 |
+
"106": "LABEL_106",
|
| 118 |
+
"107": "LABEL_107",
|
| 119 |
+
"108": "LABEL_108",
|
| 120 |
+
"109": "LABEL_109",
|
| 121 |
+
"110": "LABEL_110",
|
| 122 |
+
"111": "LABEL_111",
|
| 123 |
+
"112": "LABEL_112",
|
| 124 |
+
"113": "LABEL_113",
|
| 125 |
+
"114": "LABEL_114",
|
| 126 |
+
"115": "LABEL_115",
|
| 127 |
+
"116": "LABEL_116",
|
| 128 |
+
"117": "LABEL_117",
|
| 129 |
+
"118": "LABEL_118"
|
| 130 |
+
},
|
| 131 |
+
"initializer_range": 0.02,
|
| 132 |
+
"label2id": {
|
| 133 |
+
"LABEL_0": 0,
|
| 134 |
+
"LABEL_1": 1,
|
| 135 |
+
"LABEL_10": 10,
|
| 136 |
+
"LABEL_100": 100,
|
| 137 |
+
"LABEL_101": 101,
|
| 138 |
+
"LABEL_102": 102,
|
| 139 |
+
"LABEL_103": 103,
|
| 140 |
+
"LABEL_104": 104,
|
| 141 |
+
"LABEL_105": 105,
|
| 142 |
+
"LABEL_106": 106,
|
| 143 |
+
"LABEL_107": 107,
|
| 144 |
+
"LABEL_108": 108,
|
| 145 |
+
"LABEL_109": 109,
|
| 146 |
+
"LABEL_11": 11,
|
| 147 |
+
"LABEL_110": 110,
|
| 148 |
+
"LABEL_111": 111,
|
| 149 |
+
"LABEL_112": 112,
|
| 150 |
+
"LABEL_113": 113,
|
| 151 |
+
"LABEL_114": 114,
|
| 152 |
+
"LABEL_115": 115,
|
| 153 |
+
"LABEL_116": 116,
|
| 154 |
+
"LABEL_117": 117,
|
| 155 |
+
"LABEL_118": 118,
|
| 156 |
+
"LABEL_12": 12,
|
| 157 |
+
"LABEL_13": 13,
|
| 158 |
+
"LABEL_14": 14,
|
| 159 |
+
"LABEL_15": 15,
|
| 160 |
+
"LABEL_16": 16,
|
| 161 |
+
"LABEL_17": 17,
|
| 162 |
+
"LABEL_18": 18,
|
| 163 |
+
"LABEL_19": 19,
|
| 164 |
+
"LABEL_2": 2,
|
| 165 |
+
"LABEL_20": 20,
|
| 166 |
+
"LABEL_21": 21,
|
| 167 |
+
"LABEL_22": 22,
|
| 168 |
+
"LABEL_23": 23,
|
| 169 |
+
"LABEL_24": 24,
|
| 170 |
+
"LABEL_25": 25,
|
| 171 |
+
"LABEL_26": 26,
|
| 172 |
+
"LABEL_27": 27,
|
| 173 |
+
"LABEL_28": 28,
|
| 174 |
+
"LABEL_29": 29,
|
| 175 |
+
"LABEL_3": 3,
|
| 176 |
+
"LABEL_30": 30,
|
| 177 |
+
"LABEL_31": 31,
|
| 178 |
+
"LABEL_32": 32,
|
| 179 |
+
"LABEL_33": 33,
|
| 180 |
+
"LABEL_34": 34,
|
| 181 |
+
"LABEL_35": 35,
|
| 182 |
+
"LABEL_36": 36,
|
| 183 |
+
"LABEL_37": 37,
|
| 184 |
+
"LABEL_38": 38,
|
| 185 |
+
"LABEL_39": 39,
|
| 186 |
+
"LABEL_4": 4,
|
| 187 |
+
"LABEL_40": 40,
|
| 188 |
+
"LABEL_41": 41,
|
| 189 |
+
"LABEL_42": 42,
|
| 190 |
+
"LABEL_43": 43,
|
| 191 |
+
"LABEL_44": 44,
|
| 192 |
+
"LABEL_45": 45,
|
| 193 |
+
"LABEL_46": 46,
|
| 194 |
+
"LABEL_47": 47,
|
| 195 |
+
"LABEL_48": 48,
|
| 196 |
+
"LABEL_49": 49,
|
| 197 |
+
"LABEL_5": 5,
|
| 198 |
+
"LABEL_50": 50,
|
| 199 |
+
"LABEL_51": 51,
|
| 200 |
+
"LABEL_52": 52,
|
| 201 |
+
"LABEL_53": 53,
|
| 202 |
+
"LABEL_54": 54,
|
| 203 |
+
"LABEL_55": 55,
|
| 204 |
+
"LABEL_56": 56,
|
| 205 |
+
"LABEL_57": 57,
|
| 206 |
+
"LABEL_58": 58,
|
| 207 |
+
"LABEL_59": 59,
|
| 208 |
+
"LABEL_6": 6,
|
| 209 |
+
"LABEL_60": 60,
|
| 210 |
+
"LABEL_61": 61,
|
| 211 |
+
"LABEL_62": 62,
|
| 212 |
+
"LABEL_63": 63,
|
| 213 |
+
"LABEL_64": 64,
|
| 214 |
+
"LABEL_65": 65,
|
| 215 |
+
"LABEL_66": 66,
|
| 216 |
+
"LABEL_67": 67,
|
| 217 |
+
"LABEL_68": 68,
|
| 218 |
+
"LABEL_69": 69,
|
| 219 |
+
"LABEL_7": 7,
|
| 220 |
+
"LABEL_70": 70,
|
| 221 |
+
"LABEL_71": 71,
|
| 222 |
+
"LABEL_72": 72,
|
| 223 |
+
"LABEL_73": 73,
|
| 224 |
+
"LABEL_74": 74,
|
| 225 |
+
"LABEL_75": 75,
|
| 226 |
+
"LABEL_76": 76,
|
| 227 |
+
"LABEL_77": 77,
|
| 228 |
+
"LABEL_78": 78,
|
| 229 |
+
"LABEL_79": 79,
|
| 230 |
+
"LABEL_8": 8,
|
| 231 |
+
"LABEL_80": 80,
|
| 232 |
+
"LABEL_81": 81,
|
| 233 |
+
"LABEL_82": 82,
|
| 234 |
+
"LABEL_83": 83,
|
| 235 |
+
"LABEL_84": 84,
|
| 236 |
+
"LABEL_85": 85,
|
| 237 |
+
"LABEL_86": 86,
|
| 238 |
+
"LABEL_87": 87,
|
| 239 |
+
"LABEL_88": 88,
|
| 240 |
+
"LABEL_89": 89,
|
| 241 |
+
"LABEL_9": 9,
|
| 242 |
+
"LABEL_90": 90,
|
| 243 |
+
"LABEL_91": 91,
|
| 244 |
+
"LABEL_92": 92,
|
| 245 |
+
"LABEL_93": 93,
|
| 246 |
+
"LABEL_94": 94,
|
| 247 |
+
"LABEL_95": 95,
|
| 248 |
+
"LABEL_96": 96,
|
| 249 |
+
"LABEL_97": 97,
|
| 250 |
+
"LABEL_98": 98,
|
| 251 |
+
"LABEL_99": 99
|
| 252 |
+
},
|
| 253 |
+
"max_position_embeddings": 512,
|
| 254 |
+
"model_type": "distilbert",
|
| 255 |
+
"n_heads": 12,
|
| 256 |
+
"n_layers": 6,
|
| 257 |
+
"pad_token_id": 0,
|
| 258 |
+
"problem_type": "single_label_classification",
|
| 259 |
+
"qa_dropout": 0.1,
|
| 260 |
+
"seq_classif_dropout": 0.2,
|
| 261 |
+
"sinusoidal_pos_embds": false,
|
| 262 |
+
"tie_weights_": true,
|
| 263 |
+
"torch_dtype": "float32",
|
| 264 |
+
"transformers_version": "4.55.2",
|
| 265 |
+
"vocab_size": 30522
|
| 266 |
+
}
|
results/checkpoint-411/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c48fbc496e666bce9c5e8a5100c84963fcf87e35c510a94accb9cc1eaa4df63c
|
| 3 |
+
size 268192468
|
results/checkpoint-411/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb3f7bcf54442c7421dc73c0fb922cf3c4f981e604cf568507a6b7f4b43c49e9
|
| 3 |
+
size 536444619
|
results/checkpoint-411/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83011902e1e4a12dbc3d56a97a6a764653f4f62420143b03b1cccfebdd9ef701
|
| 3 |
+
size 14455
|
results/checkpoint-411/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd42308765ef2663a827d2f151e980dbc9aab8815c66495c3ae60d276d5771b1
|
| 3 |
+
size 1465
|
results/checkpoint-411/trainer_state.json
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 411,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.072992700729927,
|
| 14 |
+
"grad_norm": 4.225296974182129,
|
| 15 |
+
"learning_rate": 9e-07,
|
| 16 |
+
"loss": 4.7147,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.145985401459854,
|
| 21 |
+
"grad_norm": 3.1379406452178955,
|
| 22 |
+
"learning_rate": 1.9e-06,
|
| 23 |
+
"loss": 4.7051,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.21897810218978103,
|
| 28 |
+
"grad_norm": 2.993072748184204,
|
| 29 |
+
"learning_rate": 2.9e-06,
|
| 30 |
+
"loss": 4.68,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.291970802919708,
|
| 35 |
+
"grad_norm": 3.7511308193206787,
|
| 36 |
+
"learning_rate": 3.9e-06,
|
| 37 |
+
"loss": 4.6338,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.36496350364963503,
|
| 42 |
+
"grad_norm": 4.803622245788574,
|
| 43 |
+
"learning_rate": 4.9000000000000005e-06,
|
| 44 |
+
"loss": 4.5603,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.43795620437956206,
|
| 49 |
+
"grad_norm": 3.9980692863464355,
|
| 50 |
+
"learning_rate": 5.9e-06,
|
| 51 |
+
"loss": 4.4781,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.5109489051094891,
|
| 56 |
+
"grad_norm": 6.019293785095215,
|
| 57 |
+
"learning_rate": 6.900000000000001e-06,
|
| 58 |
+
"loss": 4.2795,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.583941605839416,
|
| 63 |
+
"grad_norm": 5.458958148956299,
|
| 64 |
+
"learning_rate": 7.9e-06,
|
| 65 |
+
"loss": 4.0129,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.656934306569343,
|
| 70 |
+
"grad_norm": 5.672916412353516,
|
| 71 |
+
"learning_rate": 8.9e-06,
|
| 72 |
+
"loss": 3.721,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7299270072992701,
|
| 77 |
+
"grad_norm": 5.224255084991455,
|
| 78 |
+
"learning_rate": 9.900000000000002e-06,
|
| 79 |
+
"loss": 3.6731,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.8029197080291971,
|
| 84 |
+
"grad_norm": 4.30133581161499,
|
| 85 |
+
"learning_rate": 1.09e-05,
|
| 86 |
+
"loss": 3.3891,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8759124087591241,
|
| 91 |
+
"grad_norm": 4.222207546234131,
|
| 92 |
+
"learning_rate": 1.19e-05,
|
| 93 |
+
"loss": 3.1892,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.948905109489051,
|
| 98 |
+
"grad_norm": 4.49671745300293,
|
| 99 |
+
"learning_rate": 1.29e-05,
|
| 100 |
+
"loss": 2.8813,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.0,
|
| 105 |
+
"eval_loss": 2.753905773162842,
|
| 106 |
+
"eval_runtime": 16.8702,
|
| 107 |
+
"eval_samples_per_second": 32.483,
|
| 108 |
+
"eval_steps_per_second": 0.533,
|
| 109 |
+
"step": 137
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.0218978102189782,
|
| 113 |
+
"grad_norm": 3.8793041706085205,
|
| 114 |
+
"learning_rate": 1.3900000000000002e-05,
|
| 115 |
+
"loss": 2.6665,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.094890510948905,
|
| 120 |
+
"grad_norm": 4.79223108291626,
|
| 121 |
+
"learning_rate": 1.49e-05,
|
| 122 |
+
"loss": 2.7233,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.167883211678832,
|
| 127 |
+
"grad_norm": 4.0730156898498535,
|
| 128 |
+
"learning_rate": 1.59e-05,
|
| 129 |
+
"loss": 2.6488,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.2408759124087592,
|
| 134 |
+
"grad_norm": 3.606416702270508,
|
| 135 |
+
"learning_rate": 1.69e-05,
|
| 136 |
+
"loss": 2.2883,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.313868613138686,
|
| 141 |
+
"grad_norm": 3.4078264236450195,
|
| 142 |
+
"learning_rate": 1.79e-05,
|
| 143 |
+
"loss": 2.1266,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.3868613138686132,
|
| 148 |
+
"grad_norm": 3.1551127433776855,
|
| 149 |
+
"learning_rate": 1.8900000000000002e-05,
|
| 150 |
+
"loss": 2.135,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.4598540145985401,
|
| 155 |
+
"grad_norm": 4.102710723876953,
|
| 156 |
+
"learning_rate": 1.9900000000000003e-05,
|
| 157 |
+
"loss": 2.2372,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.5328467153284673,
|
| 162 |
+
"grad_norm": 5.5426554679870605,
|
| 163 |
+
"learning_rate": 2.09e-05,
|
| 164 |
+
"loss": 2.2397,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.6058394160583942,
|
| 169 |
+
"grad_norm": 4.54184627532959,
|
| 170 |
+
"learning_rate": 2.19e-05,
|
| 171 |
+
"loss": 1.8648,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.6788321167883211,
|
| 176 |
+
"grad_norm": 3.52703595161438,
|
| 177 |
+
"learning_rate": 2.29e-05,
|
| 178 |
+
"loss": 2.1475,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.7518248175182483,
|
| 183 |
+
"grad_norm": 4.353190898895264,
|
| 184 |
+
"learning_rate": 2.39e-05,
|
| 185 |
+
"loss": 1.6978,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.8248175182481752,
|
| 190 |
+
"grad_norm": 2.747074604034424,
|
| 191 |
+
"learning_rate": 2.4900000000000002e-05,
|
| 192 |
+
"loss": 1.4718,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.897810218978102,
|
| 197 |
+
"grad_norm": 3.765878200531006,
|
| 198 |
+
"learning_rate": 2.5900000000000003e-05,
|
| 199 |
+
"loss": 1.2905,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.9708029197080292,
|
| 204 |
+
"grad_norm": 3.548633575439453,
|
| 205 |
+
"learning_rate": 2.6900000000000003e-05,
|
| 206 |
+
"loss": 1.4625,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.0,
|
| 211 |
+
"eval_loss": 1.2935103178024292,
|
| 212 |
+
"eval_runtime": 17.3264,
|
| 213 |
+
"eval_samples_per_second": 31.628,
|
| 214 |
+
"eval_steps_per_second": 0.519,
|
| 215 |
+
"step": 274
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.0437956204379564,
|
| 219 |
+
"grad_norm": 3.9908804893493652,
|
| 220 |
+
"learning_rate": 2.7900000000000004e-05,
|
| 221 |
+
"loss": 1.4628,
|
| 222 |
+
"step": 280
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.116788321167883,
|
| 226 |
+
"grad_norm": 3.394761800765991,
|
| 227 |
+
"learning_rate": 2.8899999999999998e-05,
|
| 228 |
+
"loss": 1.3286,
|
| 229 |
+
"step": 290
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.18978102189781,
|
| 233 |
+
"grad_norm": 2.8824572563171387,
|
| 234 |
+
"learning_rate": 2.9900000000000002e-05,
|
| 235 |
+
"loss": 1.1588,
|
| 236 |
+
"step": 300
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.2627737226277373,
|
| 240 |
+
"grad_norm": 3.1787123680114746,
|
| 241 |
+
"learning_rate": 3.09e-05,
|
| 242 |
+
"loss": 1.1587,
|
| 243 |
+
"step": 310
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.335766423357664,
|
| 247 |
+
"grad_norm": 3.589329242706299,
|
| 248 |
+
"learning_rate": 3.19e-05,
|
| 249 |
+
"loss": 1.1603,
|
| 250 |
+
"step": 320
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.408759124087591,
|
| 254 |
+
"grad_norm": 2.669541358947754,
|
| 255 |
+
"learning_rate": 3.29e-05,
|
| 256 |
+
"loss": 1.0705,
|
| 257 |
+
"step": 330
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.4817518248175183,
|
| 261 |
+
"grad_norm": 5.52268123626709,
|
| 262 |
+
"learning_rate": 3.3900000000000004e-05,
|
| 263 |
+
"loss": 1.1411,
|
| 264 |
+
"step": 340
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.554744525547445,
|
| 268 |
+
"grad_norm": 3.051318407058716,
|
| 269 |
+
"learning_rate": 3.49e-05,
|
| 270 |
+
"loss": 1.0764,
|
| 271 |
+
"step": 350
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.627737226277372,
|
| 275 |
+
"grad_norm": 3.43658185005188,
|
| 276 |
+
"learning_rate": 3.59e-05,
|
| 277 |
+
"loss": 1.0358,
|
| 278 |
+
"step": 360
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.7007299270072993,
|
| 282 |
+
"grad_norm": 4.066575527191162,
|
| 283 |
+
"learning_rate": 3.69e-05,
|
| 284 |
+
"loss": 0.7588,
|
| 285 |
+
"step": 370
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.7737226277372264,
|
| 289 |
+
"grad_norm": 3.2864415645599365,
|
| 290 |
+
"learning_rate": 3.79e-05,
|
| 291 |
+
"loss": 0.8228,
|
| 292 |
+
"step": 380
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.846715328467153,
|
| 296 |
+
"grad_norm": 3.6566617488861084,
|
| 297 |
+
"learning_rate": 3.8900000000000004e-05,
|
| 298 |
+
"loss": 0.7891,
|
| 299 |
+
"step": 390
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.9197080291970803,
|
| 303 |
+
"grad_norm": 2.7772223949432373,
|
| 304 |
+
"learning_rate": 3.99e-05,
|
| 305 |
+
"loss": 0.8423,
|
| 306 |
+
"step": 400
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.9927007299270074,
|
| 310 |
+
"grad_norm": 2.902259349822998,
|
| 311 |
+
"learning_rate": 4.09e-05,
|
| 312 |
+
"loss": 0.653,
|
| 313 |
+
"step": 410
|
| 314 |
+
}
|
| 315 |
+
],
|
| 316 |
+
"logging_steps": 10,
|
| 317 |
+
"max_steps": 411,
|
| 318 |
+
"num_input_tokens_seen": 0,
|
| 319 |
+
"num_train_epochs": 3,
|
| 320 |
+
"save_steps": 500,
|
| 321 |
+
"stateful_callbacks": {
|
| 322 |
+
"TrainerControl": {
|
| 323 |
+
"args": {
|
| 324 |
+
"should_epoch_stop": false,
|
| 325 |
+
"should_evaluate": false,
|
| 326 |
+
"should_log": false,
|
| 327 |
+
"should_save": true,
|
| 328 |
+
"should_training_stop": true
|
| 329 |
+
},
|
| 330 |
+
"attributes": {}
|
| 331 |
+
}
|
| 332 |
+
},
|
| 333 |
+
"total_flos": 218031684456960.0,
|
| 334 |
+
"train_batch_size": 16,
|
| 335 |
+
"trial_name": null,
|
| 336 |
+
"trial_params": null
|
| 337 |
+
}
|
results/checkpoint-411/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5abe80ed77c5c65b70b7c2c25ef1a374e233cb92d0262cc9568208a2e658e1
|
| 3 |
+
size 5777
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|