Training in progress, epoch 1
Browse files- config.json +152 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0,
|
| 24 |
+
"1": 1,
|
| 25 |
+
"10": 10,
|
| 26 |
+
"11": 11,
|
| 27 |
+
"12": 12,
|
| 28 |
+
"13": 13,
|
| 29 |
+
"14": 14,
|
| 30 |
+
"15": 15,
|
| 31 |
+
"16": 16,
|
| 32 |
+
"17": 17,
|
| 33 |
+
"18": 18,
|
| 34 |
+
"19": 19,
|
| 35 |
+
"2": 2,
|
| 36 |
+
"20": 20,
|
| 37 |
+
"21": 21,
|
| 38 |
+
"22": 22,
|
| 39 |
+
"23": 23,
|
| 40 |
+
"24": 24,
|
| 41 |
+
"25": 25,
|
| 42 |
+
"26": 26,
|
| 43 |
+
"27": 27,
|
| 44 |
+
"28": 28,
|
| 45 |
+
"29": 29,
|
| 46 |
+
"3": 3,
|
| 47 |
+
"30": 30,
|
| 48 |
+
"31": 31,
|
| 49 |
+
"32": 32,
|
| 50 |
+
"33": 33,
|
| 51 |
+
"34": 34,
|
| 52 |
+
"35": 35,
|
| 53 |
+
"36": 36,
|
| 54 |
+
"37": 37,
|
| 55 |
+
"38": 38,
|
| 56 |
+
"39": 39,
|
| 57 |
+
"4": 4,
|
| 58 |
+
"40": 40,
|
| 59 |
+
"41": 41,
|
| 60 |
+
"42": 42,
|
| 61 |
+
"43": 43,
|
| 62 |
+
"44": 44,
|
| 63 |
+
"45": 45,
|
| 64 |
+
"46": 46,
|
| 65 |
+
"47": 47,
|
| 66 |
+
"48": 48,
|
| 67 |
+
"49": 49,
|
| 68 |
+
"5": 5,
|
| 69 |
+
"50": 50,
|
| 70 |
+
"6": 6,
|
| 71 |
+
"7": 7,
|
| 72 |
+
"8": 8,
|
| 73 |
+
"9": 9
|
| 74 |
+
},
|
| 75 |
+
"initializer_cutoff_factor": 2.0,
|
| 76 |
+
"initializer_range": 0.02,
|
| 77 |
+
"intermediate_size": 1152,
|
| 78 |
+
"label2id": {
|
| 79 |
+
"0": "0",
|
| 80 |
+
"1": "1",
|
| 81 |
+
"2": "2",
|
| 82 |
+
"3": "3",
|
| 83 |
+
"4": "4",
|
| 84 |
+
"5": "5",
|
| 85 |
+
"6": "6",
|
| 86 |
+
"7": "7",
|
| 87 |
+
"8": "8",
|
| 88 |
+
"9": "9",
|
| 89 |
+
"10": "10",
|
| 90 |
+
"11": "11",
|
| 91 |
+
"12": "12",
|
| 92 |
+
"13": "13",
|
| 93 |
+
"14": "14",
|
| 94 |
+
"15": "15",
|
| 95 |
+
"16": "16",
|
| 96 |
+
"17": "17",
|
| 97 |
+
"18": "18",
|
| 98 |
+
"19": "19",
|
| 99 |
+
"20": "20",
|
| 100 |
+
"21": "21",
|
| 101 |
+
"22": "22",
|
| 102 |
+
"23": "23",
|
| 103 |
+
"24": "24",
|
| 104 |
+
"25": "25",
|
| 105 |
+
"26": "26",
|
| 106 |
+
"27": "27",
|
| 107 |
+
"28": "28",
|
| 108 |
+
"29": "29",
|
| 109 |
+
"30": "30",
|
| 110 |
+
"31": "31",
|
| 111 |
+
"32": "32",
|
| 112 |
+
"33": "33",
|
| 113 |
+
"34": "34",
|
| 114 |
+
"35": "35",
|
| 115 |
+
"36": "36",
|
| 116 |
+
"37": "37",
|
| 117 |
+
"38": "38",
|
| 118 |
+
"39": "39",
|
| 119 |
+
"40": "40",
|
| 120 |
+
"41": "41",
|
| 121 |
+
"42": "42",
|
| 122 |
+
"43": "43",
|
| 123 |
+
"44": "44",
|
| 124 |
+
"45": "45",
|
| 125 |
+
"46": "46",
|
| 126 |
+
"47": "47",
|
| 127 |
+
"48": "48",
|
| 128 |
+
"49": "49",
|
| 129 |
+
"50": "50"
|
| 130 |
+
},
|
| 131 |
+
"layer_norm_eps": 1e-05,
|
| 132 |
+
"local_attention": 128,
|
| 133 |
+
"local_rope_theta": 10000.0,
|
| 134 |
+
"max_position_embeddings": 8192,
|
| 135 |
+
"mlp_bias": false,
|
| 136 |
+
"mlp_dropout": 0.0,
|
| 137 |
+
"model_type": "modernbert",
|
| 138 |
+
"norm_bias": false,
|
| 139 |
+
"norm_eps": 1e-05,
|
| 140 |
+
"num_attention_heads": 12,
|
| 141 |
+
"num_hidden_layers": 22,
|
| 142 |
+
"pad_token_id": 50283,
|
| 143 |
+
"position_embedding_type": "absolute",
|
| 144 |
+
"problem_type": "single_label_classification",
|
| 145 |
+
"repad_logits_with_grad": false,
|
| 146 |
+
"sep_token_id": 50282,
|
| 147 |
+
"sparse_pred_ignore_index": -100,
|
| 148 |
+
"sparse_prediction": false,
|
| 149 |
+
"torch_dtype": "float32",
|
| 150 |
+
"transformers_version": "4.55.2",
|
| 151 |
+
"vocab_size": 50368
|
| 152 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4538ccd1e44dc8a5f14cae83951c59ebc94fae0362fdbf5d83890b1da6998d1b
|
| 3 |
+
size 598590516
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1475f87ec5cbd91a44a9164c4db55b94570509d77e4b5bac628d8b091fb319b9
|
| 3 |
+
size 5368
|