Training in progress, step 1000
Browse files- config.json +88 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 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 |
+
},
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 4096,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_10": 10,
|
| 44 |
+
"LABEL_11": 11,
|
| 45 |
+
"LABEL_12": 12,
|
| 46 |
+
"LABEL_13": 13,
|
| 47 |
+
"LABEL_14": 14,
|
| 48 |
+
"LABEL_15": 15,
|
| 49 |
+
"LABEL_16": 16,
|
| 50 |
+
"LABEL_17": 17,
|
| 51 |
+
"LABEL_18": 18,
|
| 52 |
+
"LABEL_19": 19,
|
| 53 |
+
"LABEL_2": 2,
|
| 54 |
+
"LABEL_20": 20,
|
| 55 |
+
"LABEL_21": 21,
|
| 56 |
+
"LABEL_22": 22,
|
| 57 |
+
"LABEL_23": 23,
|
| 58 |
+
"LABEL_24": 24,
|
| 59 |
+
"LABEL_25": 25,
|
| 60 |
+
"LABEL_3": 3,
|
| 61 |
+
"LABEL_4": 4,
|
| 62 |
+
"LABEL_5": 5,
|
| 63 |
+
"LABEL_6": 6,
|
| 64 |
+
"LABEL_7": 7,
|
| 65 |
+
"LABEL_8": 8,
|
| 66 |
+
"LABEL_9": 9
|
| 67 |
+
},
|
| 68 |
+
"layer_norm_eps": 1e-07,
|
| 69 |
+
"max_position_embeddings": 512,
|
| 70 |
+
"max_relative_positions": -1,
|
| 71 |
+
"model_type": "deberta",
|
| 72 |
+
"num_attention_heads": 16,
|
| 73 |
+
"num_hidden_layers": 24,
|
| 74 |
+
"pad_token_id": 0,
|
| 75 |
+
"pooler_dropout": 0,
|
| 76 |
+
"pooler_hidden_act": "gelu",
|
| 77 |
+
"pooler_hidden_size": 1024,
|
| 78 |
+
"pos_att_type": [
|
| 79 |
+
"c2p",
|
| 80 |
+
"p2c"
|
| 81 |
+
],
|
| 82 |
+
"position_biased_input": false,
|
| 83 |
+
"relative_attention": true,
|
| 84 |
+
"torch_dtype": "float32",
|
| 85 |
+
"transformers_version": "4.44.2",
|
| 86 |
+
"type_vocab_size": 0,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e11e471454eafbf6015a726af3644e9a3a15933a4aac6e9d471e85777ec877d1
|
| 3 |
+
size 1625005456
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88479e92ab661f49e561ad6fddcf88a48bbb1ee654c9c5c56c762958a16fd5f8
|
| 3 |
+
size 5240
|