Training in progress, epoch 1
Browse files- config.json +58 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "IDEA-CCNL/Erlangshen-Longformer-110M",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"attention_window": [
|
| 8 |
+
128,
|
| 9 |
+
128,
|
| 10 |
+
128,
|
| 11 |
+
128,
|
| 12 |
+
128,
|
| 13 |
+
128,
|
| 14 |
+
128,
|
| 15 |
+
128,
|
| 16 |
+
128,
|
| 17 |
+
128,
|
| 18 |
+
128,
|
| 19 |
+
128
|
| 20 |
+
],
|
| 21 |
+
"bos_token_id": 0,
|
| 22 |
+
"directionality": "bidi",
|
| 23 |
+
"eos_token_id": 2,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"hidden_act": "gelu",
|
| 26 |
+
"hidden_dropout_prob": 0.1,
|
| 27 |
+
"hidden_size": 768,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "Down",
|
| 30 |
+
"1": "Up"
|
| 31 |
+
},
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"intermediate_size": 3072,
|
| 34 |
+
"label2id": {
|
| 35 |
+
"Down": 0,
|
| 36 |
+
"Up": 1
|
| 37 |
+
},
|
| 38 |
+
"layer_norm_eps": 1e-12,
|
| 39 |
+
"max_position_embeddings": 4096,
|
| 40 |
+
"model_type": "longformer",
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"onnx_export": false,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pooler_fc_size": 768,
|
| 46 |
+
"pooler_num_attention_heads": 12,
|
| 47 |
+
"pooler_num_fc_layers": 3,
|
| 48 |
+
"pooler_size_per_head": 128,
|
| 49 |
+
"pooler_type": "first_token_transform",
|
| 50 |
+
"problem_type": "single_label_classification",
|
| 51 |
+
"sep_token_id": 2,
|
| 52 |
+
"tokenizer_class": "BertTokenizer",
|
| 53 |
+
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.34.1",
|
| 55 |
+
"type_vocab_size": 2,
|
| 56 |
+
"use_sparse_attention": true,
|
| 57 |
+
"vocab_size": 12000
|
| 58 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dc33db09a120d9d643f610a59a4ac72d3182a5bc2bd8b7b791b057cb7f44c9e
|
| 3 |
+
size 477186129
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2dbfddf2cdf4c701cc40499f12048ba84ef87483146fb6f2b7892fef16cc0dc
|
| 3 |
+
size 4219
|