ATL1978 commited on
Commit
dd33c48
·
verified ·
1 Parent(s): 48d3dc6

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +95 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "sadness",
24
+ "1": "joy",
25
+ "2": "love",
26
+ "3": "anger",
27
+ "4": "fear",
28
+ "5": "surprise"
29
+ },
30
+ "initializer_cutoff_factor": 2.0,
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 1152,
33
+ "label2id": {
34
+ "anger": 3,
35
+ "fear": 4,
36
+ "joy": 1,
37
+ "love": 2,
38
+ "sadness": 0,
39
+ "surprise": 5
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "layer_types": [
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "full_attention"
65
+ ],
66
+ "local_attention": 128,
67
+ "max_position_embeddings": 8192,
68
+ "mlp_bias": false,
69
+ "mlp_dropout": 0.0,
70
+ "model_type": "modernbert",
71
+ "norm_bias": false,
72
+ "norm_eps": 1e-05,
73
+ "num_attention_heads": 12,
74
+ "num_hidden_layers": 22,
75
+ "pad_token_id": 50283,
76
+ "position_embedding_type": "absolute",
77
+ "problem_type": "single_label_classification",
78
+ "rope_parameters": {
79
+ "full_attention": {
80
+ "rope_theta": 160000.0,
81
+ "rope_type": "default"
82
+ },
83
+ "sliding_attention": {
84
+ "rope_theta": 10000.0,
85
+ "rope_type": "default"
86
+ }
87
+ },
88
+ "sep_token_id": 50282,
89
+ "sparse_pred_ignore_index": -100,
90
+ "sparse_prediction": false,
91
+ "tie_word_embeddings": true,
92
+ "transformers_version": "5.3.0",
93
+ "use_cache": false,
94
+ "vocab_size": 50368
95
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a185e4f2c5e15d46c0a8804bf5273c0bd8d9fa3ad621adcb33342bccc882dca
3
+ size 598452088
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bcf1c3ad13c72373a7805f6145b79c37515338f7d397beeef9b5a70bc09f458
3
+ size 5265