benjamintli commited on
Commit
3498658
·
verified ·
1 Parent(s): d836a11

Training in progress, step 10

Browse files
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
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
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 1e-05,
26
+ "layer_types": [
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention"
49
+ ],
50
+ "local_attention": 128,
51
+ "max_position_embeddings": 8192,
52
+ "mlp_bias": false,
53
+ "mlp_dropout": 0.0,
54
+ "model_type": "modernbert",
55
+ "norm_bias": false,
56
+ "norm_eps": 1e-05,
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 22,
59
+ "pad_token_id": 50283,
60
+ "position_embedding_type": "absolute",
61
+ "rope_parameters": {
62
+ "full_attention": {
63
+ "rope_theta": 160000.0,
64
+ "rope_type": "default"
65
+ },
66
+ "sliding_attention": {
67
+ "rope_theta": 10000.0,
68
+ "rope_type": "default"
69
+ }
70
+ },
71
+ "sep_token_id": 50282,
72
+ "sparse_pred_ignore_index": -100,
73
+ "sparse_prediction": false,
74
+ "tie_word_embeddings": true,
75
+ "transformers_version": "5.3.0",
76
+ "vocab_size": 50368
77
+ }
eval/Information-Retrieval_evaluation_eval_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
2
+ 0.05263157894736842,10,0.31677047503950917,0.4237705680022311,0.46960118992284094,0.5346286139258157,0.31677047503950917,0.31677047503950917,0.1412568560007437,0.4237705680022311,0.09392023798456818,0.46960118992284094,0.053462861392581565,0.5346286139258157,0.3834089024348821,0.4194538069068056,0.391388274648253
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547d262c1b86b65456a75011721e233dfa9b0045dd78bbafbb781483b7365d6f
3
+ size 596070136
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_input_names": [
8
+ "input_ids",
9
+ "attention_mask"
10
+ ],
11
+ "model_max_length": 8192,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff63002b0696e0bca298d7362e777fb1495a075596d5a061a731da2a4ff77be
3
+ size 5585