palashsharma15 commited on
Commit
a6971c2
·
verified ·
1 Parent(s): 30344c2

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "answerdotai/ModernBERT-base",
3
+ "architectures": [
4
+ "ModernBertForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "refund-request",
25
+ "1": "communication-issue",
26
+ "2": "warranty-claim",
27
+ "3": "shipping-issue",
28
+ "4": "return-priority",
29
+ "5": "product-damage"
30
+ },
31
+ "initializer_cutoff_factor": 2.0,
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 1152,
34
+ "label2id": {
35
+ "communication-issue": "1",
36
+ "product-damage": "5",
37
+ "refund-request": "0",
38
+ "return-priority": "4",
39
+ "shipping-issue": "3",
40
+ "warranty-claim": "2"
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "local_attention": 128,
44
+ "local_rope_theta": 10000.0,
45
+ "max_position_embeddings": 8192,
46
+ "mlp_bias": false,
47
+ "mlp_dropout": 0.0,
48
+ "model_type": "modernbert",
49
+ "norm_bias": false,
50
+ "norm_eps": 1e-05,
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 22,
53
+ "pad_token_id": 50283,
54
+ "position_embedding_type": "absolute",
55
+ "problem_type": "single_label_classification",
56
+ "reference_compile": true,
57
+ "sep_token_id": 50282,
58
+ "sparse_pred_ignore_index": -100,
59
+ "sparse_prediction": false,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.48.0.dev0",
62
+ "vocab_size": 50368
63
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6944814d339d8debadda732241ddf6d09c1799de049fa7a443eedb3ae5e5a4
3
+ size 598452088
runs/Dec31_09-01-59_b3c174aa3033/events.out.tfevents.1735635735.b3c174aa3033.3309.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ad1f2778f3e82ad38dcd0063bf59cb9efaac280dcfb8deed8fd5b224547e90
3
+ size 6402
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6251fad154f01bbee7932bce7239268ba57f8104b12a24acebdcfeaa0a141b4d
3
+ size 5432