Rcarvalo commited on
Commit
6aeaafc
·
verified ·
1 Parent(s): f79a6d2

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "0_not_relevant",
25
+ "1": "1_not_happening",
26
+ "2": "2_not_human",
27
+ "3": "3_not_bad",
28
+ "4": "4_solutions_harmful_unnecessary",
29
+ "5": "5_science_unreliable",
30
+ "6": "6_proponents_biased",
31
+ "7": "7_fossil_fuels_needed"
32
+ },
33
+ "initializer_cutoff_factor": 2.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 1152,
36
+ "label2id": {
37
+ "0_not_relevant": 0,
38
+ "1_not_happening": 1,
39
+ "2_not_human": 2,
40
+ "3_not_bad": 3,
41
+ "4_solutions_harmful_unnecessary": 4,
42
+ "5_science_unreliable": 5,
43
+ "6_proponents_biased": 6,
44
+ "7_fossil_fuels_needed": 7
45
+ },
46
+ "layer_norm_eps": 1e-05,
47
+ "local_attention": 128,
48
+ "local_rope_theta": 10000.0,
49
+ "max_position_embeddings": 8192,
50
+ "mlp_bias": false,
51
+ "mlp_dropout": 0.0,
52
+ "model_type": "modernbert",
53
+ "norm_bias": false,
54
+ "norm_eps": 1e-05,
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 22,
57
+ "pad_token_id": 50283,
58
+ "position_embedding_type": "absolute",
59
+ "problem_type": "single_label_classification",
60
+ "reference_compile": true,
61
+ "repad_logits_with_grad": false,
62
+ "sep_token_id": 50282,
63
+ "sparse_pred_ignore_index": -100,
64
+ "sparse_prediction": false,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.49.0.dev0",
67
+ "vocab_size": 50368
68
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ccec083f8606ae04eb24dda4df376cfd40690d70f0c97e2e1677c9b2df14a65
3
+ size 598458240
runs/Jan25_18-50-07_02d767aa37f1/events.out.tfevents.1737831008.02d767aa37f1.3654.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7cd16d566991e5bc0c81f29d795518c14af7e185f0810eb7e27e9860ba2c3a
3
+ size 11281
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e9531ed305e3b9670d80ac8f03f5a386441e024e9ad6768ea24a2024db0ee3
3
+ size 5432