Hugging Face's logo

harikarthikmanyam
/
laya-issue-triage

Text Classification
Laya
Safetensors
typed-decisions
github
issue-triage
non-autoregressive
modernbert
Eval Results (legacy)
Model card Files
xet
 Community
harikarthikmanyam commited on
Commit
7d8cb2a
·
verified ·
1 Parent(s): 5534f56

raw checkpoint, pre-evaluation

Browse files
Files changed (10) hide show
  1. checkpoint_latest/checkpoint_meta.json +5 -0
  2. checkpoint_latest/encoder/config.json +84 -0
  3. checkpoint_latest/model.safetensors +3 -0
  4. checkpoint_latest/tokenizer/tokenizer.json +0 -0
  5. checkpoint_latest/tokenizer/tokenizer_config.json +17 -0
  6. encoder/config.json +84 -0
  7. model.safetensors +3 -0
  8. rl_agent_config.json +36 -0
  9. tokenizer/tokenizer.json +0 -0
  10. tokenizer/tokenizer_config.json +17 -0
checkpoint_latest/checkpoint_meta.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2,
3
+ "total_epochs": 2,
4
+ "avg_loss": 0.3642221501962784
5
+ }
checkpoint_latest/encoder/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForMaskedLM"
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": 1024,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 2624,
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
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention"
55
+ ],
56
+ "local_attention": 128,
57
+ "max_position_embeddings": 8192,
58
+ "mlp_bias": false,
59
+ "mlp_dropout": 0.0,
60
+ "model_type": "modernbert",
61
+ "norm_bias": false,
62
+ "norm_eps": 1e-05,
63
+ "num_attention_heads": 16,
64
+ "num_hidden_layers": 28,
65
+ "pad_token_id": 50283,
66
+ "position_embedding_type": "absolute",
67
+ "repad_logits_with_grad": false,
68
+ "rope_parameters": {
69
+ "full_attention": {
70
+ "rope_theta": 160000.0,
71
+ "rope_type": "default"
72
+ },
73
+ "sliding_attention": {
74
+ "rope_theta": 10000.0,
75
+ "rope_type": "default"
76
+ }
77
+ },
78
+ "sep_token_id": 50282,
79
+ "sparse_pred_ignore_index": -100,
80
+ "sparse_prediction": false,
81
+ "tie_word_embeddings": true,
82
+ "transformers_version": "5.17.0",
83
+ "vocab_size": 50368
84
+ }
checkpoint_latest/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a964f24a95fdbbe9afbbc87b938a6c79fb7a1ba3833d36294fcaf6e65c2cf9
3
+ size 842609220
checkpoint_latest/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint_latest/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": true,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }
encoder/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForMaskedLM"
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": 1024,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 2624,
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
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention"
55
+ ],
56
+ "local_attention": 128,
57
+ "max_position_embeddings": 8192,
58
+ "mlp_bias": false,
59
+ "mlp_dropout": 0.0,
60
+ "model_type": "modernbert",
61
+ "norm_bias": false,
62
+ "norm_eps": 1e-05,
63
+ "num_attention_heads": 16,
64
+ "num_hidden_layers": 28,
65
+ "pad_token_id": 50283,
66
+ "position_embedding_type": "absolute",
67
+ "repad_logits_with_grad": false,
68
+ "rope_parameters": {
69
+ "full_attention": {
70
+ "rope_theta": 160000.0,
71
+ "rope_type": "default"
72
+ },
73
+ "sliding_attention": {
74
+ "rope_theta": 10000.0,
75
+ "rope_type": "default"
76
+ }
77
+ },
78
+ "sep_token_id": 50282,
79
+ "sparse_pred_ignore_index": -100,
80
+ "sparse_prediction": false,
81
+ "tie_word_embeddings": true,
82
+ "transformers_version": "5.17.0",
83
+ "vocab_size": 50368
84
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a964f24a95fdbbe9afbbc87b938a6c79fb7a1ba3833d36294fcaf6e65c2cf9
3
+ size 842609220
rl_agent_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "encoder": "answerdotai/ModernBERT-large",
3
+ "head_layers": 2,
4
+ "max_len": 1024,
5
+ "head_max_len": 256,
6
+ "max_prefixes": 6,
7
+ "act_costs": {
8
+ "escalate": 0.5
9
+ },
10
+ "cost_wrong_act": 3.0,
11
+ "amp_dtype": "bf16",
12
+ "model_name": "laya-typed-decisions",
13
+ "temperature": [
14
+ 1.2721903324127197,
15
+ 1.2,
16
+ 1.4713261127471924
17
+ ],
18
+ "temperature_by_options": {
19
+ "choice:3-5": 1.7601518630981445,
20
+ "choice:6-10": 1.0000158548355103,
21
+ "score:3-5": 1.2514300346374512,
22
+ "noul:2": 1.983399510383606,
23
+ "choice:11+": 0.10058280825614929,
24
+ "choice:2": 1.9063563346862793
25
+ },
26
+ "training": {
27
+ "updates": 7313,
28
+ "epochs_completed": 1,
29
+ "hours": 1.96,
30
+ "world_size": 1,
31
+ "fine_tuned_from_checkpoint": true
32
+ },
33
+ "gradient_checkpointing": true,
34
+ "max_tokens_per_batch": 4096,
35
+ "fine_tuned": true
36
+ }
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": true,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }