Hugging Face's logo

webis
/
sigdial25-co-constructive-llms

Safetensors
Model card Files
xet
Community
leandrafichtel7 commited on
Commit
29b317c
·
verified ·
1 Parent(s): b6da5e3

Upload 12 files

Browse files

final models to predict turn labels

Files changed (12) hide show
  1. final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/best_model/config.json +68 -0
  2. final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/best_model/model.safetensors +3 -0
  3. final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/eval_results.json +1 -0
  4. final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/test_set.json +0 -0
  5. final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/best_model/config.json +68 -0
  6. final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/best_model/model.safetensors +3 -0
  7. final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/eval_results.json +1 -0
  8. final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/test_set.json +0 -0
  9. final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/best_model/config.json +56 -0
  10. final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/best_model/model.safetensors +3 -0
  11. final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/eval_results.json +1 -0
  12. final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/test_set.json +0 -0
final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/best_model/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/bigwork/nhwpficl/hf_models/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2",
32
+ "3": "LABEL_3",
33
+ "4": "LABEL_4",
34
+ "5": "LABEL_5",
35
+ "6": "LABEL_6",
36
+ "7": "LABEL_7",
37
+ "8": "LABEL_8",
38
+ "9": "LABEL_9"
39
+ },
40
+ "ignore_attention_mask": false,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_2": 2,
47
+ "LABEL_3": 3,
48
+ "LABEL_4": 4,
49
+ "LABEL_5": 5,
50
+ "LABEL_6": 6,
51
+ "LABEL_7": 7,
52
+ "LABEL_8": 8,
53
+ "LABEL_9": 9
54
+ },
55
+ "layer_norm_eps": 1e-05,
56
+ "max_position_embeddings": 4098,
57
+ "model_type": "longformer",
58
+ "num_attention_heads": 12,
59
+ "num_hidden_layers": 12,
60
+ "onnx_export": false,
61
+ "pad_token_id": 1,
62
+ "problem_type": "single_label_classification",
63
+ "sep_token_id": 2,
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.49.0",
66
+ "type_vocab_size": 1,
67
+ "vocab_size": 50265
68
+ }
final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f210ea876370728f4c01dbdabaac9094254292610d10a69b67d14195752a5ab0
3
+ size 594702792
final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/eval_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ [{"eval_loss": 1.2417681217193604, "eval_f1-score": 0.5025428681217703, "eval_runtime": 43.558, "eval_samples_per_second": 11.272, "eval_steps_per_second": 1.423, "epoch": 10.0}]
final-turn-label-models/longformer-base-4096/dlg_act_label_prediction/all_models/model/test_set.json ADDED
The diff for this file is too large to render. See raw diff
 
final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/best_model/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/bigwork/nhwpficl/hf_models/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2",
32
+ "3": "LABEL_3",
33
+ "4": "LABEL_4",
34
+ "5": "LABEL_5",
35
+ "6": "LABEL_6",
36
+ "7": "LABEL_7",
37
+ "8": "LABEL_8",
38
+ "9": "LABEL_9"
39
+ },
40
+ "ignore_attention_mask": false,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_2": 2,
47
+ "LABEL_3": 3,
48
+ "LABEL_4": 4,
49
+ "LABEL_5": 5,
50
+ "LABEL_6": 6,
51
+ "LABEL_7": 7,
52
+ "LABEL_8": 8,
53
+ "LABEL_9": 9
54
+ },
55
+ "layer_norm_eps": 1e-05,
56
+ "max_position_embeddings": 4098,
57
+ "model_type": "longformer",
58
+ "num_attention_heads": 12,
59
+ "num_hidden_layers": 12,
60
+ "onnx_export": false,
61
+ "pad_token_id": 1,
62
+ "problem_type": "single_label_classification",
63
+ "sep_token_id": 2,
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.49.0",
66
+ "type_vocab_size": 1,
67
+ "vocab_size": 50265
68
+ }
final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab2ee8d0af2e2d4cc8817292962d3ce3bb2bf1c975538a74275cd28f49e60262
3
+ size 594702792
final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/eval_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ [{"eval_loss": 1.6728483438491821, "eval_f1-score": 0.3881880797724973, "eval_runtime": 43.5934, "eval_samples_per_second": 11.263, "eval_steps_per_second": 1.422, "epoch": 10.0}]
final-turn-label-models/longformer-base-4096/exp_act_label_prediction/all_models/model/test_set.json ADDED
The diff for this file is too large to render. See raw diff
 
final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/best_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/bigwork/nhwpficl/hf_models/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2",
32
+ "3": "LABEL_3"
33
+ },
34
+ "ignore_attention_mask": false,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2,
41
+ "LABEL_3": 3
42
+ },
43
+ "layer_norm_eps": 1e-05,
44
+ "max_position_embeddings": 4098,
45
+ "model_type": "longformer",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "onnx_export": false,
49
+ "pad_token_id": 1,
50
+ "problem_type": "single_label_classification",
51
+ "sep_token_id": 2,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.49.0",
54
+ "type_vocab_size": 1,
55
+ "vocab_size": 50265
56
+ }
final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141fe18902a8cd2041c66af44103661e4fb2feef6f79a7301e73b8811655600d
3
+ size 594684336
final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/eval_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ [{"eval_loss": 0.8750081062316895, "eval_f1-score": 0.5230565664023916, "eval_runtime": 44.4493, "eval_samples_per_second": 11.046, "eval_steps_per_second": 1.395, "epoch": 10.0}]
final-turn-label-models/longformer-base-4096/topic_func_label_prediction/all_models/model/test_set.json ADDED
The diff for this file is too large to render. See raw diff