Pclanglais commited on
Commit
0f941d1
1 Parent(s): e572fbb

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 250101
3
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deberta-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "classification"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "label2id": {
16
+ "classification": 0
17
+ },
18
+ "layer_norm_eps": 1e-07,
19
+ "max_position_embeddings": 512,
20
+ "max_relative_positions": -1,
21
+ "model_type": "deberta-v2",
22
+ "norm_rel_ebd": "layer_norm",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "pooler_dropout": 0,
27
+ "pooler_hidden_act": "gelu",
28
+ "pooler_hidden_size": 768,
29
+ "pos_att_type": [
30
+ "p2c",
31
+ "c2p"
32
+ ],
33
+ "position_biased_input": false,
34
+ "position_buckets": 256,
35
+ "problem_type": "multi_label_classification",
36
+ "relative_attention": true,
37
+ "share_att_key": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.0.dev0",
40
+ "type_vocab_size": 0,
41
+ "vocab_size": 251000
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255a6359f066f9346e94f029c91d6c43ff8b71b458fe585ec6f7babc64207d43
3
+ size 1115265124
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e061024c578ca3c541cbfd93684a3b1756774a115fcd7a6c421f02afd95e5f
3
+ size 2230649850
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d9b3a71b33691150034399232a67fc24ea63d0158b95bc660fc1bd39d642fa
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe876355c3ad8ea4874b0caf7fc5563ff8f1a4c8ddc26a911f599c6afa82741
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
3
+ size 4305025
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42839ec04c3025630c31f069df13d750b5a3c969345d768ca8e0da9119600c7
3
+ size 16331661
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8532171581769437,
3
+ "best_model_checkpoint": "deberta-classification-chatrag/checkpoint-4228",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6342,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.24,
13
+ "learning_rate": 9.211605171870073e-06,
14
+ "loss": 0.4251,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 8.423210343740146e-06,
20
+ "loss": 0.3842,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.71,
25
+ "learning_rate": 7.634815515610218e-06,
26
+ "loss": 0.3502,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.95,
31
+ "learning_rate": 6.846420687480291e-06,
32
+ "loss": 0.334,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 0.8458445040214477,
38
+ "eval_f1": 0.8458445040214477,
39
+ "eval_loss": 0.37406206130981445,
40
+ "eval_roc_auc": 0.846812946081549,
41
+ "eval_runtime": 22.7345,
42
+ "eval_samples_per_second": 65.627,
43
+ "eval_steps_per_second": 8.225,
44
+ "step": 2114
45
+ },
46
+ {
47
+ "epoch": 1.18,
48
+ "learning_rate": 6.058025859350363e-06,
49
+ "loss": 0.3267,
50
+ "step": 2500
51
+ },
52
+ {
53
+ "epoch": 1.42,
54
+ "learning_rate": 5.269631031220436e-06,
55
+ "loss": 0.3134,
56
+ "step": 3000
57
+ },
58
+ {
59
+ "epoch": 1.66,
60
+ "learning_rate": 4.4812362030905085e-06,
61
+ "loss": 0.3171,
62
+ "step": 3500
63
+ },
64
+ {
65
+ "epoch": 1.89,
66
+ "learning_rate": 3.6928413749605807e-06,
67
+ "loss": 0.3197,
68
+ "step": 4000
69
+ },
70
+ {
71
+ "epoch": 2.0,
72
+ "eval_accuracy": 0.8532171581769437,
73
+ "eval_f1": 0.8532171581769437,
74
+ "eval_loss": 0.42327263951301575,
75
+ "eval_roc_auc": 0.8199641368101195,
76
+ "eval_runtime": 22.432,
77
+ "eval_samples_per_second": 66.512,
78
+ "eval_steps_per_second": 8.336,
79
+ "step": 4228
80
+ },
81
+ {
82
+ "epoch": 2.13,
83
+ "learning_rate": 2.904446546830653e-06,
84
+ "loss": 0.3166,
85
+ "step": 4500
86
+ },
87
+ {
88
+ "epoch": 2.37,
89
+ "learning_rate": 2.1160517187007253e-06,
90
+ "loss": 0.2854,
91
+ "step": 5000
92
+ },
93
+ {
94
+ "epoch": 2.6,
95
+ "learning_rate": 1.3276568905707978e-06,
96
+ "loss": 0.29,
97
+ "step": 5500
98
+ },
99
+ {
100
+ "epoch": 2.84,
101
+ "learning_rate": 5.392620624408705e-07,
102
+ "loss": 0.2915,
103
+ "step": 6000
104
+ },
105
+ {
106
+ "epoch": 3.0,
107
+ "eval_accuracy": 0.8525469168900804,
108
+ "eval_f1": 0.8525469168900803,
109
+ "eval_loss": 0.4641505181789398,
110
+ "eval_roc_auc": 0.8244735354391916,
111
+ "eval_runtime": 22.4686,
112
+ "eval_samples_per_second": 66.404,
113
+ "eval_steps_per_second": 8.323,
114
+ "step": 6342
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 6342,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 3,
121
+ "save_steps": 500,
122
+ "total_flos": 1.3345375348952064e+16,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b18c4d3e38493cfa685ef07cffd2a926b11b29f521eb55401590d3a3427fd5e
3
+ size 4792