Hugging Face's logo

hallisky
/
amt-classifier-roberta-large

Text Classification
Transformers
TensorBoard
Safetensors
roberta
text-embeddings-inference
Model card Files
xet
 Metrics Community
hallisky commited on
Commit
1c43553
·
verified ·
1 Parent(s): 151d5ec

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +38 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +15 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. trainer_state.json +121 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "h",
15
+ "1": "pp",
16
+ "2": "qq"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "h": 0,
22
+ "pp": 1,
23
+ "qq": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.38.0",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e873c3f5dae1008bc6efdc8f413b1571eb3d89f4018b22a402479ce4b01743e6
3
+ size 1421499516
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb96657e5afb4f31cd65a7563b19cdad9a106c9fa4701a12c1c67cddc6b2dc2c
3
+ size 2843231469
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1508b175b79c75a88d5f7f2a56e937c14c8f9189ac39d68d69b4fe7241feae8
3
+ size 14180
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3e199bbda9aad4143a96ea0ac9ce1bd6d44218caf1398e9109759bd9461ed0
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "train_authorship/train_outputs/05-21-2024_13:13:45/checkpoint-6",
4
+ "epoch": 2.5,
5
+ "eval_steps": 2,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "grad_norm": 6.089840412139893,
14
+ "learning_rate": 2.5e-05,
15
+ "loss": 1.1456,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "eval_acc_product": 0.0,
21
+ "eval_h_acc": 0.7692307692307693,
22
+ "eval_loss": 1.0893480777740479,
23
+ "eval_overall_acc": 0.5897435897435898,
24
+ "eval_pp_acc": 1.0,
25
+ "eval_qq_acc": 0.0,
26
+ "eval_runtime": 0.2361,
27
+ "eval_samples_per_second": 165.177,
28
+ "eval_steps_per_second": 4.235,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 1.0,
33
+ "grad_norm": 6.872375965118408,
34
+ "learning_rate": 5e-05,
35
+ "loss": 1.12,
36
+ "step": 4
37
+ },
38
+ {
39
+ "epoch": 1.0,
40
+ "eval_acc_product": 0.1301775147928994,
41
+ "eval_h_acc": 0.8461538461538461,
42
+ "eval_loss": 1.0048478841781616,
43
+ "eval_overall_acc": 0.6666666666666666,
44
+ "eval_pp_acc": 0.15384615384615385,
45
+ "eval_qq_acc": 1.0,
46
+ "eval_runtime": 0.2352,
47
+ "eval_samples_per_second": 165.814,
48
+ "eval_steps_per_second": 4.252,
49
+ "step": 4
50
+ },
51
+ {
52
+ "epoch": 1.5,
53
+ "grad_norm": 6.280738830566406,
54
+ "learning_rate": 4.722222222222222e-05,
55
+ "loss": 0.9317,
56
+ "step": 6
57
+ },
58
+ {
59
+ "epoch": 1.5,
60
+ "eval_acc_product": 1.0,
61
+ "eval_h_acc": 1.0,
62
+ "eval_loss": 0.4365764558315277,
63
+ "eval_overall_acc": 1.0,
64
+ "eval_pp_acc": 1.0,
65
+ "eval_qq_acc": 1.0,
66
+ "eval_runtime": 0.2356,
67
+ "eval_samples_per_second": 165.51,
68
+ "eval_steps_per_second": 4.244,
69
+ "step": 6
70
+ },
71
+ {
72
+ "epoch": 2.0,
73
+ "grad_norm": 8.260248184204102,
74
+ "learning_rate": 4.4444444444444447e-05,
75
+ "loss": 0.3742,
76
+ "step": 8
77
+ },
78
+ {
79
+ "epoch": 2.0,
80
+ "eval_acc_product": 1.0,
81
+ "eval_h_acc": 1.0,
82
+ "eval_loss": 0.09832292050123215,
83
+ "eval_overall_acc": 1.0,
84
+ "eval_pp_acc": 1.0,
85
+ "eval_qq_acc": 1.0,
86
+ "eval_runtime": 0.2365,
87
+ "eval_samples_per_second": 164.897,
88
+ "eval_steps_per_second": 4.228,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 2.5,
93
+ "grad_norm": 3.575946807861328,
94
+ "learning_rate": 4.166666666666667e-05,
95
+ "loss": 0.1006,
96
+ "step": 10
97
+ },
98
+ {
99
+ "epoch": 2.5,
100
+ "eval_acc_product": 1.0,
101
+ "eval_h_acc": 1.0,
102
+ "eval_loss": 0.011917746625840664,
103
+ "eval_overall_acc": 1.0,
104
+ "eval_pp_acc": 1.0,
105
+ "eval_qq_acc": 1.0,
106
+ "eval_runtime": 0.2364,
107
+ "eval_samples_per_second": 164.977,
108
+ "eval_steps_per_second": 4.23,
109
+ "step": 10
110
+ }
111
+ ],
112
+ "logging_steps": 2,
113
+ "max_steps": 40,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 10,
116
+ "save_steps": 2,
117
+ "total_flos": 190740783974448.0,
118
+ "train_batch_size": 64,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:341a94260346a9cd04bb1b76b2f75d7df3df564fee684d0d747abb6aa98713bd
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff