Hugging Face's logo

elenaovv
/
IceBERT-ic3-igc-text-class

Text Classification
Transformers
Safetensors
roberta
Model card Files Community
elenaovv commited on
Commit
ee31313
·
verified ·
1 Parent(s): 0187e2b

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +41 -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 +51 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. trainer_state.json +93 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mideind/IceBERT-ic3",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.39.2",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 50000
41
+ }
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 sha256:4aca66693b00afe96f499b832f31cbefdcb5b27877c2cb9cd82f066d55aa1643
3
+ size 497804896
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1d1097915c492de83fed9f8cc9abba8b6d274d634a21ee86cffa282b7a60a0
3
+ size 995679738
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac695c1393aa1ebefc46556747a794b655d9c37fc3be0bb46cdb3f468d66eb21
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ec472f09a44e132657b3d1383f0bab7aaa054634cdf3ea26a7027f2849f211
3
+ size 1000
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
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
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
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": 1000000000000000019884624838656,
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 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06124882400035858,
3
+ "best_model_checkpoint": "/users/home/elenao23/Models_2/results/elenaovv/model_igc_full/checkpoint-34101",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 45468,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 0.14601550996303558,
14
+ "learning_rate": 9.843747422595384e-07,
15
+ "loss": 0.2032,
16
+ "step": 11367
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_acc": 0.9787542887305357,
21
+ "eval_f1": 0.9787347588271672,
22
+ "eval_loss": 0.08981657028198242,
23
+ "eval_mcc": 0.971707102962192,
24
+ "eval_runtime": 4552.0707,
25
+ "eval_samples_per_second": 4.994,
26
+ "eval_steps_per_second": 0.312,
27
+ "step": 11367
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "grad_norm": 0.00603042496368289,
32
+ "learning_rate": 9.68749484519077e-07,
33
+ "loss": 0.0839,
34
+ "step": 22734
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_acc": 0.9825371689979766,
39
+ "eval_f1": 0.9825188346886068,
40
+ "eval_loss": 0.08358927816152573,
41
+ "eval_mcc": 0.9767754694591899,
42
+ "eval_runtime": 4581.7412,
43
+ "eval_samples_per_second": 4.962,
44
+ "eval_steps_per_second": 0.31,
45
+ "step": 22734
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "grad_norm": 34.3592414855957,
50
+ "learning_rate": 9.531242267786154e-07,
51
+ "loss": 0.0602,
52
+ "step": 34101
53
+ },
54
+ {
55
+ "epoch": 3.0,
56
+ "eval_acc": 0.9879475675200141,
57
+ "eval_f1": 0.9879534397785568,
58
+ "eval_loss": 0.06124882400035858,
59
+ "eval_mcc": 0.9839390539982584,
60
+ "eval_runtime": 4587.1168,
61
+ "eval_samples_per_second": 4.956,
62
+ "eval_steps_per_second": 0.31,
63
+ "step": 34101
64
+ },
65
+ {
66
+ "epoch": 4.0,
67
+ "grad_norm": 0.2689647376537323,
68
+ "learning_rate": 9.374989690381538e-07,
69
+ "loss": 0.0471,
70
+ "step": 45468
71
+ },
72
+ {
73
+ "epoch": 4.0,
74
+ "eval_acc": 0.9893551508753409,
75
+ "eval_f1": 0.9893534822467795,
76
+ "eval_loss": 0.06302130222320557,
77
+ "eval_mcc": 0.9858294150542775,
78
+ "eval_runtime": 4574.485,
79
+ "eval_samples_per_second": 4.97,
80
+ "eval_steps_per_second": 0.311,
81
+ "step": 45468
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 45468,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 4,
88
+ "save_steps": 500,
89
+ "total_flos": 9.570520762055885e+16,
90
+ "train_batch_size": 16,
91
+ "trial_name": null,
92
+ "trial_params": null
93
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684cee2e0d7ded49196690db13c742aa54d0fa1d6269278c771ada0fd8e37948
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff