UniversalAlgorithmic commited on
Commit
07f52e2
·
verified ·
1 Parent(s): 13d8f04

Delete cola

Browse files
cola/README.md DELETED
@@ -1,73 +0,0 @@
1
- ---
2
- library_name: transformers
3
- language:
4
- - en
5
- license: apache-2.0
6
- base_model: google-bert/bert-base-cased
7
- tags:
8
- - generated_from_trainer
9
- datasets:
10
- - glue
11
- metrics:
12
- - matthews_correlation
13
- model-index:
14
- - name: cola
15
- results:
16
- - task:
17
- name: Text Classification
18
- type: text-classification
19
- dataset:
20
- name: GLUE COLA
21
- type: glue
22
- args: cola
23
- metrics:
24
- - name: Matthews Correlation
25
- type: matthews_correlation
26
- value: 0.6212584232587556
27
- ---
28
-
29
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
- should probably proofread and complete it, then remove this comment. -->
31
-
32
- # cola
33
-
34
- This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the GLUE COLA dataset.
35
- It achieves the following results on the evaluation set:
36
- - Loss: 0.8440
37
- - Matthews Correlation: 0.6213
38
-
39
- ## Model description
40
-
41
- More information needed
42
-
43
- ## Intended uses & limitations
44
-
45
- More information needed
46
-
47
- ## Training and evaluation data
48
-
49
- More information needed
50
-
51
- ## Training procedure
52
-
53
- ### Training hyperparameters
54
-
55
- The following hyperparameters were used during training:
56
- - learning_rate: 2.5e-05
57
- - train_batch_size: 32
58
- - eval_batch_size: 8
59
- - seed: 42
60
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
- - lr_scheduler_type: linear
62
- - num_epochs: 6.0
63
-
64
- ### Training results
65
-
66
-
67
-
68
- ### Framework versions
69
-
70
- - Transformers 4.49.0
71
- - Pytorch 2.6.0+cu118
72
- - Datasets 3.3.1
73
- - Tokenizers 0.21.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cola/all_results.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "epoch": 6.0,
3
- "eval_loss": 0.8439584374427795,
4
- "eval_matthews_correlation": 0.6212584232587556,
5
- "eval_runtime": 2.0452,
6
- "eval_samples": 1043,
7
- "eval_samples_per_second": 509.983,
8
- "eval_steps_per_second": 64.053,
9
- "total_flos": 3444607255477248.0,
10
- "train_loss": 0.2595453208951808,
11
- "train_runtime": 282.1547,
12
- "train_samples": 8551,
13
- "train_samples_per_second": 181.836,
14
- "train_steps_per_second": 5.699
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cola/config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "_name_or_path": "google-bert/bert-base-cased",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "finetuning_task": "cola",
9
- "gradient_checkpointing": false,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "label2id": {
16
- "acceptable": 1,
17
- "unacceptable": 0
18
- },
19
- "layer_norm_eps": 1e-12,
20
- "max_position_embeddings": 512,
21
- "model_type": "bert",
22
- "num_attention_heads": 12,
23
- "num_hidden_layers": 12,
24
- "pad_token_id": 0,
25
- "position_embedding_type": "absolute",
26
- "problem_type": "single_label_classification",
27
- "torch_dtype": "float32",
28
- "transformers_version": "4.49.0",
29
- "type_vocab_size": 2,
30
- "use_cache": true,
31
- "vocab_size": 28996
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cola/eval_results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "epoch": 6.0,
3
- "eval_loss": 0.8439584374427795,
4
- "eval_matthews_correlation": 0.6212584232587556,
5
- "eval_runtime": 2.0452,
6
- "eval_samples": 1043,
7
- "eval_samples_per_second": 509.983,
8
- "eval_steps_per_second": 64.053
9
- }
 
 
 
 
 
 
 
 
 
 
cola/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3914a1bf70fbecb9956a8d59981be21e5576bb355f0ab579504e817dd59f90c7
3
- size 440358464
 
 
 
 
cola/runs/May14_16-35-17_cs-Precision-7960-Tower/events.out.tfevents.1747254922.cs-Precision-7960-Tower.130992.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ab978f6f85953900c6734ffd3c4f91245121876a9ff5592ca2598c61a810052
3
- size 6124
 
 
 
 
cola/runs/May14_16-35-17_cs-Precision-7960-Tower/events.out.tfevents.1747255207.cs-Precision-7960-Tower.130992.1 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3521e2517a690ea4f4d14b15f8f324d643ee900860a8e57bc6a8994faddfcb17
3
- size 423
 
 
 
 
cola/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
cola/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
cola/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "clean_up_tokenization_spaces": false,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
- "extra_special_tokens": {},
48
- "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
- "pad_token": "[PAD]",
51
- "sep_token": "[SEP]",
52
- "strip_accents": null,
53
- "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
- "unk_token": "[UNK]"
56
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cola/train_results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "epoch": 6.0,
3
- "total_flos": 3444607255477248.0,
4
- "train_loss": 0.2595453208951808,
5
- "train_runtime": 282.1547,
6
- "train_samples": 8551,
7
- "train_samples_per_second": 181.836,
8
- "train_steps_per_second": 5.699
9
- }
 
 
 
 
 
 
 
 
 
 
cola/trainer_state.json DELETED
@@ -1,63 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 6.0,
5
- "eval_steps": 500,
6
- "global_step": 1608,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 1.8656716417910446,
13
- "grad_norm": 11.32163143157959,
14
- "learning_rate": 1.722636815920398e-05,
15
- "loss": 0.5103,
16
- "step": 500
17
- },
18
- {
19
- "epoch": 3.7313432835820897,
20
- "grad_norm": 6.54978609085083,
21
- "learning_rate": 9.45273631840796e-06,
22
- "loss": 0.2075,
23
- "step": 1000
24
- },
25
- {
26
- "epoch": 5.597014925373134,
27
- "grad_norm": 0.33858296275138855,
28
- "learning_rate": 1.6791044776119404e-06,
29
- "loss": 0.1026,
30
- "step": 1500
31
- },
32
- {
33
- "epoch": 6.0,
34
- "step": 1608,
35
- "total_flos": 3444607255477248.0,
36
- "train_loss": 0.2595453208951808,
37
- "train_runtime": 282.1547,
38
- "train_samples_per_second": 181.836,
39
- "train_steps_per_second": 5.699
40
- }
41
- ],
42
- "logging_steps": 500,
43
- "max_steps": 1608,
44
- "num_input_tokens_seen": 0,
45
- "num_train_epochs": 6,
46
- "save_steps": 500,
47
- "stateful_callbacks": {
48
- "TrainerControl": {
49
- "args": {
50
- "should_epoch_stop": false,
51
- "should_evaluate": false,
52
- "should_log": false,
53
- "should_save": true,
54
- "should_training_stop": true
55
- },
56
- "attributes": {}
57
- }
58
- },
59
- "total_flos": 3444607255477248.0,
60
- "train_batch_size": 32,
61
- "trial_name": null,
62
- "trial_params": null
63
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cola/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:962a988eb1be8ecfc90ceb9c0fd20c2b520b2bd205c902f91a899823e3d647e1
3
- size 5304
 
 
 
 
cola/vocab.txt DELETED
The diff for this file is too large to render. See raw diff