ltuzova commited on
Commit
266f6a3
·
1 Parent(s): 5ba01c7

citation_intent_classification_roberta_dapt

Browse files
last-checkpoint/config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "_name_or_path": "ltuzova/cs_domain_pretrained_model",
3
- "architectures": [
4
- "RobertaForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": 0.1,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
- "id2label": {
14
- "0": "Background",
15
- "1": "CompareOrContrast",
16
- "2": "Uses",
17
- "3": "Motivation",
18
- "4": "Future",
19
- "5": "Extends"
20
- },
21
- "initializer_range": 0.02,
22
- "intermediate_size": 3072,
23
- "label2id": {
24
- "Background": 0,
25
- "CompareOrContrast": 1,
26
- "Extends": 5,
27
- "Future": 4,
28
- "Motivation": 3,
29
- "Uses": 2
30
- },
31
- "layer_norm_eps": 1e-05,
32
- "max_position_embeddings": 514,
33
- "model_type": "roberta",
34
- "num_attention_heads": 12,
35
- "num_hidden_layers": 12,
36
- "num_of_labels": 6,
37
- "pad_token_id": 1,
38
- "position_embedding_type": "absolute",
39
- "problem_type": "single_label_classification",
40
- "torch_dtype": "float32",
41
- "transformers_version": "4.30.2",
42
- "type_vocab_size": 1,
43
- "use_cache": true,
44
- "vocab_size": 50265
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfba36c4e8f80031e56a0777d75bb8c8cea5215d00c0e7e95ef5117901f4fdcd
3
- size 997319621
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:66fa2d4d1438d9e3c80629c01a36932041dd5fe913de0ae7c56339dca851b0eb
3
- size 498674357
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01e7f2bd676c936e7a6fdf9cde6071c5938c578820d54a54ab03298d96dc82c2
3
- size 14575
 
 
 
 
last-checkpoint/special_tokens_map.json DELETED
@@ -1,15 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "bos_token": "<s>",
4
- "clean_up_tokenization_spaces": true,
5
- "cls_token": "<s>",
6
- "eos_token": "</s>",
7
- "errors": "replace",
8
- "mask_token": "<mask>",
9
- "model_max_length": 512,
10
- "pad_token": "<pad>",
11
- "sep_token": "</s>",
12
- "tokenizer_class": "RobertaTokenizer",
13
- "trim_offsets": true,
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "best_metric": 0.2652136752136752,
3
- "best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-105",
4
- "epoch": 0.995260663507109,
5
- "global_step": 105,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.95,
12
- "learning_rate": 1.9250253292806485e-05,
13
- "loss": 1.4812,
14
- "step": 100
15
- },
16
- {
17
- "epoch": 1.0,
18
- "eval_accuracy": 0.6228070175438597,
19
- "eval_f1_macro": 0.2652136752136752,
20
- "eval_loss": 1.1202526092529297,
21
- "eval_runtime": 0.3252,
22
- "eval_samples_per_second": 350.595,
23
- "eval_steps_per_second": 24.603,
24
- "step": 105
25
- }
26
- ],
27
- "max_steps": 1050,
28
- "num_train_epochs": 10,
29
- "total_flos": 88083700250400.0,
30
- "trial_name": null,
31
- "trial_params": null
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a82ba2d5725c467bfc3412179472a4ca7b1afb1409e3c26c41d2afbb8ac6165b
3
- size 4027
 
 
 
 
last-checkpoint/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66fa2d4d1438d9e3c80629c01a36932041dd5fe913de0ae7c56339dca851b0eb
3
  size 498674357
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07d93a87c4e2ff39ff6d37e3978096ba0f2244c1339460e4dff4ce416948d22
3
  size 498674357
runs/Apr20_23-46-24_jupyter/events.out.tfevents.1713656793.jupyter.2697769.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4fd980c53c2dc5d30fe4b5c1033afc34ed5fc61705536004286df9f6ef5dc9e
3
- size 4912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7719da23057a0747e3b32138e8d548e25ed59ab8d6aaaa607a6db25ac0aa089d
3
+ size 10054
last-checkpoint/scheduler.pt → runs/Apr20_23-46-24_jupyter/events.out.tfevents.1713657026.jupyter.2697769.1 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6aae226b0a385b18c8012f4d652e8fbdd18f15a3fe78c710dfd63cccbeb8c1b
3
- size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55cf96a2089482edcad10a0e7bdcaddf830539a1054f3982e2fec5831b0b103b
3
+ size 415