maulairfani commited on
Commit
46789b8
1 Parent(s): 3b443c3

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,45 +1,47 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "Ideologi",
13
- "1": "Sosial Budaya",
14
  "2": "Sumber Daya Alam",
15
- "3": "Geografi",
16
  "4": "Demografi",
17
- "5": "Pertahanan dan Keamanan",
18
- "6": "Politik",
19
- "7": "Ekonomi"
20
  },
21
  "initializer_range": 0.02,
 
22
  "label2id": {
23
  "Demografi": 4,
24
- "Ekonomi": 7,
25
- "Geografi": 3,
26
  "Ideologi": 0,
27
- "Pertahanan dan Keamanan": 5,
28
- "Politik": 6,
29
- "Sosial Budaya": 1,
30
  "Sumber Daya Alam": 2
31
  },
 
32
  "max_position_embeddings": 512,
33
- "model_type": "distilbert",
34
- "n_heads": 12,
35
- "n_layers": 6,
36
  "pad_token_id": 0,
 
37
  "problem_type": "single_label_classification",
38
- "qa_dropout": 0.1,
39
- "seq_classif_dropout": 0.2,
40
- "sinusoidal_pos_embds": false,
41
- "tie_weights_": true,
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.41.2",
 
 
44
  "vocab_size": 30522
45
  }
 
1
  {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
 
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
  "id2label": {
13
  "0": "Ideologi",
14
+ "1": "Politik",
15
  "2": "Sumber Daya Alam",
16
+ "3": "Sosial Budaya",
17
  "4": "Demografi",
18
+ "5": "Geografi",
19
+ "6": "Ekonomi",
20
+ "7": "Pertahanan dan Keamanan"
21
  },
22
  "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
  "label2id": {
25
  "Demografi": 4,
26
+ "Ekonomi": 6,
27
+ "Geografi": 5,
28
  "Ideologi": 0,
29
+ "Pertahanan dan Keamanan": 7,
30
+ "Politik": 1,
31
+ "Sosial Budaya": 3,
32
  "Sumber Daya Alam": 2
33
  },
34
+ "layer_norm_eps": 1e-12,
35
  "max_position_embeddings": 512,
36
+ "model_type": "bert",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
  "pad_token_id": 0,
40
+ "position_embedding_type": "absolute",
41
  "problem_type": "single_label_classification",
 
 
 
 
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.41.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
  "vocab_size": 30522
47
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:286e1d9b200b828485a07f8e9e6840965a4cf62069ebc701d1afdf4b558ba20c
3
- size 267851024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147b043c4eebd0436a12a687cee56fac32311db88864be30d239481b91e2b60f
3
+ size 437977104
run-0/checkpoint-250/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Ideologi",
14
+ "1": "Politik",
15
+ "2": "Sumber Daya Alam",
16
+ "3": "Sosial Budaya",
17
+ "4": "Demografi",
18
+ "5": "Geografi",
19
+ "6": "Ekonomi",
20
+ "7": "Pertahanan dan Keamanan"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "Demografi": 4,
26
+ "Ekonomi": 6,
27
+ "Geografi": 5,
28
+ "Ideologi": 0,
29
+ "Pertahanan dan Keamanan": 7,
30
+ "Politik": 1,
31
+ "Sosial Budaya": 3,
32
+ "Sumber Daya Alam": 2
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "max_position_embeddings": 512,
36
+ "model_type": "bert",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "pad_token_id": 0,
40
+ "position_embedding_type": "absolute",
41
+ "problem_type": "single_label_classification",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.41.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 30522
47
+ }
run-0/checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147b043c4eebd0436a12a687cee56fac32311db88864be30d239481b91e2b60f
3
+ size 437977104
run-0/checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0e9ebde22cc873942f71c19b4b21d417ccbf7d2e2690b88a1e5e50e90e60919
3
+ size 876075258
run-0/checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435df9bc2d6f7132f805738c14de53037aad8fd051b67b374c384827cfa4abc4
3
+ size 14244
run-0/checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8028e0723a17101f5e3b41ac85f0a58777f62476f5d5422cd103e7c8896e5119
3
+ size 1064
run-0/checkpoint-250/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-250/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-250/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3270556926727295,
3
+ "best_model_checkpoint": "satriadata/run-0/checkpoint-250",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 250,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_f1": 0.520844900048434,
14
+ "eval_loss": 1.3270556926727295,
15
+ "eval_runtime": 15.2159,
16
+ "eval_samples_per_second": 65.721,
17
+ "eval_steps_per_second": 4.14,
18
+ "step": 250
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1250,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "stateful_callbacks": {
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": false
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 16,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "gradient_accumulation_steps": 1,
43
+ "learning_rate": 6.781729507379398e-05,
44
+ "optimizer": "adamw",
45
+ "per_device_train_batch_size": 16,
46
+ "warmup_ratio": 0.2,
47
+ "weight_decay": 0.01
48
+ }
49
+ }
run-0/checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4abaae79bebab84d41f2cc797ca65537defd0aa0551a2db6488e1d56e27f56e5
3
+ size 5112
run-0/checkpoint-250/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jun18_14-28-53_8081f73fda98/events.out.tfevents.1718720935.8081f73fda98.283.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a72046291c2dc879c83004c20040ee13b3e085d7872cb73dcac42e392cb4c2a
3
+ size 5226
runs/Jun18_14-34-24_8081f73fda98/events.out.tfevents.1718721268.8081f73fda98.3906.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6984d055a11e8e0d94ccc53d4fb1e948c4d58562da352d5545a66b305f6656
3
+ size 5541
tokenizer_config.json CHANGED
@@ -50,6 +50,6 @@
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03b307a21b51df0656b6cb9db3423c69bf0cc114b8b216ac3ac0297312c11ef5
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4abaae79bebab84d41f2cc797ca65537defd0aa0551a2db6488e1d56e27f56e5
3
  size 5112