maulairfani commited on
Commit
f51e858
1 Parent(s): 46789b8

Training in progress, epoch 3

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:147b043c4eebd0436a12a687cee56fac32311db88864be30d239481b91e2b60f
3
  size 437977104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65181ea900570cf5127cb660d03607b024721098ca998459251fd3e5d5fd2a8d
3
  size 437977104
run-0/checkpoint-500/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-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c398b95a1345d7b7a057ecd09a1a31ddff5579146db211a0bdfc8e1f26581c6f
3
+ size 437977104
run-0/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7ca23e0a9ce4fb27827592825125d1eda0cd447b38d87f4b55ee70bda6ebc8
3
+ size 876075258
run-0/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f3735e95080a2561dfe77dad28c55e67ceafd77105e11cdd4e0e88bebd1ce01
3
+ size 14244
run-0/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd75260403d0f1e7fe2f03be482d36c7a56e9e5e0e8a3ffbeba5b6cbf704863
3
+ size 1064
run-0/checkpoint-500/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-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-500/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-500/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8877580165863037,
3
+ "best_model_checkpoint": "satriadata/run-0/checkpoint-500",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
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
+ "epoch": 2.0,
22
+ "grad_norm": 8.648948669433594,
23
+ "learning_rate": 5.086297130534548e-05,
24
+ "loss": 1.4798,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_f1": 0.7148278885110101,
30
+ "eval_loss": 0.8877580165863037,
31
+ "eval_runtime": 15.0754,
32
+ "eval_samples_per_second": 66.333,
33
+ "eval_steps_per_second": 4.179,
34
+ "step": 500
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1250,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 5,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": false
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 2105001836544000.0,
55
+ "train_batch_size": 16,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "gradient_accumulation_steps": 1,
59
+ "learning_rate": 6.781729507379398e-05,
60
+ "optimizer": "adamw",
61
+ "per_device_train_batch_size": 16,
62
+ "warmup_ratio": 0.2,
63
+ "weight_decay": 0.01
64
+ }
65
+ }
run-0/checkpoint-500/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-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-750/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-750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65181ea900570cf5127cb660d03607b024721098ca998459251fd3e5d5fd2a8d
3
+ size 437977104
run-0/checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa9a3a325c889f28ee781949c054548aee5cb3ab373c39b32ba47c3285a905e
3
+ size 876075258
run-0/checkpoint-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a63e39490720f9e5149f22ea1c9305a9eb986e42d172cfe5b25c344828e2a4c
3
+ size 14244
run-0/checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9799234be91e6fc2704898efe49a84d28434c1af72711214f7b4ab5d5fea0b95
3
+ size 1064
run-0/checkpoint-750/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-750/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-750/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-750/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6009902358055115,
3
+ "best_model_checkpoint": "satriadata/run-0/checkpoint-750",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 750,
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
+ "epoch": 2.0,
22
+ "grad_norm": 8.648948669433594,
23
+ "learning_rate": 5.086297130534548e-05,
24
+ "loss": 1.4798,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_f1": 0.7148278885110101,
30
+ "eval_loss": 0.8877580165863037,
31
+ "eval_runtime": 15.0754,
32
+ "eval_samples_per_second": 66.333,
33
+ "eval_steps_per_second": 4.179,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_f1": 0.8147606395143462,
39
+ "eval_loss": 0.6009902358055115,
40
+ "eval_runtime": 15.0542,
41
+ "eval_samples_per_second": 66.427,
42
+ "eval_steps_per_second": 4.185,
43
+ "step": 750
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 1250,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 5,
50
+ "save_steps": 500,
51
+ "stateful_callbacks": {
52
+ "TrainerControl": {
53
+ "args": {
54
+ "should_epoch_stop": false,
55
+ "should_evaluate": false,
56
+ "should_log": false,
57
+ "should_save": true,
58
+ "should_training_stop": false
59
+ },
60
+ "attributes": {}
61
+ }
62
+ },
63
+ "total_flos": 2105001836544000.0,
64
+ "train_batch_size": 16,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "gradient_accumulation_steps": 1,
68
+ "learning_rate": 6.781729507379398e-05,
69
+ "optimizer": "adamw",
70
+ "per_device_train_batch_size": 16,
71
+ "warmup_ratio": 0.2,
72
+ "weight_decay": 0.01
73
+ }
74
+ }
run-0/checkpoint-750/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-750/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jun18_14-34-24_8081f73fda98/events.out.tfevents.1718721268.8081f73fda98.3906.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de6984d055a11e8e0d94ccc53d4fb1e948c4d58562da352d5545a66b305f6656
3
- size 5541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee9b134d922d2e257ece0cac4f18d7d0bf858707575b2d7daefe89e1034ce072
3
+ size 6386