maulairfani commited on
Commit
b70bc65
1 Parent(s): 5024f91

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1036b0e130873abffbdebd8d5d578898371e33ac172389ec55bfbdc9aa024367
3
  size 437977104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e590568e759b254d8d68e6b275bf92d5a77fc1a3153443d7ccf006d8aef4902a
3
  size 437977104
run-1/checkpoint-166/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-1/checkpoint-166/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e590568e759b254d8d68e6b275bf92d5a77fc1a3153443d7ccf006d8aef4902a
3
+ size 437977104
run-1/checkpoint-166/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c61793c3d7543d340aa164fa2ccef5bdb0d5247fb1eaa8f4f025d8a95d54e22
3
+ size 876075258
run-1/checkpoint-166/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-1/checkpoint-166/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b3facfaaad2bd918838f3c98c73551a6e41ded25b8d4fb52ed28a5f0c8049a
3
+ size 1064
run-1/checkpoint-166/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-1/checkpoint-166/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-166/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-1/checkpoint-166/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0041351318359375,
3
+ "best_model_checkpoint": "satriadata/run-1/checkpoint-166",
4
+ "epoch": 1.992,
5
+ "eval_steps": 500,
6
+ "global_step": 166,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.996,
13
+ "eval_f1": 0.34139582972404187,
14
+ "eval_loss": 1.5640060901641846,
15
+ "eval_runtime": 15.1373,
16
+ "eval_samples_per_second": 66.062,
17
+ "eval_steps_per_second": 4.162,
18
+ "step": 83
19
+ },
20
+ {
21
+ "epoch": 1.992,
22
+ "eval_f1": 0.6408845370670369,
23
+ "eval_loss": 1.0041351318359375,
24
+ "eval_runtime": 15.1161,
25
+ "eval_samples_per_second": 66.155,
26
+ "eval_steps_per_second": 4.168,
27
+ "step": 166
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 415,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": false
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "gradient_accumulation_steps": 3,
52
+ "learning_rate": 8.484535826382634e-05,
53
+ "optimizer": "sgd",
54
+ "per_device_train_batch_size": 16,
55
+ "warmup_ratio": 0.3,
56
+ "weight_decay": 0.01
57
+ }
58
+ }
run-1/checkpoint-166/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108227d95b08c5e3d95c9d4f4c5b66777995656dac6ed7edd37b99b02be46fed
3
+ size 5112
run-1/checkpoint-166/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-83/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-1/checkpoint-83/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7d381ff2b5faa94ea77935d3e4086351f00bf8dcd9ec78ba9285752f32661c
3
+ size 437977104
run-1/checkpoint-83/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e907eb376af21dcbf0d648659daab3ca6e4de53fcb5699d77b049d6fbf02e3
3
+ size 876075258
run-1/checkpoint-83/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-1/checkpoint-83/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e787743030f676d666cfb4882c3381010254ffd2149aa33e3f64cf19a5fc42cc
3
+ size 1064
run-1/checkpoint-83/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-1/checkpoint-83/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-83/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-1/checkpoint-83/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.5640060901641846,
3
+ "best_model_checkpoint": "satriadata/run-1/checkpoint-83",
4
+ "epoch": 0.996,
5
+ "eval_steps": 500,
6
+ "global_step": 83,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.996,
13
+ "eval_f1": 0.34139582972404187,
14
+ "eval_loss": 1.5640060901641846,
15
+ "eval_runtime": 15.1373,
16
+ "eval_samples_per_second": 66.062,
17
+ "eval_steps_per_second": 4.162,
18
+ "step": 83
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 415,
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": 3,
43
+ "learning_rate": 8.484535826382634e-05,
44
+ "optimizer": "sgd",
45
+ "per_device_train_batch_size": 16,
46
+ "warmup_ratio": 0.3,
47
+ "weight_decay": 0.01
48
+ }
49
+ }
run-1/checkpoint-83/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108227d95b08c5e3d95c9d4f4c5b66777995656dac6ed7edd37b99b02be46fed
3
+ size 5112
run-1/checkpoint-83/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.1718722224.8081f73fda98.3906.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978bbdbbcf94f4c48357a9272a364af3d0bc085baa29cf333891fef30fc09ee7
3
+ size 5852
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4abaae79bebab84d41f2cc797ca65537defd0aa0551a2db6488e1d56e27f56e5
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108227d95b08c5e3d95c9d4f4c5b66777995656dac6ed7edd37b99b02be46fed
3
  size 5112