michaelmanurung commited on
Commit
8cf6b0a
·
1 Parent(s): b7c67ef

Upload FinBERT for Bahasa Indonesia finance sentiment

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .DS_Store +0 -0
  2. checkpoint-126/config.json +36 -0
  3. checkpoint-126/model.safetensors +3 -0
  4. checkpoint-126/optimizer.pt +3 -0
  5. checkpoint-126/rng_state.pth +3 -0
  6. checkpoint-126/scheduler.pt +3 -0
  7. checkpoint-126/special_tokens_map.json +7 -0
  8. checkpoint-126/tokenizer.json +0 -0
  9. checkpoint-126/tokenizer_config.json +58 -0
  10. checkpoint-126/trainer_state.json +145 -0
  11. checkpoint-126/training_args.bin +3 -0
  12. checkpoint-126/vocab.txt +0 -0
  13. checkpoint-168/config.json +36 -0
  14. checkpoint-168/model.safetensors +3 -0
  15. checkpoint-168/optimizer.pt +3 -0
  16. checkpoint-168/rng_state.pth +3 -0
  17. checkpoint-168/scheduler.pt +3 -0
  18. checkpoint-168/special_tokens_map.json +7 -0
  19. checkpoint-168/tokenizer.json +0 -0
  20. checkpoint-168/tokenizer_config.json +58 -0
  21. checkpoint-168/trainer_state.json +182 -0
  22. checkpoint-168/training_args.bin +3 -0
  23. checkpoint-168/vocab.txt +0 -0
  24. checkpoint-210/config.json +36 -0
  25. checkpoint-210/model.safetensors +3 -0
  26. checkpoint-210/optimizer.pt +3 -0
  27. checkpoint-210/rng_state.pth +3 -0
  28. checkpoint-210/scheduler.pt +3 -0
  29. checkpoint-210/special_tokens_map.json +7 -0
  30. checkpoint-210/tokenizer.json +0 -0
  31. checkpoint-210/tokenizer_config.json +58 -0
  32. checkpoint-210/trainer_state.json +226 -0
  33. checkpoint-210/training_args.bin +3 -0
  34. checkpoint-210/vocab.txt +0 -0
  35. checkpoint-42/config.json +36 -0
  36. checkpoint-42/model.safetensors +3 -0
  37. checkpoint-42/optimizer.pt +3 -0
  38. checkpoint-42/rng_state.pth +3 -0
  39. checkpoint-42/scheduler.pt +3 -0
  40. checkpoint-42/special_tokens_map.json +7 -0
  41. checkpoint-42/tokenizer.json +0 -0
  42. checkpoint-42/tokenizer_config.json +58 -0
  43. checkpoint-42/trainer_state.json +71 -0
  44. checkpoint-42/training_args.bin +3 -0
  45. checkpoint-42/vocab.txt +0 -0
  46. checkpoint-84/config.json +36 -0
  47. checkpoint-84/model.safetensors +3 -0
  48. checkpoint-84/optimizer.pt +3 -0
  49. checkpoint-84/rng_state.pth +3 -0
  50. checkpoint-84/scheduler.pt +3 -0
.DS_Store ADDED
Binary file (6.15 kB). View file
 
checkpoint-126/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "negative",
14
+ "2": "neutral"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 1,
20
+ "neutral": 2,
21
+ "positive": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.52.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-126/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1bc9d20734e8995b0b581498c2cb1a44003e4c7f2568ce78eccbb3166c12a83
3
+ size 437961724
checkpoint-126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7734a56e5ef4b5a5fa948218baeb0f47da6ee81de85e909f5cac79fe8d2677f2
3
+ size 876039307
checkpoint-126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391d01d3aeb4a35151817d446e4ba0b9c8a04084ae1b1b66eda188a30729da0a
3
+ size 14455
checkpoint-126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b1a9a40162a28023ab4d3ac5ac7ba35825c87b27f08a07b5c96d9ef66c8f28
3
+ size 1465
checkpoint-126/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
+ }
checkpoint-126/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-126/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-126/trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 84,
3
+ "best_metric": 0.6309523809523809,
4
+ "best_model_checkpoint": "./finbert-indonesia/checkpoint-84",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 126,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23809523809523808,
14
+ "grad_norm": 11.72082805633545,
15
+ "learning_rate": 1.9142857142857146e-05,
16
+ "loss": 1.4184,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.47619047619047616,
21
+ "grad_norm": 5.9547343254089355,
22
+ "learning_rate": 1.819047619047619e-05,
23
+ "loss": 1.0193,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7142857142857143,
28
+ "grad_norm": 3.776716709136963,
29
+ "learning_rate": 1.723809523809524e-05,
30
+ "loss": 0.9112,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9523809523809523,
35
+ "grad_norm": 12.227482795715332,
36
+ "learning_rate": 1.6285714285714287e-05,
37
+ "loss": 1.1293,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.4880952380952381,
43
+ "eval_loss": 1.0485572814941406,
44
+ "eval_runtime": 2.6921,
45
+ "eval_samples_per_second": 31.202,
46
+ "eval_steps_per_second": 4.086,
47
+ "step": 42
48
+ },
49
+ {
50
+ "epoch": 1.1904761904761905,
51
+ "grad_norm": 4.766658782958984,
52
+ "learning_rate": 1.5333333333333334e-05,
53
+ "loss": 1.0195,
54
+ "step": 50
55
+ },
56
+ {
57
+ "epoch": 1.4285714285714286,
58
+ "grad_norm": 6.310060501098633,
59
+ "learning_rate": 1.4380952380952382e-05,
60
+ "loss": 0.9741,
61
+ "step": 60
62
+ },
63
+ {
64
+ "epoch": 1.6666666666666665,
65
+ "grad_norm": 4.878066062927246,
66
+ "learning_rate": 1.3428571428571429e-05,
67
+ "loss": 0.8246,
68
+ "step": 70
69
+ },
70
+ {
71
+ "epoch": 1.9047619047619047,
72
+ "grad_norm": 6.193632125854492,
73
+ "learning_rate": 1.2476190476190478e-05,
74
+ "loss": 0.9586,
75
+ "step": 80
76
+ },
77
+ {
78
+ "epoch": 2.0,
79
+ "eval_accuracy": 0.6309523809523809,
80
+ "eval_loss": 0.9428242444992065,
81
+ "eval_runtime": 3.1407,
82
+ "eval_samples_per_second": 26.745,
83
+ "eval_steps_per_second": 3.502,
84
+ "step": 84
85
+ },
86
+ {
87
+ "epoch": 2.142857142857143,
88
+ "grad_norm": 6.544936656951904,
89
+ "learning_rate": 1.1523809523809524e-05,
90
+ "loss": 0.9448,
91
+ "step": 90
92
+ },
93
+ {
94
+ "epoch": 2.380952380952381,
95
+ "grad_norm": 6.193615913391113,
96
+ "learning_rate": 1.0571428571428572e-05,
97
+ "loss": 0.7096,
98
+ "step": 100
99
+ },
100
+ {
101
+ "epoch": 2.619047619047619,
102
+ "grad_norm": 15.770059585571289,
103
+ "learning_rate": 9.61904761904762e-06,
104
+ "loss": 0.8479,
105
+ "step": 110
106
+ },
107
+ {
108
+ "epoch": 2.857142857142857,
109
+ "grad_norm": 18.868295669555664,
110
+ "learning_rate": 8.666666666666668e-06,
111
+ "loss": 0.7619,
112
+ "step": 120
113
+ },
114
+ {
115
+ "epoch": 3.0,
116
+ "eval_accuracy": 0.6071428571428571,
117
+ "eval_loss": 0.8931267857551575,
118
+ "eval_runtime": 2.8535,
119
+ "eval_samples_per_second": 29.437,
120
+ "eval_steps_per_second": 3.855,
121
+ "step": 126
122
+ }
123
+ ],
124
+ "logging_steps": 10,
125
+ "max_steps": 210,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 5,
128
+ "save_steps": 500,
129
+ "stateful_callbacks": {
130
+ "TrainerControl": {
131
+ "args": {
132
+ "should_epoch_stop": false,
133
+ "should_evaluate": false,
134
+ "should_log": false,
135
+ "should_save": true,
136
+ "should_training_stop": false
137
+ },
138
+ "attributes": {}
139
+ }
140
+ },
141
+ "total_flos": 66107246204160.0,
142
+ "train_batch_size": 8,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }
checkpoint-126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6cc0b41b9d8f9898b0c646044debe9f1c3eaf0dd449d9c0dab2f17e006e62d
3
+ size 5649
checkpoint-126/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-168/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "negative",
14
+ "2": "neutral"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 1,
20
+ "neutral": 2,
21
+ "positive": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.52.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-168/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722f89756ba3b9fdc8f97bdd2ec23b174c13de6a768153fe5114db2a39d4c15f
3
+ size 437961724
checkpoint-168/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb611da54380dbdf984b2d93dcae52098e598ae90eda09f25318948fd0e7def6
3
+ size 876039307
checkpoint-168/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67627e3b026c4c5d776980914bd7f99f2f9814ae6ac5a3bd1d93ee8d2ff6784f
3
+ size 14455
checkpoint-168/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6bde06fcf3dff00ce3fd903502be0594a381e3b079ab0de0abb3de57acab8e
3
+ size 1465
checkpoint-168/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
+ }
checkpoint-168/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-168/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-168/trainer_state.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 84,
3
+ "best_metric": 0.6309523809523809,
4
+ "best_model_checkpoint": "./finbert-indonesia/checkpoint-84",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 168,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23809523809523808,
14
+ "grad_norm": 11.72082805633545,
15
+ "learning_rate": 1.9142857142857146e-05,
16
+ "loss": 1.4184,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.47619047619047616,
21
+ "grad_norm": 5.9547343254089355,
22
+ "learning_rate": 1.819047619047619e-05,
23
+ "loss": 1.0193,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7142857142857143,
28
+ "grad_norm": 3.776716709136963,
29
+ "learning_rate": 1.723809523809524e-05,
30
+ "loss": 0.9112,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9523809523809523,
35
+ "grad_norm": 12.227482795715332,
36
+ "learning_rate": 1.6285714285714287e-05,
37
+ "loss": 1.1293,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.4880952380952381,
43
+ "eval_loss": 1.0485572814941406,
44
+ "eval_runtime": 2.6921,
45
+ "eval_samples_per_second": 31.202,
46
+ "eval_steps_per_second": 4.086,
47
+ "step": 42
48
+ },
49
+ {
50
+ "epoch": 1.1904761904761905,
51
+ "grad_norm": 4.766658782958984,
52
+ "learning_rate": 1.5333333333333334e-05,
53
+ "loss": 1.0195,
54
+ "step": 50
55
+ },
56
+ {
57
+ "epoch": 1.4285714285714286,
58
+ "grad_norm": 6.310060501098633,
59
+ "learning_rate": 1.4380952380952382e-05,
60
+ "loss": 0.9741,
61
+ "step": 60
62
+ },
63
+ {
64
+ "epoch": 1.6666666666666665,
65
+ "grad_norm": 4.878066062927246,
66
+ "learning_rate": 1.3428571428571429e-05,
67
+ "loss": 0.8246,
68
+ "step": 70
69
+ },
70
+ {
71
+ "epoch": 1.9047619047619047,
72
+ "grad_norm": 6.193632125854492,
73
+ "learning_rate": 1.2476190476190478e-05,
74
+ "loss": 0.9586,
75
+ "step": 80
76
+ },
77
+ {
78
+ "epoch": 2.0,
79
+ "eval_accuracy": 0.6309523809523809,
80
+ "eval_loss": 0.9428242444992065,
81
+ "eval_runtime": 3.1407,
82
+ "eval_samples_per_second": 26.745,
83
+ "eval_steps_per_second": 3.502,
84
+ "step": 84
85
+ },
86
+ {
87
+ "epoch": 2.142857142857143,
88
+ "grad_norm": 6.544936656951904,
89
+ "learning_rate": 1.1523809523809524e-05,
90
+ "loss": 0.9448,
91
+ "step": 90
92
+ },
93
+ {
94
+ "epoch": 2.380952380952381,
95
+ "grad_norm": 6.193615913391113,
96
+ "learning_rate": 1.0571428571428572e-05,
97
+ "loss": 0.7096,
98
+ "step": 100
99
+ },
100
+ {
101
+ "epoch": 2.619047619047619,
102
+ "grad_norm": 15.770059585571289,
103
+ "learning_rate": 9.61904761904762e-06,
104
+ "loss": 0.8479,
105
+ "step": 110
106
+ },
107
+ {
108
+ "epoch": 2.857142857142857,
109
+ "grad_norm": 18.868295669555664,
110
+ "learning_rate": 8.666666666666668e-06,
111
+ "loss": 0.7619,
112
+ "step": 120
113
+ },
114
+ {
115
+ "epoch": 3.0,
116
+ "eval_accuracy": 0.6071428571428571,
117
+ "eval_loss": 0.8931267857551575,
118
+ "eval_runtime": 2.8535,
119
+ "eval_samples_per_second": 29.437,
120
+ "eval_steps_per_second": 3.855,
121
+ "step": 126
122
+ },
123
+ {
124
+ "epoch": 3.0952380952380953,
125
+ "grad_norm": 26.78553581237793,
126
+ "learning_rate": 7.714285714285716e-06,
127
+ "loss": 0.6672,
128
+ "step": 130
129
+ },
130
+ {
131
+ "epoch": 3.3333333333333335,
132
+ "grad_norm": 6.862189769744873,
133
+ "learning_rate": 6.761904761904763e-06,
134
+ "loss": 0.627,
135
+ "step": 140
136
+ },
137
+ {
138
+ "epoch": 3.571428571428571,
139
+ "grad_norm": 58.950984954833984,
140
+ "learning_rate": 5.8095238095238106e-06,
141
+ "loss": 0.5897,
142
+ "step": 150
143
+ },
144
+ {
145
+ "epoch": 3.8095238095238093,
146
+ "grad_norm": 3.6594722270965576,
147
+ "learning_rate": 4.857142857142858e-06,
148
+ "loss": 0.5593,
149
+ "step": 160
150
+ },
151
+ {
152
+ "epoch": 4.0,
153
+ "eval_accuracy": 0.6190476190476191,
154
+ "eval_loss": 0.9272316694259644,
155
+ "eval_runtime": 2.8868,
156
+ "eval_samples_per_second": 29.098,
157
+ "eval_steps_per_second": 3.81,
158
+ "step": 168
159
+ }
160
+ ],
161
+ "logging_steps": 10,
162
+ "max_steps": 210,
163
+ "num_input_tokens_seen": 0,
164
+ "num_train_epochs": 5,
165
+ "save_steps": 500,
166
+ "stateful_callbacks": {
167
+ "TrainerControl": {
168
+ "args": {
169
+ "should_epoch_stop": false,
170
+ "should_evaluate": false,
171
+ "should_log": false,
172
+ "should_save": true,
173
+ "should_training_stop": false
174
+ },
175
+ "attributes": {}
176
+ }
177
+ },
178
+ "total_flos": 88142994938880.0,
179
+ "train_batch_size": 8,
180
+ "trial_name": null,
181
+ "trial_params": null
182
+ }
checkpoint-168/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6cc0b41b9d8f9898b0c646044debe9f1c3eaf0dd449d9c0dab2f17e006e62d
3
+ size 5649
checkpoint-168/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-210/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "negative",
14
+ "2": "neutral"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 1,
20
+ "neutral": 2,
21
+ "positive": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.52.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-210/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3811cd45c1c1349d18b11b49c5ce790c3e21a6aec21887e3cf1a543a6ae1bfe0
3
+ size 437961724
checkpoint-210/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa061d52aa9c0a65d8ded76ed49c13ff5ad00cff1df8b1b054c2c525ebe7a5b
3
+ size 876039307
checkpoint-210/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b652c6269b998b96ab924b2734c0818fab436c642524e13fc6cd4d9082e62b5
3
+ size 14455
checkpoint-210/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5712dcf5930ea5bcebe90766f60664af7663d5cee63b1f78045e1eacc4868843
3
+ size 1465
checkpoint-210/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
+ }
checkpoint-210/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-210/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-210/trainer_state.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 210,
3
+ "best_metric": 0.6547619047619048,
4
+ "best_model_checkpoint": "./finbert-indonesia/checkpoint-210",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 210,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23809523809523808,
14
+ "grad_norm": 11.72082805633545,
15
+ "learning_rate": 1.9142857142857146e-05,
16
+ "loss": 1.4184,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.47619047619047616,
21
+ "grad_norm": 5.9547343254089355,
22
+ "learning_rate": 1.819047619047619e-05,
23
+ "loss": 1.0193,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7142857142857143,
28
+ "grad_norm": 3.776716709136963,
29
+ "learning_rate": 1.723809523809524e-05,
30
+ "loss": 0.9112,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9523809523809523,
35
+ "grad_norm": 12.227482795715332,
36
+ "learning_rate": 1.6285714285714287e-05,
37
+ "loss": 1.1293,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.4880952380952381,
43
+ "eval_loss": 1.0485572814941406,
44
+ "eval_runtime": 2.6921,
45
+ "eval_samples_per_second": 31.202,
46
+ "eval_steps_per_second": 4.086,
47
+ "step": 42
48
+ },
49
+ {
50
+ "epoch": 1.1904761904761905,
51
+ "grad_norm": 4.766658782958984,
52
+ "learning_rate": 1.5333333333333334e-05,
53
+ "loss": 1.0195,
54
+ "step": 50
55
+ },
56
+ {
57
+ "epoch": 1.4285714285714286,
58
+ "grad_norm": 6.310060501098633,
59
+ "learning_rate": 1.4380952380952382e-05,
60
+ "loss": 0.9741,
61
+ "step": 60
62
+ },
63
+ {
64
+ "epoch": 1.6666666666666665,
65
+ "grad_norm": 4.878066062927246,
66
+ "learning_rate": 1.3428571428571429e-05,
67
+ "loss": 0.8246,
68
+ "step": 70
69
+ },
70
+ {
71
+ "epoch": 1.9047619047619047,
72
+ "grad_norm": 6.193632125854492,
73
+ "learning_rate": 1.2476190476190478e-05,
74
+ "loss": 0.9586,
75
+ "step": 80
76
+ },
77
+ {
78
+ "epoch": 2.0,
79
+ "eval_accuracy": 0.6309523809523809,
80
+ "eval_loss": 0.9428242444992065,
81
+ "eval_runtime": 3.1407,
82
+ "eval_samples_per_second": 26.745,
83
+ "eval_steps_per_second": 3.502,
84
+ "step": 84
85
+ },
86
+ {
87
+ "epoch": 2.142857142857143,
88
+ "grad_norm": 6.544936656951904,
89
+ "learning_rate": 1.1523809523809524e-05,
90
+ "loss": 0.9448,
91
+ "step": 90
92
+ },
93
+ {
94
+ "epoch": 2.380952380952381,
95
+ "grad_norm": 6.193615913391113,
96
+ "learning_rate": 1.0571428571428572e-05,
97
+ "loss": 0.7096,
98
+ "step": 100
99
+ },
100
+ {
101
+ "epoch": 2.619047619047619,
102
+ "grad_norm": 15.770059585571289,
103
+ "learning_rate": 9.61904761904762e-06,
104
+ "loss": 0.8479,
105
+ "step": 110
106
+ },
107
+ {
108
+ "epoch": 2.857142857142857,
109
+ "grad_norm": 18.868295669555664,
110
+ "learning_rate": 8.666666666666668e-06,
111
+ "loss": 0.7619,
112
+ "step": 120
113
+ },
114
+ {
115
+ "epoch": 3.0,
116
+ "eval_accuracy": 0.6071428571428571,
117
+ "eval_loss": 0.8931267857551575,
118
+ "eval_runtime": 2.8535,
119
+ "eval_samples_per_second": 29.437,
120
+ "eval_steps_per_second": 3.855,
121
+ "step": 126
122
+ },
123
+ {
124
+ "epoch": 3.0952380952380953,
125
+ "grad_norm": 26.78553581237793,
126
+ "learning_rate": 7.714285714285716e-06,
127
+ "loss": 0.6672,
128
+ "step": 130
129
+ },
130
+ {
131
+ "epoch": 3.3333333333333335,
132
+ "grad_norm": 6.862189769744873,
133
+ "learning_rate": 6.761904761904763e-06,
134
+ "loss": 0.627,
135
+ "step": 140
136
+ },
137
+ {
138
+ "epoch": 3.571428571428571,
139
+ "grad_norm": 58.950984954833984,
140
+ "learning_rate": 5.8095238095238106e-06,
141
+ "loss": 0.5897,
142
+ "step": 150
143
+ },
144
+ {
145
+ "epoch": 3.8095238095238093,
146
+ "grad_norm": 3.6594722270965576,
147
+ "learning_rate": 4.857142857142858e-06,
148
+ "loss": 0.5593,
149
+ "step": 160
150
+ },
151
+ {
152
+ "epoch": 4.0,
153
+ "eval_accuracy": 0.6190476190476191,
154
+ "eval_loss": 0.9272316694259644,
155
+ "eval_runtime": 2.8868,
156
+ "eval_samples_per_second": 29.098,
157
+ "eval_steps_per_second": 3.81,
158
+ "step": 168
159
+ },
160
+ {
161
+ "epoch": 4.0476190476190474,
162
+ "grad_norm": 13.396079063415527,
163
+ "learning_rate": 3.9047619047619055e-06,
164
+ "loss": 0.5422,
165
+ "step": 170
166
+ },
167
+ {
168
+ "epoch": 4.285714285714286,
169
+ "grad_norm": 20.802480697631836,
170
+ "learning_rate": 2.9523809523809525e-06,
171
+ "loss": 0.4654,
172
+ "step": 180
173
+ },
174
+ {
175
+ "epoch": 4.523809523809524,
176
+ "grad_norm": 13.685426712036133,
177
+ "learning_rate": 2.0000000000000003e-06,
178
+ "loss": 0.4475,
179
+ "step": 190
180
+ },
181
+ {
182
+ "epoch": 4.761904761904762,
183
+ "grad_norm": 19.87287139892578,
184
+ "learning_rate": 1.0476190476190478e-06,
185
+ "loss": 0.3511,
186
+ "step": 200
187
+ },
188
+ {
189
+ "epoch": 5.0,
190
+ "grad_norm": 23.369476318359375,
191
+ "learning_rate": 9.523809523809525e-08,
192
+ "loss": 0.4605,
193
+ "step": 210
194
+ },
195
+ {
196
+ "epoch": 5.0,
197
+ "eval_accuracy": 0.6547619047619048,
198
+ "eval_loss": 0.9152089357376099,
199
+ "eval_runtime": 4.0091,
200
+ "eval_samples_per_second": 20.952,
201
+ "eval_steps_per_second": 2.744,
202
+ "step": 210
203
+ }
204
+ ],
205
+ "logging_steps": 10,
206
+ "max_steps": 210,
207
+ "num_input_tokens_seen": 0,
208
+ "num_train_epochs": 5,
209
+ "save_steps": 500,
210
+ "stateful_callbacks": {
211
+ "TrainerControl": {
212
+ "args": {
213
+ "should_epoch_stop": false,
214
+ "should_evaluate": false,
215
+ "should_log": false,
216
+ "should_save": true,
217
+ "should_training_stop": true
218
+ },
219
+ "attributes": {}
220
+ }
221
+ },
222
+ "total_flos": 110178743673600.0,
223
+ "train_batch_size": 8,
224
+ "trial_name": null,
225
+ "trial_params": null
226
+ }
checkpoint-210/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6cc0b41b9d8f9898b0c646044debe9f1c3eaf0dd449d9c0dab2f17e006e62d
3
+ size 5649
checkpoint-210/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-42/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "negative",
14
+ "2": "neutral"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 1,
20
+ "neutral": 2,
21
+ "positive": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.52.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c7139adaa929cb1033919842907503afe6ca4e18267d058eac2552ffc3650d
3
+ size 437961724
checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f9f9452eda9dc041f447373c3bc8c6064e0c3c034de79a619116315d8d71b2
3
+ size 876039307
checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
3
+ size 14455
checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea9e889ce1cb0d66bce78bfb9f71c1a7878533e28bc71ea584f8f9b7af3665a
3
+ size 1465
checkpoint-42/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
+ }
checkpoint-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-42/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-42/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 42,
3
+ "best_metric": 0.4880952380952381,
4
+ "best_model_checkpoint": "./finbert-indonesia/checkpoint-42",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 42,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23809523809523808,
14
+ "grad_norm": 11.72082805633545,
15
+ "learning_rate": 1.9142857142857146e-05,
16
+ "loss": 1.4184,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.47619047619047616,
21
+ "grad_norm": 5.9547343254089355,
22
+ "learning_rate": 1.819047619047619e-05,
23
+ "loss": 1.0193,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7142857142857143,
28
+ "grad_norm": 3.776716709136963,
29
+ "learning_rate": 1.723809523809524e-05,
30
+ "loss": 0.9112,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9523809523809523,
35
+ "grad_norm": 12.227482795715332,
36
+ "learning_rate": 1.6285714285714287e-05,
37
+ "loss": 1.1293,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.4880952380952381,
43
+ "eval_loss": 1.0485572814941406,
44
+ "eval_runtime": 2.6921,
45
+ "eval_samples_per_second": 31.202,
46
+ "eval_steps_per_second": 4.086,
47
+ "step": 42
48
+ }
49
+ ],
50
+ "logging_steps": 10,
51
+ "max_steps": 210,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 5,
54
+ "save_steps": 500,
55
+ "stateful_callbacks": {
56
+ "TrainerControl": {
57
+ "args": {
58
+ "should_epoch_stop": false,
59
+ "should_evaluate": false,
60
+ "should_log": false,
61
+ "should_save": true,
62
+ "should_training_stop": false
63
+ },
64
+ "attributes": {}
65
+ }
66
+ },
67
+ "total_flos": 22035748734720.0,
68
+ "train_batch_size": 8,
69
+ "trial_name": null,
70
+ "trial_params": null
71
+ }
checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6cc0b41b9d8f9898b0c646044debe9f1c3eaf0dd449d9c0dab2f17e006e62d
3
+ size 5649
checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-84/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "negative",
14
+ "2": "neutral"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 1,
20
+ "neutral": 2,
21
+ "positive": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.52.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-84/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb288af2b948ffa440f4c11ecc3fa96a2dd772e8bccd41d0d398b79f765b7cdc
3
+ size 437961724
checkpoint-84/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab4c77f790a2659359701880f5cec07edc0378af3de078bc9193ec2b44badf4
3
+ size 876039307
checkpoint-84/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1e0d31acc437fbbd16411d0d11d500c5f4dbbc7561671dab7dbf23eb0f2c43
3
+ size 14455
checkpoint-84/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b59639e9eae595718a1ab01c5b4747c82cb564bc10e15514a398801f4cabc5
3
+ size 1465