Hugging Face's logo

amruthsaravanan
/
nlp_coursework

Safetensors
bert
Model card Files
xet
Community
amruthsaravanan commited on
Commit
df9dca9
·
verified ·
1 Parent(s): 2496337

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. .gitattributes +35 -35
  2. checkpoint-500/config.json +37 -0
  3. checkpoint-500/model.safetensors +3 -0
  4. checkpoint-500/optimizer.pt +3 -0
  5. checkpoint-500/rng_state.pth +3 -0
  6. checkpoint-500/scheduler.pt +3 -0
  7. checkpoint-500/special_tokens_map.json +7 -0
  8. checkpoint-500/tokenizer.json +0 -0
  9. checkpoint-500/tokenizer_config.json +56 -0
  10. checkpoint-500/trainer_state.json +104 -0
  11. checkpoint-500/training_args.bin +3 -0
  12. checkpoint-500/vocab.txt +0 -0
  13. checkpoint-625/config.json +37 -0
  14. checkpoint-625/model.safetensors +3 -0
  15. checkpoint-625/optimizer.pt +3 -0
  16. checkpoint-625/rng_state.pth +3 -0
  17. checkpoint-625/scheduler.pt +3 -0
  18. checkpoint-625/special_tokens_map.json +7 -0
  19. checkpoint-625/tokenizer.json +0 -0
  20. checkpoint-625/tokenizer_config.json +56 -0
  21. checkpoint-625/trainer_state.json +118 -0
  22. checkpoint-625/training_args.bin +3 -0
  23. checkpoint-625/vocab.txt +0 -0
  24. config.json +37 -0
  25. model.safetensors +3 -0
  26. special_tokens_map.json +7 -0
  27. tokenizer.json +0 -0
  28. tokenizer_config.json +56 -0
  29. training_args.bin +3 -0
  30. vocab.txt +0 -0
.gitattributes CHANGED
@@ -1,35 +1,35 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
checkpoint-500/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.51.3",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 28996
37
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028ea11c5abcd21891d01ff9f4c26045ff24b8c9cd7ae92bcd561aef1ace4541
3
+ size 430914360
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e881cfff01339af3f8cf4ada8ca4bf464b1e5950c42afcd40e603e437eb42271
3
+ size 861942970
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e55bfc8723f269a626afca0be6f7def5753f3bb265436b94c5580b703cfcc7
3
+ size 13990
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b5e9db7dc485fb6903e2510137e5c68e03a012c440742c6f543e7d43c06d45
3
+ size 1064
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
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 1.7108097076416016,
15
+ "learning_rate": 4.608e-05,
16
+ "loss": 0.3769,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.3901269435882568,
22
+ "learning_rate": 4.2080000000000004e-05,
23
+ "loss": 0.2247,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 1.2,
28
+ "grad_norm": 1.5942708253860474,
29
+ "learning_rate": 3.808e-05,
30
+ "loss": 0.1805,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 1.6,
35
+ "grad_norm": 1.3408385515213013,
36
+ "learning_rate": 3.408e-05,
37
+ "loss": 0.1612,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "grad_norm": 0.718839168548584,
43
+ "learning_rate": 3.0080000000000003e-05,
44
+ "loss": 0.1457,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 2.4,
49
+ "grad_norm": 1.317421317100525,
50
+ "learning_rate": 2.6079999999999998e-05,
51
+ "loss": 0.1073,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 2.8,
56
+ "grad_norm": 0.8703721761703491,
57
+ "learning_rate": 2.2080000000000002e-05,
58
+ "loss": 0.1069,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 3.2,
63
+ "grad_norm": 1.669245719909668,
64
+ "learning_rate": 1.808e-05,
65
+ "loss": 0.1054,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 3.6,
70
+ "grad_norm": 3.690030336380005,
71
+ "learning_rate": 1.408e-05,
72
+ "loss": 0.0716,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "grad_norm": 0.9665364027023315,
78
+ "learning_rate": 1.008e-05,
79
+ "loss": 0.0798,
80
+ "step": 500
81
+ }
82
+ ],
83
+ "logging_steps": 50,
84
+ "max_steps": 625,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 5,
87
+ "save_steps": 500,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 522602962944000.0,
101
+ "train_batch_size": 16,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069780af66158dfff77a4ff07116f0be07b09dccab2586eb69a772150e5a0c8b
3
+ size 5240
checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-625/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.51.3",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 28996
37
+ }
checkpoint-625/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0124364870da5d509992c424a23cc8580a0fdc3396aacf61062f870e7bd924e1
3
+ size 430914360
checkpoint-625/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2bbda34ad73519bd8615a4f7a50713cd835b7bb90592aeb9e66e51aeca113a0
3
+ size 861942970
checkpoint-625/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99a64e57ebe46b8c692a3d62fe6ba40a21098b994c532d59b224553bcda3498
3
+ size 13990
checkpoint-625/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b65f21654a9b986602342db77742d0ba552a9a0ef1341e525f9fb900240570
3
+ size 1064
checkpoint-625/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-625/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-625/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-625/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 625,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 1.7108097076416016,
15
+ "learning_rate": 4.608e-05,
16
+ "loss": 0.3769,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.3901269435882568,
22
+ "learning_rate": 4.2080000000000004e-05,
23
+ "loss": 0.2247,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 1.2,
28
+ "grad_norm": 1.5942708253860474,
29
+ "learning_rate": 3.808e-05,
30
+ "loss": 0.1805,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 1.6,
35
+ "grad_norm": 1.3408385515213013,
36
+ "learning_rate": 3.408e-05,
37
+ "loss": 0.1612,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "grad_norm": 0.718839168548584,
43
+ "learning_rate": 3.0080000000000003e-05,
44
+ "loss": 0.1457,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 2.4,
49
+ "grad_norm": 1.317421317100525,
50
+ "learning_rate": 2.6079999999999998e-05,
51
+ "loss": 0.1073,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 2.8,
56
+ "grad_norm": 0.8703721761703491,
57
+ "learning_rate": 2.2080000000000002e-05,
58
+ "loss": 0.1069,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 3.2,
63
+ "grad_norm": 1.669245719909668,
64
+ "learning_rate": 1.808e-05,
65
+ "loss": 0.1054,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 3.6,
70
+ "grad_norm": 3.690030336380005,
71
+ "learning_rate": 1.408e-05,
72
+ "loss": 0.0716,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "grad_norm": 0.9665364027023315,
78
+ "learning_rate": 1.008e-05,
79
+ "loss": 0.0798,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 4.4,
84
+ "grad_norm": 0.6615438461303711,
85
+ "learning_rate": 6.08e-06,
86
+ "loss": 0.0549,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 4.8,
91
+ "grad_norm": 1.9341555833816528,
92
+ "learning_rate": 2.08e-06,
93
+ "loss": 0.0547,
94
+ "step": 600
95
+ }
96
+ ],
97
+ "logging_steps": 50,
98
+ "max_steps": 625,
99
+ "num_input_tokens_seen": 0,
100
+ "num_train_epochs": 5,
101
+ "save_steps": 500,
102
+ "stateful_callbacks": {
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": true
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 653253703680000.0,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-625/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069780af66158dfff77a4ff07116f0be07b09dccab2586eb69a772150e5a0c8b
3
+ size 5240
checkpoint-625/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.51.3",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 28996
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0124364870da5d509992c424a23cc8580a0fdc3396aacf61062f870e7bd924e1
3
+ size 430914360
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069780af66158dfff77a4ff07116f0be07b09dccab2586eb69a772150e5a0c8b
3
+ size 5240
vocab.txt ADDED
The diff for this file is too large to render. See raw diff