Hugging Face's logo

parthesh111
/
layoutlmv3-finetune-bioes-new

Token Classification
Safetensors
English
layoutlmv3
document-understanding
ocr
medical
bioes
Model card Files
xet
Community
parthesh111 commited on
Commit
7496a21
·
verified ·
1 Parent(s): 068dfda

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. checkpoint-800/config.json +133 -0
  2. checkpoint-800/merges.txt +0 -0
  3. checkpoint-800/model.safetensors +3 -0
  4. checkpoint-800/optimizer.pt +3 -0
  5. checkpoint-800/preprocessor_config.json +26 -0
  6. checkpoint-800/rng_state.pth +3 -0
  7. checkpoint-800/scaler.pt +3 -0
  8. checkpoint-800/scheduler.pt +3 -0
  9. checkpoint-800/special_tokens_map.json +51 -0
  10. checkpoint-800/tokenizer.json +0 -0
  11. checkpoint-800/tokenizer_config.json +80 -0
  12. checkpoint-800/trainer_state.json +594 -0
  13. checkpoint-800/training_args.bin +3 -0
  14. checkpoint-800/vocab.json +0 -0
  15. checkpoint-820/config.json +133 -0
  16. checkpoint-820/merges.txt +0 -0
  17. checkpoint-820/model.safetensors +3 -0
  18. checkpoint-820/optimizer.pt +3 -0
  19. checkpoint-820/preprocessor_config.json +26 -0
  20. checkpoint-820/rng_state.pth +3 -0
  21. checkpoint-820/scaler.pt +3 -0
  22. checkpoint-820/scheduler.pt +3 -0
  23. checkpoint-820/special_tokens_map.json +51 -0
  24. checkpoint-820/tokenizer.json +0 -0
  25. checkpoint-820/tokenizer_config.json +80 -0
  26. checkpoint-820/trainer_state.json +608 -0
  27. checkpoint-820/training_args.bin +3 -0
  28. checkpoint-820/vocab.json +0 -0
checkpoint-800/config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LayoutLMv3ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "coordinate_size": 128,
9
+ "eos_token_id": 2,
10
+ "has_relative_attention_bias": true,
11
+ "has_spatial_attention_bias": true,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-Lab-name",
18
+ "2": "I-Lab-name",
19
+ "3": "E-Lab-name",
20
+ "4": "S-Lab-name",
21
+ "5": "B-Dr-name",
22
+ "6": "I-Dr-name",
23
+ "7": "E-Dr-name",
24
+ "8": "S-Dr-name",
25
+ "9": "B-Dr-edu",
26
+ "10": "I-Dr-edu",
27
+ "11": "E-Dr-edu",
28
+ "12": "S-Dr-edu",
29
+ "13": "B-Address",
30
+ "14": "I-Address",
31
+ "15": "E-Address",
32
+ "16": "S-Address",
33
+ "17": "B-Phone-no",
34
+ "18": "I-Phone-no",
35
+ "19": "E-Phone-no",
36
+ "20": "S-Phone-no",
37
+ "21": "B-Patitent-no",
38
+ "22": "I-Patitent-no",
39
+ "23": "E-Patitent-no",
40
+ "24": "S-Patitent-no",
41
+ "25": "B-Patient-name",
42
+ "26": "I-Patient-name",
43
+ "27": "E-Patient-name",
44
+ "28": "S-Patient-name",
45
+ "29": "B-age",
46
+ "30": "I-age",
47
+ "31": "E-age",
48
+ "32": "S-age",
49
+ "33": "B-sex",
50
+ "34": "I-sex",
51
+ "35": "E-sex",
52
+ "36": "S-sex",
53
+ "37": "B-ref-by",
54
+ "38": "I-ref-by",
55
+ "39": "E-ref-by",
56
+ "40": "S-ref-by",
57
+ "41": "B-date",
58
+ "42": "I-date",
59
+ "43": "E-date",
60
+ "44": "S-date"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "input_size": 224,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "B-Address": 13,
67
+ "B-Dr-edu": 9,
68
+ "B-Dr-name": 5,
69
+ "B-Lab-name": 1,
70
+ "B-Patient-name": 25,
71
+ "B-Patitent-no": 21,
72
+ "B-Phone-no": 17,
73
+ "B-age": 29,
74
+ "B-date": 41,
75
+ "B-ref-by": 37,
76
+ "B-sex": 33,
77
+ "E-Address": 15,
78
+ "E-Dr-edu": 11,
79
+ "E-Dr-name": 7,
80
+ "E-Lab-name": 3,
81
+ "E-Patient-name": 27,
82
+ "E-Patitent-no": 23,
83
+ "E-Phone-no": 19,
84
+ "E-age": 31,
85
+ "E-date": 43,
86
+ "E-ref-by": 39,
87
+ "E-sex": 35,
88
+ "I-Address": 14,
89
+ "I-Dr-edu": 10,
90
+ "I-Dr-name": 6,
91
+ "I-Lab-name": 2,
92
+ "I-Patient-name": 26,
93
+ "I-Patitent-no": 22,
94
+ "I-Phone-no": 18,
95
+ "I-age": 30,
96
+ "I-date": 42,
97
+ "I-ref-by": 38,
98
+ "I-sex": 34,
99
+ "O": 0,
100
+ "S-Address": 16,
101
+ "S-Dr-edu": 12,
102
+ "S-Dr-name": 8,
103
+ "S-Lab-name": 4,
104
+ "S-Patient-name": 28,
105
+ "S-Patitent-no": 24,
106
+ "S-Phone-no": 20,
107
+ "S-age": 32,
108
+ "S-date": 44,
109
+ "S-ref-by": 40,
110
+ "S-sex": 36
111
+ },
112
+ "layer_norm_eps": 1e-05,
113
+ "max_2d_position_embeddings": 1024,
114
+ "max_position_embeddings": 514,
115
+ "max_rel_2d_pos": 256,
116
+ "max_rel_pos": 128,
117
+ "model_type": "layoutlmv3",
118
+ "num_attention_heads": 12,
119
+ "num_channels": 3,
120
+ "num_hidden_layers": 12,
121
+ "pad_token_id": 1,
122
+ "patch_size": 16,
123
+ "rel_2d_pos_bins": 64,
124
+ "rel_pos_bins": 32,
125
+ "second_input_size": 112,
126
+ "shape_size": 128,
127
+ "text_embed": true,
128
+ "torch_dtype": "float32",
129
+ "transformers_version": "4.52.2",
130
+ "type_vocab_size": 1,
131
+ "visual_embed": true,
132
+ "vocab_size": 50265
133
+ }
checkpoint-800/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbbca4ce86f9de964133d815bd2b02b9f6a14bcd8ae3f102c865986c422013a0
3
+ size 503835020
checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff5add7ee40abc95f83d161336a615bcbbc80836417a0defee0d203b5b45616
3
+ size 1007780154
checkpoint-800/preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "LayoutLMv3ImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv3Processor",
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
checkpoint-800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae639c9ae3d0b0017320eccabc13e42562c3b5c1439c142565c7a88f80fdb30
3
+ size 14244
checkpoint-800/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d26e9687ed387160aa99c5f36032f8ef15c2391c97a795e46a4329714467bc
3
+ size 988
checkpoint-800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d08f08b6c497105da5163c5d97686500f41b28f5d9719aa8e78dd960d4ac7e0
3
+ size 1064
checkpoint-800/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-800/tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "apply_ocr": false,
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": false,
48
+ "cls_token": "<s>",
49
+ "cls_token_box": [
50
+ 0,
51
+ 0,
52
+ 0,
53
+ 0
54
+ ],
55
+ "eos_token": "</s>",
56
+ "errors": "replace",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "model_max_length": 512,
60
+ "only_label_first_subword": true,
61
+ "pad_token": "<pad>",
62
+ "pad_token_box": [
63
+ 0,
64
+ 0,
65
+ 0,
66
+ 0
67
+ ],
68
+ "pad_token_label": -100,
69
+ "processor_class": "LayoutLMv3Processor",
70
+ "sep_token": "</s>",
71
+ "sep_token_box": [
72
+ 0,
73
+ 0,
74
+ 0,
75
+ 0
76
+ ],
77
+ "tokenizer_class": "LayoutLMv3Tokenizer",
78
+ "trim_offsets": true,
79
+ "unk_token": "<unk>"
80
+ }
checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 19.51851851851852,
6
+ "eval_steps": 500,
7
+ "global_step": 800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24691358024691357,
14
+ "grad_norm": 3.9386653900146484,
15
+ "learning_rate": 4.945121951219512e-05,
16
+ "loss": 2.6292,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.49382716049382713,
21
+ "grad_norm": 2.194047451019287,
22
+ "learning_rate": 4.884146341463415e-05,
23
+ "loss": 1.7588,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7407407407407407,
28
+ "grad_norm": 3.3464252948760986,
29
+ "learning_rate": 4.823170731707317e-05,
30
+ "loss": 1.2321,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9876543209876543,
35
+ "grad_norm": 4.9754157066345215,
36
+ "learning_rate": 4.76219512195122e-05,
37
+ "loss": 1.1094,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.2222222222222223,
42
+ "grad_norm": 1.6857168674468994,
43
+ "learning_rate": 4.701219512195122e-05,
44
+ "loss": 0.8016,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.4691358024691357,
49
+ "grad_norm": 1.711855173110962,
50
+ "learning_rate": 4.640243902439025e-05,
51
+ "loss": 0.6045,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 1.7160493827160495,
56
+ "grad_norm": 3.110994338989258,
57
+ "learning_rate": 4.5792682926829275e-05,
58
+ "loss": 0.611,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.9629629629629628,
63
+ "grad_norm": 2.2832303047180176,
64
+ "learning_rate": 4.5182926829268296e-05,
65
+ "loss": 0.4029,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 2.197530864197531,
70
+ "grad_norm": 2.3041841983795166,
71
+ "learning_rate": 4.457317073170732e-05,
72
+ "loss": 0.4292,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 2.4444444444444446,
77
+ "grad_norm": 1.5648462772369385,
78
+ "learning_rate": 4.3963414634146346e-05,
79
+ "loss": 0.3602,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 2.691358024691358,
84
+ "grad_norm": 0.8374887704849243,
85
+ "learning_rate": 4.335365853658537e-05,
86
+ "loss": 0.309,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 2.9382716049382713,
91
+ "grad_norm": 0.9409658908843994,
92
+ "learning_rate": 4.2743902439024395e-05,
93
+ "loss": 0.2612,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 3.1728395061728394,
98
+ "grad_norm": 3.718695878982544,
99
+ "learning_rate": 4.2134146341463416e-05,
100
+ "loss": 0.2936,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 3.419753086419753,
105
+ "grad_norm": 3.2449347972869873,
106
+ "learning_rate": 4.152439024390244e-05,
107
+ "loss": 0.1758,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 3.6666666666666665,
112
+ "grad_norm": 1.2654057741165161,
113
+ "learning_rate": 4.0914634146341465e-05,
114
+ "loss": 0.2181,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 3.9135802469135803,
119
+ "grad_norm": 0.7008330225944519,
120
+ "learning_rate": 4.030487804878049e-05,
121
+ "loss": 0.1788,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 4.148148148148148,
126
+ "grad_norm": 0.927452802658081,
127
+ "learning_rate": 3.9695121951219514e-05,
128
+ "loss": 0.2255,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 4.395061728395062,
133
+ "grad_norm": 0.9944292902946472,
134
+ "learning_rate": 3.908536585365854e-05,
135
+ "loss": 0.2719,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 4.6419753086419755,
140
+ "grad_norm": 1.1106724739074707,
141
+ "learning_rate": 3.847560975609756e-05,
142
+ "loss": 0.1458,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 4.888888888888889,
147
+ "grad_norm": 3.588369369506836,
148
+ "learning_rate": 3.786585365853659e-05,
149
+ "loss": 0.2225,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 5.1234567901234565,
154
+ "grad_norm": 14.498685836791992,
155
+ "learning_rate": 3.725609756097561e-05,
156
+ "loss": 0.1737,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 5.37037037037037,
161
+ "grad_norm": 15.858694076538086,
162
+ "learning_rate": 3.664634146341463e-05,
163
+ "loss": 0.1728,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 5.617283950617284,
168
+ "grad_norm": 3.0714364051818848,
169
+ "learning_rate": 3.603658536585366e-05,
170
+ "loss": 0.0774,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 5.864197530864198,
175
+ "grad_norm": 0.775265634059906,
176
+ "learning_rate": 3.542682926829268e-05,
177
+ "loss": 0.2107,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 6.098765432098766,
182
+ "grad_norm": 1.262907862663269,
183
+ "learning_rate": 3.48170731707317e-05,
184
+ "loss": 0.1312,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 6.345679012345679,
189
+ "grad_norm": 0.7409253120422363,
190
+ "learning_rate": 3.420731707317074e-05,
191
+ "loss": 0.1074,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 6.592592592592593,
196
+ "grad_norm": 2.9899144172668457,
197
+ "learning_rate": 3.359756097560976e-05,
198
+ "loss": 0.2688,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 6.839506172839506,
203
+ "grad_norm": 0.6718606352806091,
204
+ "learning_rate": 3.298780487804878e-05,
205
+ "loss": 0.0848,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 7.074074074074074,
210
+ "grad_norm": 0.3312334716320038,
211
+ "learning_rate": 3.237804878048781e-05,
212
+ "loss": 0.0607,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 7.320987654320987,
217
+ "grad_norm": 2.2608187198638916,
218
+ "learning_rate": 3.176829268292683e-05,
219
+ "loss": 0.1274,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 7.567901234567901,
224
+ "grad_norm": 0.7812129855155945,
225
+ "learning_rate": 3.115853658536586e-05,
226
+ "loss": 0.0824,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 7.814814814814815,
231
+ "grad_norm": 0.8673564195632935,
232
+ "learning_rate": 3.054878048780488e-05,
233
+ "loss": 0.1774,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 8.049382716049383,
238
+ "grad_norm": 1.7585481405258179,
239
+ "learning_rate": 2.9939024390243903e-05,
240
+ "loss": 0.1415,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 8.296296296296296,
245
+ "grad_norm": 2.8376216888427734,
246
+ "learning_rate": 2.9329268292682927e-05,
247
+ "loss": 0.1173,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 8.54320987654321,
252
+ "grad_norm": 1.6730660200119019,
253
+ "learning_rate": 2.8719512195121952e-05,
254
+ "loss": 0.1585,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 8.790123456790123,
259
+ "grad_norm": 0.30232733488082886,
260
+ "learning_rate": 2.810975609756098e-05,
261
+ "loss": 0.0377,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 9.024691358024691,
266
+ "grad_norm": 2.1726369857788086,
267
+ "learning_rate": 2.7500000000000004e-05,
268
+ "loss": 0.0568,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 9.271604938271604,
273
+ "grad_norm": 0.7406997084617615,
274
+ "learning_rate": 2.689024390243903e-05,
275
+ "loss": 0.105,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 9.518518518518519,
280
+ "grad_norm": 0.2634631097316742,
281
+ "learning_rate": 2.628048780487805e-05,
282
+ "loss": 0.0328,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 9.765432098765432,
287
+ "grad_norm": 0.15690064430236816,
288
+ "learning_rate": 2.5670731707317075e-05,
289
+ "loss": 0.069,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 10.0,
294
+ "grad_norm": 0.09763717651367188,
295
+ "learning_rate": 2.50609756097561e-05,
296
+ "loss": 0.1503,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 10.246913580246913,
301
+ "grad_norm": 0.9397181272506714,
302
+ "learning_rate": 2.4451219512195124e-05,
303
+ "loss": 0.1123,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 10.493827160493828,
308
+ "grad_norm": 0.1911344975233078,
309
+ "learning_rate": 2.3841463414634148e-05,
310
+ "loss": 0.0439,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 10.74074074074074,
315
+ "grad_norm": 2.133268117904663,
316
+ "learning_rate": 2.3231707317073173e-05,
317
+ "loss": 0.0466,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 10.987654320987655,
322
+ "grad_norm": 3.681490898132324,
323
+ "learning_rate": 2.2621951219512197e-05,
324
+ "loss": 0.083,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 11.222222222222221,
329
+ "grad_norm": 0.09520290791988373,
330
+ "learning_rate": 2.2012195121951222e-05,
331
+ "loss": 0.1275,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 11.469135802469136,
336
+ "grad_norm": 0.18467915058135986,
337
+ "learning_rate": 2.1402439024390243e-05,
338
+ "loss": 0.0206,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 11.716049382716049,
343
+ "grad_norm": 0.1692470908164978,
344
+ "learning_rate": 2.0792682926829267e-05,
345
+ "loss": 0.0694,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 11.962962962962964,
350
+ "grad_norm": 0.21938467025756836,
351
+ "learning_rate": 2.0182926829268295e-05,
352
+ "loss": 0.1137,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 12.197530864197532,
357
+ "grad_norm": 0.6872503161430359,
358
+ "learning_rate": 1.957317073170732e-05,
359
+ "loss": 0.0909,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 12.444444444444445,
364
+ "grad_norm": 0.18933941423892975,
365
+ "learning_rate": 1.896341463414634e-05,
366
+ "loss": 0.0255,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 12.691358024691358,
371
+ "grad_norm": 0.2120848298072815,
372
+ "learning_rate": 1.8353658536585365e-05,
373
+ "loss": 0.0383,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 12.938271604938272,
378
+ "grad_norm": 0.12255409359931946,
379
+ "learning_rate": 1.774390243902439e-05,
380
+ "loss": 0.0941,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 13.17283950617284,
385
+ "grad_norm": 0.10398901998996735,
386
+ "learning_rate": 1.7134146341463418e-05,
387
+ "loss": 0.0191,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 13.419753086419753,
392
+ "grad_norm": 0.31278660893440247,
393
+ "learning_rate": 1.652439024390244e-05,
394
+ "loss": 0.0281,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 13.666666666666666,
399
+ "grad_norm": 1.0805507898330688,
400
+ "learning_rate": 1.5914634146341464e-05,
401
+ "loss": 0.1726,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 13.91358024691358,
406
+ "grad_norm": 0.4380980432033539,
407
+ "learning_rate": 1.5304878048780488e-05,
408
+ "loss": 0.0186,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 14.148148148148149,
413
+ "grad_norm": 0.07801090180873871,
414
+ "learning_rate": 1.4695121951219513e-05,
415
+ "loss": 0.0473,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 14.395061728395062,
420
+ "grad_norm": 0.10922332108020782,
421
+ "learning_rate": 1.4085365853658535e-05,
422
+ "loss": 0.023,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 14.641975308641975,
427
+ "grad_norm": 0.2793682813644409,
428
+ "learning_rate": 1.3475609756097562e-05,
429
+ "loss": 0.0149,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 14.88888888888889,
434
+ "grad_norm": 1.3744605779647827,
435
+ "learning_rate": 1.2865853658536586e-05,
436
+ "loss": 0.1422,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 15.123456790123457,
441
+ "grad_norm": 0.1263941377401352,
442
+ "learning_rate": 1.225609756097561e-05,
443
+ "loss": 0.0124,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 15.37037037037037,
448
+ "grad_norm": 0.13304823637008667,
449
+ "learning_rate": 1.1646341463414635e-05,
450
+ "loss": 0.0317,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 15.617283950617283,
455
+ "grad_norm": 1.772745132446289,
456
+ "learning_rate": 1.103658536585366e-05,
457
+ "loss": 0.0443,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 15.864197530864198,
462
+ "grad_norm": 0.06537698954343796,
463
+ "learning_rate": 1.0426829268292683e-05,
464
+ "loss": 0.0918,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 16.098765432098766,
469
+ "grad_norm": 0.07521393895149231,
470
+ "learning_rate": 9.817073170731709e-06,
471
+ "loss": 0.0395,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 16.34567901234568,
476
+ "grad_norm": 0.16562214493751526,
477
+ "learning_rate": 9.207317073170732e-06,
478
+ "loss": 0.1106,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 16.59259259259259,
483
+ "grad_norm": 0.24475818872451782,
484
+ "learning_rate": 8.597560975609756e-06,
485
+ "loss": 0.019,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 16.839506172839506,
490
+ "grad_norm": 0.32736074924468994,
491
+ "learning_rate": 7.98780487804878e-06,
492
+ "loss": 0.0326,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 17.074074074074073,
497
+ "grad_norm": 0.05227570980787277,
498
+ "learning_rate": 7.378048780487805e-06,
499
+ "loss": 0.0103,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 17.320987654320987,
504
+ "grad_norm": 0.09976907074451447,
505
+ "learning_rate": 6.76829268292683e-06,
506
+ "loss": 0.0864,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 17.567901234567902,
511
+ "grad_norm": 0.04490213841199875,
512
+ "learning_rate": 6.1585365853658535e-06,
513
+ "loss": 0.0178,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 17.814814814814813,
518
+ "grad_norm": 0.11479590833187103,
519
+ "learning_rate": 5.548780487804878e-06,
520
+ "loss": 0.0236,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 18.049382716049383,
525
+ "grad_norm": 0.16496780514717102,
526
+ "learning_rate": 4.9390243902439025e-06,
527
+ "loss": 0.0481,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 18.296296296296298,
532
+ "grad_norm": 6.131174564361572,
533
+ "learning_rate": 4.329268292682927e-06,
534
+ "loss": 0.0696,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 18.54320987654321,
539
+ "grad_norm": 0.612872838973999,
540
+ "learning_rate": 3.719512195121951e-06,
541
+ "loss": 0.0194,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 18.790123456790123,
546
+ "grad_norm": 1.3853808641433716,
547
+ "learning_rate": 3.1097560975609757e-06,
548
+ "loss": 0.037,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 19.02469135802469,
553
+ "grad_norm": 0.06428851932287216,
554
+ "learning_rate": 2.5e-06,
555
+ "loss": 0.0269,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 19.271604938271604,
560
+ "grad_norm": 0.15213467180728912,
561
+ "learning_rate": 1.8902439024390245e-06,
562
+ "loss": 0.017,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 19.51851851851852,
567
+ "grad_norm": 2.0686116218566895,
568
+ "learning_rate": 1.2804878048780488e-06,
569
+ "loss": 0.088,
570
+ "step": 800
571
+ }
572
+ ],
573
+ "logging_steps": 10,
574
+ "max_steps": 820,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 20,
577
+ "save_steps": 100,
578
+ "stateful_callbacks": {
579
+ "TrainerControl": {
580
+ "args": {
581
+ "should_epoch_stop": false,
582
+ "should_evaluate": false,
583
+ "should_log": false,
584
+ "should_save": true,
585
+ "should_training_stop": false
586
+ },
587
+ "attributes": {}
588
+ }
589
+ },
590
+ "total_flos": 419770380119040.0,
591
+ "train_batch_size": 1,
592
+ "trial_name": null,
593
+ "trial_params": null
594
+ }
checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb6bb5d5091c10bfd46488b22f6c68d71402d3947521d2ca6071033c5f5dc9f
3
+ size 5240
checkpoint-800/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-820/config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LayoutLMv3ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "coordinate_size": 128,
9
+ "eos_token_id": 2,
10
+ "has_relative_attention_bias": true,
11
+ "has_spatial_attention_bias": true,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-Lab-name",
18
+ "2": "I-Lab-name",
19
+ "3": "E-Lab-name",
20
+ "4": "S-Lab-name",
21
+ "5": "B-Dr-name",
22
+ "6": "I-Dr-name",
23
+ "7": "E-Dr-name",
24
+ "8": "S-Dr-name",
25
+ "9": "B-Dr-edu",
26
+ "10": "I-Dr-edu",
27
+ "11": "E-Dr-edu",
28
+ "12": "S-Dr-edu",
29
+ "13": "B-Address",
30
+ "14": "I-Address",
31
+ "15": "E-Address",
32
+ "16": "S-Address",
33
+ "17": "B-Phone-no",
34
+ "18": "I-Phone-no",
35
+ "19": "E-Phone-no",
36
+ "20": "S-Phone-no",
37
+ "21": "B-Patitent-no",
38
+ "22": "I-Patitent-no",
39
+ "23": "E-Patitent-no",
40
+ "24": "S-Patitent-no",
41
+ "25": "B-Patient-name",
42
+ "26": "I-Patient-name",
43
+ "27": "E-Patient-name",
44
+ "28": "S-Patient-name",
45
+ "29": "B-age",
46
+ "30": "I-age",
47
+ "31": "E-age",
48
+ "32": "S-age",
49
+ "33": "B-sex",
50
+ "34": "I-sex",
51
+ "35": "E-sex",
52
+ "36": "S-sex",
53
+ "37": "B-ref-by",
54
+ "38": "I-ref-by",
55
+ "39": "E-ref-by",
56
+ "40": "S-ref-by",
57
+ "41": "B-date",
58
+ "42": "I-date",
59
+ "43": "E-date",
60
+ "44": "S-date"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "input_size": 224,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "B-Address": 13,
67
+ "B-Dr-edu": 9,
68
+ "B-Dr-name": 5,
69
+ "B-Lab-name": 1,
70
+ "B-Patient-name": 25,
71
+ "B-Patitent-no": 21,
72
+ "B-Phone-no": 17,
73
+ "B-age": 29,
74
+ "B-date": 41,
75
+ "B-ref-by": 37,
76
+ "B-sex": 33,
77
+ "E-Address": 15,
78
+ "E-Dr-edu": 11,
79
+ "E-Dr-name": 7,
80
+ "E-Lab-name": 3,
81
+ "E-Patient-name": 27,
82
+ "E-Patitent-no": 23,
83
+ "E-Phone-no": 19,
84
+ "E-age": 31,
85
+ "E-date": 43,
86
+ "E-ref-by": 39,
87
+ "E-sex": 35,
88
+ "I-Address": 14,
89
+ "I-Dr-edu": 10,
90
+ "I-Dr-name": 6,
91
+ "I-Lab-name": 2,
92
+ "I-Patient-name": 26,
93
+ "I-Patitent-no": 22,
94
+ "I-Phone-no": 18,
95
+ "I-age": 30,
96
+ "I-date": 42,
97
+ "I-ref-by": 38,
98
+ "I-sex": 34,
99
+ "O": 0,
100
+ "S-Address": 16,
101
+ "S-Dr-edu": 12,
102
+ "S-Dr-name": 8,
103
+ "S-Lab-name": 4,
104
+ "S-Patient-name": 28,
105
+ "S-Patitent-no": 24,
106
+ "S-Phone-no": 20,
107
+ "S-age": 32,
108
+ "S-date": 44,
109
+ "S-ref-by": 40,
110
+ "S-sex": 36
111
+ },
112
+ "layer_norm_eps": 1e-05,
113
+ "max_2d_position_embeddings": 1024,
114
+ "max_position_embeddings": 514,
115
+ "max_rel_2d_pos": 256,
116
+ "max_rel_pos": 128,
117
+ "model_type": "layoutlmv3",
118
+ "num_attention_heads": 12,
119
+ "num_channels": 3,
120
+ "num_hidden_layers": 12,
121
+ "pad_token_id": 1,
122
+ "patch_size": 16,
123
+ "rel_2d_pos_bins": 64,
124
+ "rel_pos_bins": 32,
125
+ "second_input_size": 112,
126
+ "shape_size": 128,
127
+ "text_embed": true,
128
+ "torch_dtype": "float32",
129
+ "transformers_version": "4.52.2",
130
+ "type_vocab_size": 1,
131
+ "visual_embed": true,
132
+ "vocab_size": 50265
133
+ }
checkpoint-820/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-820/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19099da8fd09b83c2b07cc753f31dbb5ffefdcee20499857e26c14a37eccc86
3
+ size 503835020
checkpoint-820/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868cc0cf4f7228321d7a92e98f2495e48777b4c98451450fae93f47e9142aa71
3
+ size 1007780154
checkpoint-820/preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "LayoutLMv3ImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv3Processor",
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
checkpoint-820/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3397cd40c784b7ac494ba3c75029b154d0b8c466c5e56658527f5dea4811560e
3
+ size 14244
checkpoint-820/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ba5dee8543aa07dbf5e345babd8d68ac56874dc9d7959bb1584b2a9f2f4e80
3
+ size 988
checkpoint-820/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25b56b913f9004a6ddd42919e346c128256d90056af437623ae995b1d5dd5a2
3
+ size 1064
checkpoint-820/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-820/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-820/tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "apply_ocr": false,
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": false,
48
+ "cls_token": "<s>",
49
+ "cls_token_box": [
50
+ 0,
51
+ 0,
52
+ 0,
53
+ 0
54
+ ],
55
+ "eos_token": "</s>",
56
+ "errors": "replace",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "model_max_length": 512,
60
+ "only_label_first_subword": true,
61
+ "pad_token": "<pad>",
62
+ "pad_token_box": [
63
+ 0,
64
+ 0,
65
+ 0,
66
+ 0
67
+ ],
68
+ "pad_token_label": -100,
69
+ "processor_class": "LayoutLMv3Processor",
70
+ "sep_token": "</s>",
71
+ "sep_token_box": [
72
+ 0,
73
+ 0,
74
+ 0,
75
+ 0
76
+ ],
77
+ "tokenizer_class": "LayoutLMv3Tokenizer",
78
+ "trim_offsets": true,
79
+ "unk_token": "<unk>"
80
+ }
checkpoint-820/trainer_state.json ADDED
@@ -0,0 +1,608 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 20.0,
6
+ "eval_steps": 500,
7
+ "global_step": 820,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24691358024691357,
14
+ "grad_norm": 3.9386653900146484,
15
+ "learning_rate": 4.945121951219512e-05,
16
+ "loss": 2.6292,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.49382716049382713,
21
+ "grad_norm": 2.194047451019287,
22
+ "learning_rate": 4.884146341463415e-05,
23
+ "loss": 1.7588,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7407407407407407,
28
+ "grad_norm": 3.3464252948760986,
29
+ "learning_rate": 4.823170731707317e-05,
30
+ "loss": 1.2321,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9876543209876543,
35
+ "grad_norm": 4.9754157066345215,
36
+ "learning_rate": 4.76219512195122e-05,
37
+ "loss": 1.1094,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.2222222222222223,
42
+ "grad_norm": 1.6857168674468994,
43
+ "learning_rate": 4.701219512195122e-05,
44
+ "loss": 0.8016,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.4691358024691357,
49
+ "grad_norm": 1.711855173110962,
50
+ "learning_rate": 4.640243902439025e-05,
51
+ "loss": 0.6045,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 1.7160493827160495,
56
+ "grad_norm": 3.110994338989258,
57
+ "learning_rate": 4.5792682926829275e-05,
58
+ "loss": 0.611,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.9629629629629628,
63
+ "grad_norm": 2.2832303047180176,
64
+ "learning_rate": 4.5182926829268296e-05,
65
+ "loss": 0.4029,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 2.197530864197531,
70
+ "grad_norm": 2.3041841983795166,
71
+ "learning_rate": 4.457317073170732e-05,
72
+ "loss": 0.4292,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 2.4444444444444446,
77
+ "grad_norm": 1.5648462772369385,
78
+ "learning_rate": 4.3963414634146346e-05,
79
+ "loss": 0.3602,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 2.691358024691358,
84
+ "grad_norm": 0.8374887704849243,
85
+ "learning_rate": 4.335365853658537e-05,
86
+ "loss": 0.309,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 2.9382716049382713,
91
+ "grad_norm": 0.9409658908843994,
92
+ "learning_rate": 4.2743902439024395e-05,
93
+ "loss": 0.2612,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 3.1728395061728394,
98
+ "grad_norm": 3.718695878982544,
99
+ "learning_rate": 4.2134146341463416e-05,
100
+ "loss": 0.2936,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 3.419753086419753,
105
+ "grad_norm": 3.2449347972869873,
106
+ "learning_rate": 4.152439024390244e-05,
107
+ "loss": 0.1758,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 3.6666666666666665,
112
+ "grad_norm": 1.2654057741165161,
113
+ "learning_rate": 4.0914634146341465e-05,
114
+ "loss": 0.2181,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 3.9135802469135803,
119
+ "grad_norm": 0.7008330225944519,
120
+ "learning_rate": 4.030487804878049e-05,
121
+ "loss": 0.1788,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 4.148148148148148,
126
+ "grad_norm": 0.927452802658081,
127
+ "learning_rate": 3.9695121951219514e-05,
128
+ "loss": 0.2255,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 4.395061728395062,
133
+ "grad_norm": 0.9944292902946472,
134
+ "learning_rate": 3.908536585365854e-05,
135
+ "loss": 0.2719,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 4.6419753086419755,
140
+ "grad_norm": 1.1106724739074707,
141
+ "learning_rate": 3.847560975609756e-05,
142
+ "loss": 0.1458,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 4.888888888888889,
147
+ "grad_norm": 3.588369369506836,
148
+ "learning_rate": 3.786585365853659e-05,
149
+ "loss": 0.2225,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 5.1234567901234565,
154
+ "grad_norm": 14.498685836791992,
155
+ "learning_rate": 3.725609756097561e-05,
156
+ "loss": 0.1737,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 5.37037037037037,
161
+ "grad_norm": 15.858694076538086,
162
+ "learning_rate": 3.664634146341463e-05,
163
+ "loss": 0.1728,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 5.617283950617284,
168
+ "grad_norm": 3.0714364051818848,
169
+ "learning_rate": 3.603658536585366e-05,
170
+ "loss": 0.0774,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 5.864197530864198,
175
+ "grad_norm": 0.775265634059906,
176
+ "learning_rate": 3.542682926829268e-05,
177
+ "loss": 0.2107,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 6.098765432098766,
182
+ "grad_norm": 1.262907862663269,
183
+ "learning_rate": 3.48170731707317e-05,
184
+ "loss": 0.1312,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 6.345679012345679,
189
+ "grad_norm": 0.7409253120422363,
190
+ "learning_rate": 3.420731707317074e-05,
191
+ "loss": 0.1074,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 6.592592592592593,
196
+ "grad_norm": 2.9899144172668457,
197
+ "learning_rate": 3.359756097560976e-05,
198
+ "loss": 0.2688,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 6.839506172839506,
203
+ "grad_norm": 0.6718606352806091,
204
+ "learning_rate": 3.298780487804878e-05,
205
+ "loss": 0.0848,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 7.074074074074074,
210
+ "grad_norm": 0.3312334716320038,
211
+ "learning_rate": 3.237804878048781e-05,
212
+ "loss": 0.0607,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 7.320987654320987,
217
+ "grad_norm": 2.2608187198638916,
218
+ "learning_rate": 3.176829268292683e-05,
219
+ "loss": 0.1274,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 7.567901234567901,
224
+ "grad_norm": 0.7812129855155945,
225
+ "learning_rate": 3.115853658536586e-05,
226
+ "loss": 0.0824,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 7.814814814814815,
231
+ "grad_norm": 0.8673564195632935,
232
+ "learning_rate": 3.054878048780488e-05,
233
+ "loss": 0.1774,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 8.049382716049383,
238
+ "grad_norm": 1.7585481405258179,
239
+ "learning_rate": 2.9939024390243903e-05,
240
+ "loss": 0.1415,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 8.296296296296296,
245
+ "grad_norm": 2.8376216888427734,
246
+ "learning_rate": 2.9329268292682927e-05,
247
+ "loss": 0.1173,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 8.54320987654321,
252
+ "grad_norm": 1.6730660200119019,
253
+ "learning_rate": 2.8719512195121952e-05,
254
+ "loss": 0.1585,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 8.790123456790123,
259
+ "grad_norm": 0.30232733488082886,
260
+ "learning_rate": 2.810975609756098e-05,
261
+ "loss": 0.0377,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 9.024691358024691,
266
+ "grad_norm": 2.1726369857788086,
267
+ "learning_rate": 2.7500000000000004e-05,
268
+ "loss": 0.0568,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 9.271604938271604,
273
+ "grad_norm": 0.7406997084617615,
274
+ "learning_rate": 2.689024390243903e-05,
275
+ "loss": 0.105,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 9.518518518518519,
280
+ "grad_norm": 0.2634631097316742,
281
+ "learning_rate": 2.628048780487805e-05,
282
+ "loss": 0.0328,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 9.765432098765432,
287
+ "grad_norm": 0.15690064430236816,
288
+ "learning_rate": 2.5670731707317075e-05,
289
+ "loss": 0.069,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 10.0,
294
+ "grad_norm": 0.09763717651367188,
295
+ "learning_rate": 2.50609756097561e-05,
296
+ "loss": 0.1503,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 10.246913580246913,
301
+ "grad_norm": 0.9397181272506714,
302
+ "learning_rate": 2.4451219512195124e-05,
303
+ "loss": 0.1123,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 10.493827160493828,
308
+ "grad_norm": 0.1911344975233078,
309
+ "learning_rate": 2.3841463414634148e-05,
310
+ "loss": 0.0439,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 10.74074074074074,
315
+ "grad_norm": 2.133268117904663,
316
+ "learning_rate": 2.3231707317073173e-05,
317
+ "loss": 0.0466,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 10.987654320987655,
322
+ "grad_norm": 3.681490898132324,
323
+ "learning_rate": 2.2621951219512197e-05,
324
+ "loss": 0.083,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 11.222222222222221,
329
+ "grad_norm": 0.09520290791988373,
330
+ "learning_rate": 2.2012195121951222e-05,
331
+ "loss": 0.1275,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 11.469135802469136,
336
+ "grad_norm": 0.18467915058135986,
337
+ "learning_rate": 2.1402439024390243e-05,
338
+ "loss": 0.0206,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 11.716049382716049,
343
+ "grad_norm": 0.1692470908164978,
344
+ "learning_rate": 2.0792682926829267e-05,
345
+ "loss": 0.0694,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 11.962962962962964,
350
+ "grad_norm": 0.21938467025756836,
351
+ "learning_rate": 2.0182926829268295e-05,
352
+ "loss": 0.1137,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 12.197530864197532,
357
+ "grad_norm": 0.6872503161430359,
358
+ "learning_rate": 1.957317073170732e-05,
359
+ "loss": 0.0909,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 12.444444444444445,
364
+ "grad_norm": 0.18933941423892975,
365
+ "learning_rate": 1.896341463414634e-05,
366
+ "loss": 0.0255,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 12.691358024691358,
371
+ "grad_norm": 0.2120848298072815,
372
+ "learning_rate": 1.8353658536585365e-05,
373
+ "loss": 0.0383,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 12.938271604938272,
378
+ "grad_norm": 0.12255409359931946,
379
+ "learning_rate": 1.774390243902439e-05,
380
+ "loss": 0.0941,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 13.17283950617284,
385
+ "grad_norm": 0.10398901998996735,
386
+ "learning_rate": 1.7134146341463418e-05,
387
+ "loss": 0.0191,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 13.419753086419753,
392
+ "grad_norm": 0.31278660893440247,
393
+ "learning_rate": 1.652439024390244e-05,
394
+ "loss": 0.0281,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 13.666666666666666,
399
+ "grad_norm": 1.0805507898330688,
400
+ "learning_rate": 1.5914634146341464e-05,
401
+ "loss": 0.1726,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 13.91358024691358,
406
+ "grad_norm": 0.4380980432033539,
407
+ "learning_rate": 1.5304878048780488e-05,
408
+ "loss": 0.0186,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 14.148148148148149,
413
+ "grad_norm": 0.07801090180873871,
414
+ "learning_rate": 1.4695121951219513e-05,
415
+ "loss": 0.0473,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 14.395061728395062,
420
+ "grad_norm": 0.10922332108020782,
421
+ "learning_rate": 1.4085365853658535e-05,
422
+ "loss": 0.023,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 14.641975308641975,
427
+ "grad_norm": 0.2793682813644409,
428
+ "learning_rate": 1.3475609756097562e-05,
429
+ "loss": 0.0149,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 14.88888888888889,
434
+ "grad_norm": 1.3744605779647827,
435
+ "learning_rate": 1.2865853658536586e-05,
436
+ "loss": 0.1422,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 15.123456790123457,
441
+ "grad_norm": 0.1263941377401352,
442
+ "learning_rate": 1.225609756097561e-05,
443
+ "loss": 0.0124,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 15.37037037037037,
448
+ "grad_norm": 0.13304823637008667,
449
+ "learning_rate": 1.1646341463414635e-05,
450
+ "loss": 0.0317,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 15.617283950617283,
455
+ "grad_norm": 1.772745132446289,
456
+ "learning_rate": 1.103658536585366e-05,
457
+ "loss": 0.0443,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 15.864197530864198,
462
+ "grad_norm": 0.06537698954343796,
463
+ "learning_rate": 1.0426829268292683e-05,
464
+ "loss": 0.0918,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 16.098765432098766,
469
+ "grad_norm": 0.07521393895149231,
470
+ "learning_rate": 9.817073170731709e-06,
471
+ "loss": 0.0395,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 16.34567901234568,
476
+ "grad_norm": 0.16562214493751526,
477
+ "learning_rate": 9.207317073170732e-06,
478
+ "loss": 0.1106,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 16.59259259259259,
483
+ "grad_norm": 0.24475818872451782,
484
+ "learning_rate": 8.597560975609756e-06,
485
+ "loss": 0.019,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 16.839506172839506,
490
+ "grad_norm": 0.32736074924468994,
491
+ "learning_rate": 7.98780487804878e-06,
492
+ "loss": 0.0326,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 17.074074074074073,
497
+ "grad_norm": 0.05227570980787277,
498
+ "learning_rate": 7.378048780487805e-06,
499
+ "loss": 0.0103,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 17.320987654320987,
504
+ "grad_norm": 0.09976907074451447,
505
+ "learning_rate": 6.76829268292683e-06,
506
+ "loss": 0.0864,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 17.567901234567902,
511
+ "grad_norm": 0.04490213841199875,
512
+ "learning_rate": 6.1585365853658535e-06,
513
+ "loss": 0.0178,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 17.814814814814813,
518
+ "grad_norm": 0.11479590833187103,
519
+ "learning_rate": 5.548780487804878e-06,
520
+ "loss": 0.0236,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 18.049382716049383,
525
+ "grad_norm": 0.16496780514717102,
526
+ "learning_rate": 4.9390243902439025e-06,
527
+ "loss": 0.0481,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 18.296296296296298,
532
+ "grad_norm": 6.131174564361572,
533
+ "learning_rate": 4.329268292682927e-06,
534
+ "loss": 0.0696,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 18.54320987654321,
539
+ "grad_norm": 0.612872838973999,
540
+ "learning_rate": 3.719512195121951e-06,
541
+ "loss": 0.0194,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 18.790123456790123,
546
+ "grad_norm": 1.3853808641433716,
547
+ "learning_rate": 3.1097560975609757e-06,
548
+ "loss": 0.037,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 19.02469135802469,
553
+ "grad_norm": 0.06428851932287216,
554
+ "learning_rate": 2.5e-06,
555
+ "loss": 0.0269,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 19.271604938271604,
560
+ "grad_norm": 0.15213467180728912,
561
+ "learning_rate": 1.8902439024390245e-06,
562
+ "loss": 0.017,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 19.51851851851852,
567
+ "grad_norm": 2.0686116218566895,
568
+ "learning_rate": 1.2804878048780488e-06,
569
+ "loss": 0.088,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 19.765432098765434,
574
+ "grad_norm": 0.05781777948141098,
575
+ "learning_rate": 6.707317073170731e-07,
576
+ "loss": 0.0367,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 20.0,
581
+ "grad_norm": 0.05907975882291794,
582
+ "learning_rate": 6.097560975609757e-08,
583
+ "loss": 0.0093,
584
+ "step": 820
585
+ }
586
+ ],
587
+ "logging_steps": 10,
588
+ "max_steps": 820,
589
+ "num_input_tokens_seen": 0,
590
+ "num_train_epochs": 20,
591
+ "save_steps": 100,
592
+ "stateful_callbacks": {
593
+ "TrainerControl": {
594
+ "args": {
595
+ "should_epoch_stop": false,
596
+ "should_evaluate": false,
597
+ "should_log": false,
598
+ "should_save": true,
599
+ "should_training_stop": true
600
+ },
601
+ "attributes": {}
602
+ }
603
+ },
604
+ "total_flos": 430125247180800.0,
605
+ "train_batch_size": 1,
606
+ "trial_name": null,
607
+ "trial_params": null
608
+ }
checkpoint-820/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb6bb5d5091c10bfd46488b22f6c68d71402d3947521d2ca6071033c5f5dc9f
3
+ size 5240
checkpoint-820/vocab.json ADDED
The diff for this file is too large to render. See raw diff