Training in progress, step 1200, checkpoint
Browse files- checkpoint-1200/config.json +56 -0
- checkpoint-1200/model.safetensors +3 -0
- checkpoint-1200/optimizer.pt +3 -0
- checkpoint-1200/rng_state.pth +3 -0
- checkpoint-1200/scheduler.pt +3 -0
- checkpoint-1200/special_tokens_map.json +51 -0
- checkpoint-1200/tokenizer.json +3 -0
- checkpoint-1200/tokenizer_config.json +54 -0
- checkpoint-1200/trainer_state.json +175 -0
- checkpoint-1200/training_args.bin +3 -0
checkpoint-1200/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "zwaarcontrast/lilt-xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"LiltForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"channel_shrink_ratio": 4,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "Caption",
|
16 |
+
"1": "Footnote",
|
17 |
+
"2": "Formula",
|
18 |
+
"3": "List-item",
|
19 |
+
"4": "Page-footer",
|
20 |
+
"5": "Page-header",
|
21 |
+
"6": "Picture",
|
22 |
+
"7": "Section-header",
|
23 |
+
"8": "Table",
|
24 |
+
"9": "Text",
|
25 |
+
"10": "Title"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"Caption": 0,
|
31 |
+
"Footnote": 1,
|
32 |
+
"Formula": 2,
|
33 |
+
"List-item": 3,
|
34 |
+
"Page-footer": 4,
|
35 |
+
"Page-header": 5,
|
36 |
+
"Picture": 6,
|
37 |
+
"Section-header": 7,
|
38 |
+
"Table": 8,
|
39 |
+
"Text": 9,
|
40 |
+
"Title": 10
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-05,
|
43 |
+
"max_2d_position_embeddings": 1024,
|
44 |
+
"max_position_embeddings": 514,
|
45 |
+
"model_type": "lilt",
|
46 |
+
"num_attention_heads": 12,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"output_past": true,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"position_embedding_type": "absolute",
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.35.0",
|
53 |
+
"type_vocab_size": 1,
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 250002
|
56 |
+
}
|
checkpoint-1200/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43c8c07dc553ac72d5b7105271681a2cbaf456f1c043c04ddbc992f45f94b35c
|
3 |
+
size 1134332228
|
checkpoint-1200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a755ce56edf292a62a2fe3a6eda539f54605f0741abce952133d7d67eed20c88
|
3 |
+
size 2265914014
|
checkpoint-1200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e738280f72446e89aa0edc24935b396a080fe9029ab8d3bd3a05ba02b2a11d17
|
3 |
+
size 13990
|
checkpoint-1200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b465eaa3a7f610674d0cbabdaa229633b011df3e3aca7f33910cab22578b2273
|
3 |
+
size 1064
|
checkpoint-1200/special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
checkpoint-1200/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41d744d03ec3af69401e720d3867d9f13d4211c73a66a7d43d194d9ea218a4af
|
3 |
+
size 17082955
|
checkpoint-1200/tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
checkpoint-1200/trainer_state.json
ADDED
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.827712178226716,
|
3 |
+
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-500",
|
4 |
+
"epoch": 0.6396588486140725,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"eval_accuracy": 0.687484404164213,
|
14 |
+
"eval_f1": 0.687484404164213,
|
15 |
+
"eval_loss": 0.11619879305362701,
|
16 |
+
"eval_precision": 0.687484404164213,
|
17 |
+
"eval_recall": 0.687484404164213,
|
18 |
+
"eval_runtime": 114.5058,
|
19 |
+
"eval_samples_per_second": 14.034,
|
20 |
+
"eval_steps_per_second": 0.882,
|
21 |
+
"step": 100
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.11,
|
25 |
+
"eval_accuracy": 0.6755467276193519,
|
26 |
+
"eval_f1": 0.6755467276193519,
|
27 |
+
"eval_loss": 0.1096724346280098,
|
28 |
+
"eval_precision": 0.6755467276193519,
|
29 |
+
"eval_recall": 0.6755467276193519,
|
30 |
+
"eval_runtime": 97.2211,
|
31 |
+
"eval_samples_per_second": 16.529,
|
32 |
+
"eval_steps_per_second": 1.039,
|
33 |
+
"step": 200
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.16,
|
37 |
+
"eval_accuracy": 0.7780849810853704,
|
38 |
+
"eval_f1": 0.7780849810853703,
|
39 |
+
"eval_loss": 0.08659958839416504,
|
40 |
+
"eval_precision": 0.7780849810853704,
|
41 |
+
"eval_recall": 0.7780849810853704,
|
42 |
+
"eval_runtime": 98.762,
|
43 |
+
"eval_samples_per_second": 16.271,
|
44 |
+
"eval_steps_per_second": 1.023,
|
45 |
+
"step": 300
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.21,
|
49 |
+
"eval_accuracy": 0.7477716669827422,
|
50 |
+
"eval_f1": 0.7477716669827422,
|
51 |
+
"eval_loss": 0.10182594507932663,
|
52 |
+
"eval_precision": 0.7477716669827422,
|
53 |
+
"eval_recall": 0.7477716669827422,
|
54 |
+
"eval_runtime": 99.9428,
|
55 |
+
"eval_samples_per_second": 16.079,
|
56 |
+
"eval_steps_per_second": 1.011,
|
57 |
+
"step": 400
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.27,
|
61 |
+
"learning_rate": 1.4669509594882732e-05,
|
62 |
+
"loss": 0.0975,
|
63 |
+
"step": 500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.27,
|
67 |
+
"eval_accuracy": 0.827712178226716,
|
68 |
+
"eval_f1": 0.827712178226716,
|
69 |
+
"eval_loss": 0.06453556567430496,
|
70 |
+
"eval_precision": 0.827712178226716,
|
71 |
+
"eval_recall": 0.827712178226716,
|
72 |
+
"eval_runtime": 100.1167,
|
73 |
+
"eval_samples_per_second": 16.051,
|
74 |
+
"eval_steps_per_second": 1.009,
|
75 |
+
"step": 500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.32,
|
79 |
+
"eval_accuracy": 0.7984968109634982,
|
80 |
+
"eval_f1": 0.7984968109634982,
|
81 |
+
"eval_loss": 0.07669692486524582,
|
82 |
+
"eval_precision": 0.7984968109634982,
|
83 |
+
"eval_recall": 0.7984968109634982,
|
84 |
+
"eval_runtime": 101.2405,
|
85 |
+
"eval_samples_per_second": 15.873,
|
86 |
+
"eval_steps_per_second": 0.998,
|
87 |
+
"step": 600
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.37,
|
91 |
+
"eval_accuracy": 0.7903320790122471,
|
92 |
+
"eval_f1": 0.7903320790122471,
|
93 |
+
"eval_loss": 0.07575991004705429,
|
94 |
+
"eval_precision": 0.7903320790122471,
|
95 |
+
"eval_recall": 0.7903320790122471,
|
96 |
+
"eval_runtime": 99.3914,
|
97 |
+
"eval_samples_per_second": 16.168,
|
98 |
+
"eval_steps_per_second": 1.016,
|
99 |
+
"step": 700
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.43,
|
103 |
+
"eval_accuracy": 0.7865491530837334,
|
104 |
+
"eval_f1": 0.7865491530837335,
|
105 |
+
"eval_loss": 0.08622009307146072,
|
106 |
+
"eval_precision": 0.7865491530837334,
|
107 |
+
"eval_recall": 0.7865491530837334,
|
108 |
+
"eval_runtime": 102.0728,
|
109 |
+
"eval_samples_per_second": 15.744,
|
110 |
+
"eval_steps_per_second": 0.989,
|
111 |
+
"step": 800
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.48,
|
115 |
+
"eval_accuracy": 0.6891712497629433,
|
116 |
+
"eval_f1": 0.6891712497629433,
|
117 |
+
"eval_loss": 0.12430301308631897,
|
118 |
+
"eval_precision": 0.6891712497629433,
|
119 |
+
"eval_recall": 0.6891712497629433,
|
120 |
+
"eval_runtime": 101.8092,
|
121 |
+
"eval_samples_per_second": 15.784,
|
122 |
+
"eval_steps_per_second": 0.992,
|
123 |
+
"step": 900
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.53,
|
127 |
+
"learning_rate": 9.339019189765458e-06,
|
128 |
+
"loss": 0.1389,
|
129 |
+
"step": 1000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.53,
|
133 |
+
"eval_accuracy": 0.8255961352271253,
|
134 |
+
"eval_f1": 0.8255961352271252,
|
135 |
+
"eval_loss": 0.07946911454200745,
|
136 |
+
"eval_precision": 0.8255961352271253,
|
137 |
+
"eval_recall": 0.8255961352271253,
|
138 |
+
"eval_runtime": 101.762,
|
139 |
+
"eval_samples_per_second": 15.792,
|
140 |
+
"eval_steps_per_second": 0.993,
|
141 |
+
"step": 1000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.59,
|
145 |
+
"eval_accuracy": 0.470200724644914,
|
146 |
+
"eval_f1": 0.470200724644914,
|
147 |
+
"eval_loss": 0.1683182567358017,
|
148 |
+
"eval_precision": 0.470200724644914,
|
149 |
+
"eval_recall": 0.470200724644914,
|
150 |
+
"eval_runtime": 100.8271,
|
151 |
+
"eval_samples_per_second": 15.938,
|
152 |
+
"eval_steps_per_second": 1.002,
|
153 |
+
"step": 1100
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.64,
|
157 |
+
"eval_accuracy": 0.6635990697395869,
|
158 |
+
"eval_f1": 0.6635990697395869,
|
159 |
+
"eval_loss": 0.12526559829711914,
|
160 |
+
"eval_precision": 0.6635990697395869,
|
161 |
+
"eval_recall": 0.6635990697395869,
|
162 |
+
"eval_runtime": 98.9873,
|
163 |
+
"eval_samples_per_second": 16.234,
|
164 |
+
"eval_steps_per_second": 1.02,
|
165 |
+
"step": 1200
|
166 |
+
}
|
167 |
+
],
|
168 |
+
"logging_steps": 500,
|
169 |
+
"max_steps": 1876,
|
170 |
+
"num_train_epochs": 1,
|
171 |
+
"save_steps": 100,
|
172 |
+
"total_flos": 2670453492940800.0,
|
173 |
+
"trial_name": null,
|
174 |
+
"trial_params": null
|
175 |
+
}
|
checkpoint-1200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81b0d2133f50cb264ebc324905cfe0c128a8af522d0c9dae9836e41dc0a2d2c3
|
3 |
+
size 4792
|