MuafiraThasni commited on
Commit
3ec047b
1 Parent(s): 2da2166

Training in progress, step 1400, checkpoint

Browse files
checkpoint-1400/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nielsr/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": "4.42.3",
53
+ "type_vocab_size": 1,
54
+ "use_cache": true,
55
+ "vocab_size": 250002
56
+ }
checkpoint-1400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a6c53636fb712ee688ae59da3b5b0df4bbde8aa99d9144a5bbc52f1cb2ddc9
3
+ size 1134332228
checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7f5b5dd358153bfde01daebaf8aa23c5dd15beed3d55c20f52896b81fceb11
3
+ size 2268900866
checkpoint-1400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a2e3346e541f31cbcff8cb7a83b3a5eefc030dbaf2a39bf6d695f7ca74a7d6
3
+ size 14244
checkpoint-1400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4787d79bfc133d23ef0498e036c59b9a58e1e7d74dd757b1a8e285daf6e68f08
3
+ size 1064
checkpoint-1400/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-1400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
+ size 17082734
checkpoint-1400/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-1400/trainer_state.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8767404952738379,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-700",
4
+ "epoch": 0.746268656716418,
5
+ "eval_steps": 100,
6
+ "global_step": 1400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.053304904051172705,
13
+ "eval_accuracy": 0.6321578647928374,
14
+ "eval_f1": 0.6321578647928374,
15
+ "eval_loss": 0.9594171643257141,
16
+ "eval_precision": 0.6321578647928374,
17
+ "eval_recall": 0.6321578647928374,
18
+ "eval_runtime": 69.4219,
19
+ "eval_samples_per_second": 23.148,
20
+ "eval_steps_per_second": 0.735,
21
+ "step": 100
22
+ },
23
+ {
24
+ "epoch": 0.10660980810234541,
25
+ "eval_accuracy": 0.8202860650583409,
26
+ "eval_f1": 0.8202860650583409,
27
+ "eval_loss": 0.6088714599609375,
28
+ "eval_precision": 0.8202860650583409,
29
+ "eval_recall": 0.8202860650583409,
30
+ "eval_runtime": 69.0048,
31
+ "eval_samples_per_second": 23.288,
32
+ "eval_steps_per_second": 0.739,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 0.15991471215351813,
37
+ "eval_accuracy": 0.7378602014233383,
38
+ "eval_f1": 0.7378602014233383,
39
+ "eval_loss": 0.7009087800979614,
40
+ "eval_precision": 0.7378602014233383,
41
+ "eval_recall": 0.7378602014233383,
42
+ "eval_runtime": 68.7975,
43
+ "eval_samples_per_second": 23.358,
44
+ "eval_steps_per_second": 0.741,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 0.21321961620469082,
49
+ "eval_accuracy": 0.7694710890634513,
50
+ "eval_f1": 0.7694710890634513,
51
+ "eval_loss": 0.5369378328323364,
52
+ "eval_precision": 0.7694710890634513,
53
+ "eval_recall": 0.7694710890634513,
54
+ "eval_runtime": 69.0856,
55
+ "eval_samples_per_second": 23.261,
56
+ "eval_steps_per_second": 0.738,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 0.26652452025586354,
61
+ "grad_norm": 443972.875,
62
+ "learning_rate": 1.4669509594882732e-05,
63
+ "loss": 0.7136,
64
+ "step": 500
65
+ },
66
+ {
67
+ "epoch": 0.26652452025586354,
68
+ "eval_accuracy": 0.8621777276492958,
69
+ "eval_f1": 0.8621777276492958,
70
+ "eval_loss": 0.4052257537841797,
71
+ "eval_precision": 0.8621777276492958,
72
+ "eval_recall": 0.8621777276492958,
73
+ "eval_runtime": 68.528,
74
+ "eval_samples_per_second": 23.45,
75
+ "eval_steps_per_second": 0.744,
76
+ "step": 500
77
+ },
78
+ {
79
+ "epoch": 0.31982942430703626,
80
+ "eval_accuracy": 0.8714304251050535,
81
+ "eval_f1": 0.8714304251050535,
82
+ "eval_loss": 0.40161609649658203,
83
+ "eval_precision": 0.8714304251050535,
84
+ "eval_recall": 0.8714304251050535,
85
+ "eval_runtime": 68.104,
86
+ "eval_samples_per_second": 23.596,
87
+ "eval_steps_per_second": 0.749,
88
+ "step": 600
89
+ },
90
+ {
91
+ "epoch": 0.373134328358209,
92
+ "eval_accuracy": 0.8767404952738379,
93
+ "eval_f1": 0.8767404952738379,
94
+ "eval_loss": 0.38839995861053467,
95
+ "eval_precision": 0.8767404952738379,
96
+ "eval_recall": 0.8767404952738379,
97
+ "eval_runtime": 69.1004,
98
+ "eval_samples_per_second": 23.256,
99
+ "eval_steps_per_second": 0.738,
100
+ "step": 700
101
+ },
102
+ {
103
+ "epoch": 0.42643923240938164,
104
+ "eval_accuracy": 0.866569515006937,
105
+ "eval_f1": 0.866569515006937,
106
+ "eval_loss": 0.4080258309841156,
107
+ "eval_precision": 0.866569515006937,
108
+ "eval_recall": 0.866569515006937,
109
+ "eval_runtime": 68.4146,
110
+ "eval_samples_per_second": 23.489,
111
+ "eval_steps_per_second": 0.745,
112
+ "step": 800
113
+ },
114
+ {
115
+ "epoch": 0.47974413646055436,
116
+ "eval_accuracy": 0.8303472506413008,
117
+ "eval_f1": 0.8303472506413008,
118
+ "eval_loss": 0.45843783020973206,
119
+ "eval_precision": 0.8303472506413008,
120
+ "eval_recall": 0.8303472506413008,
121
+ "eval_runtime": 68.5359,
122
+ "eval_samples_per_second": 23.448,
123
+ "eval_steps_per_second": 0.744,
124
+ "step": 900
125
+ },
126
+ {
127
+ "epoch": 0.5330490405117271,
128
+ "grad_norm": 97385.5703125,
129
+ "learning_rate": 9.339019189765458e-06,
130
+ "loss": 0.4387,
131
+ "step": 1000
132
+ },
133
+ {
134
+ "epoch": 0.5330490405117271,
135
+ "eval_accuracy": 0.7901524149839799,
136
+ "eval_f1": 0.7901524149839798,
137
+ "eval_loss": 0.525492250919342,
138
+ "eval_precision": 0.7901524149839799,
139
+ "eval_recall": 0.7901524149839799,
140
+ "eval_runtime": 69.1745,
141
+ "eval_samples_per_second": 23.231,
142
+ "eval_steps_per_second": 0.737,
143
+ "step": 1000
144
+ },
145
+ {
146
+ "epoch": 0.5863539445628998,
147
+ "eval_accuracy": 0.8467964905626478,
148
+ "eval_f1": 0.8467964905626478,
149
+ "eval_loss": 0.43574053049087524,
150
+ "eval_precision": 0.8467964905626478,
151
+ "eval_recall": 0.8467964905626478,
152
+ "eval_runtime": 68.6889,
153
+ "eval_samples_per_second": 23.395,
154
+ "eval_steps_per_second": 0.742,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.6396588486140725,
159
+ "eval_accuracy": 0.8247676844301157,
160
+ "eval_f1": 0.8247676844301157,
161
+ "eval_loss": 0.434725821018219,
162
+ "eval_precision": 0.8247676844301157,
163
+ "eval_recall": 0.8247676844301157,
164
+ "eval_runtime": 68.391,
165
+ "eval_samples_per_second": 23.497,
166
+ "eval_steps_per_second": 0.746,
167
+ "step": 1200
168
+ },
169
+ {
170
+ "epoch": 0.6929637526652452,
171
+ "eval_accuracy": 0.8064120095421562,
172
+ "eval_f1": 0.8064120095421562,
173
+ "eval_loss": 0.48625513911247253,
174
+ "eval_precision": 0.8064120095421562,
175
+ "eval_recall": 0.8064120095421562,
176
+ "eval_runtime": 69.3358,
177
+ "eval_samples_per_second": 23.177,
178
+ "eval_steps_per_second": 0.736,
179
+ "step": 1300
180
+ },
181
+ {
182
+ "epoch": 0.746268656716418,
183
+ "eval_accuracy": 0.8167426911675167,
184
+ "eval_f1": 0.8167426911675167,
185
+ "eval_loss": 0.4896146357059479,
186
+ "eval_precision": 0.8167426911675167,
187
+ "eval_recall": 0.8167426911675167,
188
+ "eval_runtime": 68.8901,
189
+ "eval_samples_per_second": 23.327,
190
+ "eval_steps_per_second": 0.74,
191
+ "step": 1400
192
+ }
193
+ ],
194
+ "logging_steps": 500,
195
+ "max_steps": 1876,
196
+ "num_input_tokens_seen": 0,
197
+ "num_train_epochs": 1,
198
+ "save_steps": 100,
199
+ "stateful_callbacks": {
200
+ "TrainerControl": {
201
+ "args": {
202
+ "should_epoch_stop": false,
203
+ "should_evaluate": false,
204
+ "should_log": false,
205
+ "should_save": true,
206
+ "should_training_stop": false
207
+ },
208
+ "attributes": {}
209
+ }
210
+ },
211
+ "total_flos": 3115529075097600.0,
212
+ "train_batch_size": 16,
213
+ "trial_name": null,
214
+ "trial_params": null
215
+ }
checkpoint-1400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2544ef83614d223e3dbe1cbe496bce99a66932dd46abc19142f548bbc4c106c4
3
+ size 5304