gowitheflow-1998 commited on
Commit
ed73917
1 Parent(s): 1d329bf
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* 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
 
 
 
 
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
36
+ 763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 filter=lfs diff=lfs merge=lfs -text
37
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
38
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
3
+ size 15645492
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - allnli
6
+ model-index:
7
+ - name: 00-allnli-p9-allnli-p9-allnli-p9-allnli-old-best
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # 00-allnli-p9-allnli-p9-allnli-p9-allnli-old-best
15
+
16
+ This model is a fine-tuned version of [00-p9-allnli-p9-allnli-p9-allnli-old-best/checkpoint-26000](https://huggingface.co/00-p9-allnli-p9-allnli-p9-allnli-old-best/checkpoint-26000) on the ALLNLI dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 3e-05
36
+ - train_batch_size: 128
37
+ - eval_batch_size: 16
38
+ - seed: 1
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_steps: 200
42
+ - training_steps: 2600
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.17.0
51
+ - Pytorch 1.11.0
52
+ - Datasets 2.14.6
53
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.06,
3
+ "train_loss": 0.12790855224315936,
4
+ "train_runtime": 1337.6408,
5
+ "train_samples": 314315,
6
+ "train_samples_per_second": 248.796,
7
+ "train_steps_per_second": 1.944
8
+ }
checkpoint-2600/763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
3
+ size 15645492
checkpoint-2600/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "00-p9-allnli-p9-allnli-p9-allnli-old-best/checkpoint-26000",
3
+ "architectures": [
4
+ "PIXELForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "decoder_hidden_size": 512,
8
+ "decoder_intermediate_size": 2048,
9
+ "decoder_num_attention_heads": 16,
10
+ "decoder_num_hidden_layers": 8,
11
+ "finetuning_task": "allnli",
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "Entailment",
17
+ "1": "Neutral",
18
+ "2": "Contradiction"
19
+ },
20
+ "image_size": [
21
+ 16,
22
+ 1024
23
+ ],
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "interpolate_pos_encoding": false,
27
+ "label2id": {
28
+ "Contradiction": 2,
29
+ "Entailment": 0,
30
+ "Neutral": 1
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "mask_ratio": 0.25,
34
+ "model_type": "pixel",
35
+ "norm_pix_loss": true,
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "qkv_bias": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.17.0"
43
+ }
checkpoint-2600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e90b244bf52ef6c60b7507458d77609c1d26b529bbd9311c7668743b60cb3dde
3
+ size 690432409
checkpoint-2600/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10404bb3d32713a43d20fdc2cac18e4c93c76fdd1de9d82cb4a67a98afb037f2
3
+ size 345238445
checkpoint-2600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccfed887d012085e4cd957888c435f79fcb70a4adcf82aaa693f934182002099
3
+ size 14503
checkpoint-2600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edd626b2966941bd24f4f737c0c5a0d7217527566ad36807e91288fc8bf3f416
3
+ size 623
checkpoint-2600/text_renderer_config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": "white",
3
+ "dpi": 120,
4
+ "font_color": "black",
5
+ "font_file": "763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
6
+ "font_size": 8,
7
+ "fonts_list": [
8
+ "Abyssinica SIL",
9
+ "Ani",
10
+ "AnjaliOldLipi",
11
+ "C059",
12
+ "Chandas",
13
+ "Chilanka",
14
+ "D050000L",
15
+ "DejaVu Math TeX Gyre",
16
+ "DejaVu Sans",
17
+ "DejaVu Sans Mono",
18
+ "DejaVu Serif",
19
+ "Dhurjati",
20
+ "Droid Sans Fallback",
21
+ "Dyuthi",
22
+ "FreeMono",
23
+ "FreeSans",
24
+ "FreeSerif",
25
+ "Gargi",
26
+ "Garuda",
27
+ "Gayathri",
28
+ "Gidugu",
29
+ "Go Noto Current",
30
+ "Gubbi",
31
+ "Gurajada",
32
+ "Inconsolata",
33
+ "Jamrul",
34
+ "KacstArt",
35
+ "KacstBook",
36
+ "KacstDecorative",
37
+ "KacstDigital",
38
+ "KacstFarsi",
39
+ "KacstLetter",
40
+ "KacstNaskh",
41
+ "KacstOffice",
42
+ "KacstOne",
43
+ "KacstPen",
44
+ "KacstPoster",
45
+ "KacstQurn",
46
+ "KacstScreen",
47
+ "KacstTitle",
48
+ "KacstTitleL",
49
+ "Kalapi",
50
+ "Kalimati",
51
+ "Karumbi",
52
+ "Keraleeyam",
53
+ "Khmer OS",
54
+ "Khmer OS System",
55
+ "Kinnari",
56
+ "LKLUG",
57
+ "LakkiReddy",
58
+ "Laksaman",
59
+ "Liberation Mono",
60
+ "Liberation Sans",
61
+ "Liberation Sans Narrow",
62
+ "Liberation Serif",
63
+ "Likhan",
64
+ "Lohit Assamese",
65
+ "Lohit Bengali",
66
+ "Lohit Devanagari",
67
+ "Lohit Gujarati",
68
+ "Lohit Gurmukhi",
69
+ "Lohit Kannada",
70
+ "Lohit Malayalam",
71
+ "Lohit Odia",
72
+ "Lohit Tamil",
73
+ "Lohit Tamil Classical",
74
+ "Lohit Telugu",
75
+ "Loma",
76
+ "Mallanna",
77
+ "Mandali",
78
+ "Manjari",
79
+ "Meera",
80
+ "Mitra Mono",
81
+ "Monospace",
82
+ "Mukti Narrow",
83
+ "NATS",
84
+ "NTR",
85
+ "Nakula",
86
+ "Navilu",
87
+ "Nimbus Mono PS",
88
+ "Nimbus Roman",
89
+ "Nimbus Sans",
90
+ "Nimbus Sans Narrow",
91
+ "Norasi",
92
+ "Noto Color Emoji",
93
+ "Noto Mono",
94
+ "Noto Sans CJK HK",
95
+ "Noto Sans CJK JP",
96
+ "Noto Sans CJK KR",
97
+ "Noto Sans CJK SC",
98
+ "Noto Sans CJK TC",
99
+ "Noto Sans Mono",
100
+ "Noto Sans Mono CJK HK",
101
+ "Noto Sans Mono CJK JP",
102
+ "Noto Sans Mono CJK KR",
103
+ "Noto Sans Mono CJK SC",
104
+ "Noto Sans Mono CJK TC",
105
+ "Noto Serif CJK JP",
106
+ "Noto Serif CJK KR",
107
+ "Noto Serif CJK SC",
108
+ "Noto Serif CJK TC",
109
+ "OpenSymbol",
110
+ "P052",
111
+ "Padauk",
112
+ "Padauk Book",
113
+ "Pagul",
114
+ "Peddana",
115
+ "Phetsarath OT",
116
+ "Ponnala",
117
+ "Pothana2000",
118
+ "Potti Sreeramulu",
119
+ "Purisa",
120
+ "Rachana",
121
+ "RaghuMalayalamSans",
122
+ "Ramabhadra",
123
+ "Ramaraja",
124
+ "Rasa",
125
+ "RaviPrakash",
126
+ "Rekha",
127
+ "Saab",
128
+ "Sahadeva",
129
+ "Samanata",
130
+ "Samyak Devanagari",
131
+ "Samyak Gujarati",
132
+ "Samyak Malayalam",
133
+ "Samyak Tamil",
134
+ "Sans",
135
+ "Sarai",
136
+ "Sawasdee",
137
+ "Serif",
138
+ "Source Code Pro",
139
+ "Sree Krushnadevaraya",
140
+ "Standard Symbols PS",
141
+ "Suranna",
142
+ "Suravaram",
143
+ "Suruma",
144
+ "Syamala Ramana",
145
+ "System-ui",
146
+ "TenaliRamakrishna",
147
+ "Tibetan Machine Uni",
148
+ "Timmana",
149
+ "Tlwg Mono",
150
+ "Tlwg Typewriter",
151
+ "Tlwg Typist",
152
+ "Tlwg Typo",
153
+ "URW Bookman",
154
+ "URW Gothic",
155
+ "Ubuntu",
156
+ "Ubuntu Condensed",
157
+ "Ubuntu Mono",
158
+ "Umpush",
159
+ "Uroob",
160
+ "Vemana2000",
161
+ "Waree",
162
+ "Yrsa",
163
+ "Z003",
164
+ "aakar",
165
+ "mry_KacstQurn",
166
+ "ori1Uni",
167
+ "padmaa",
168
+ "padmaa-Bold.1.1"
169
+ ],
170
+ "max_seq_length": 64,
171
+ "pad_size": 3,
172
+ "pixels_per_patch": 16,
173
+ "rgb": false,
174
+ "text_renderer_type": "PangoCairoTextRenderer"
175
+ }
checkpoint-2600/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7974429202242631,
3
+ "best_model_checkpoint": "00-allnli-p9-allnli-p9-allnli-p9-allnli-old-best/checkpoint-2600",
4
+ "epoch": 1.0586319218241043,
5
+ "global_step": 2600,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 3e-05,
13
+ "loss": 0.129,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 2.75e-05,
19
+ "loss": 0.0665,
20
+ "step": 400
21
+ },
22
+ {
23
+ "epoch": 0.24,
24
+ "learning_rate": 2.5e-05,
25
+ "loss": 0.0754,
26
+ "step": 600
27
+ },
28
+ {
29
+ "epoch": 0.33,
30
+ "learning_rate": 2.25e-05,
31
+ "loss": 0.0806,
32
+ "step": 800
33
+ },
34
+ {
35
+ "epoch": 0.41,
36
+ "learning_rate": 1.9999999999999998e-05,
37
+ "loss": 0.0895,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 0.49,
42
+ "learning_rate": 1.7500000000000002e-05,
43
+ "loss": 0.0959,
44
+ "step": 1200
45
+ },
46
+ {
47
+ "epoch": 0.57,
48
+ "learning_rate": 1.5e-05,
49
+ "loss": 0.1116,
50
+ "step": 1400
51
+ },
52
+ {
53
+ "epoch": 0.65,
54
+ "learning_rate": 1.25e-05,
55
+ "loss": 0.1274,
56
+ "step": 1600
57
+ },
58
+ {
59
+ "epoch": 0.73,
60
+ "learning_rate": 9.999999999999999e-06,
61
+ "loss": 0.1436,
62
+ "step": 1800
63
+ },
64
+ {
65
+ "epoch": 0.81,
66
+ "learning_rate": 7.5e-06,
67
+ "loss": 0.1621,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 0.9,
72
+ "learning_rate": 4.9999999999999996e-06,
73
+ "loss": 0.1891,
74
+ "step": 2200
75
+ },
76
+ {
77
+ "epoch": 0.98,
78
+ "learning_rate": 2.4999999999999998e-06,
79
+ "loss": 0.2067,
80
+ "step": 2400
81
+ },
82
+ {
83
+ "epoch": 1.06,
84
+ "learning_rate": 0.0,
85
+ "loss": 0.1854,
86
+ "step": 2600
87
+ }
88
+ ],
89
+ "max_steps": 2600,
90
+ "num_train_epochs": 2,
91
+ "total_flos": 172275249862656.0,
92
+ "trial_name": null,
93
+ "trial_params": null
94
+ }
checkpoint-2600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3819c49352298be9c93a53aa22a51dcb1078d6e39a93e96a3cb9c6d9979fd6
3
+ size 3183
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "00-p9-allnli-p9-allnli-p9-allnli-old-best/checkpoint-26000",
3
+ "architectures": [
4
+ "PIXELForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "decoder_hidden_size": 512,
8
+ "decoder_intermediate_size": 2048,
9
+ "decoder_num_attention_heads": 16,
10
+ "decoder_num_hidden_layers": 8,
11
+ "finetuning_task": "allnli",
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "Entailment",
17
+ "1": "Neutral",
18
+ "2": "Contradiction"
19
+ },
20
+ "image_size": [
21
+ 16,
22
+ 1024
23
+ ],
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "interpolate_pos_encoding": false,
27
+ "label2id": {
28
+ "Contradiction": 2,
29
+ "Entailment": 0,
30
+ "Neutral": 1
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "mask_ratio": 0.25,
34
+ "model_type": "pixel",
35
+ "norm_pix_loss": true,
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "qkv_bias": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.17.0"
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10404bb3d32713a43d20fdc2cac18e4c93c76fdd1de9d82cb4a67a98afb037f2
3
+ size 345238445
text_renderer_config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": "white",
3
+ "dpi": 120,
4
+ "font_color": "black",
5
+ "font_file": "763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
6
+ "font_size": 8,
7
+ "fonts_list": [
8
+ "Abyssinica SIL",
9
+ "Ani",
10
+ "AnjaliOldLipi",
11
+ "C059",
12
+ "Chandas",
13
+ "Chilanka",
14
+ "D050000L",
15
+ "DejaVu Math TeX Gyre",
16
+ "DejaVu Sans",
17
+ "DejaVu Sans Mono",
18
+ "DejaVu Serif",
19
+ "Dhurjati",
20
+ "Droid Sans Fallback",
21
+ "Dyuthi",
22
+ "FreeMono",
23
+ "FreeSans",
24
+ "FreeSerif",
25
+ "Gargi",
26
+ "Garuda",
27
+ "Gayathri",
28
+ "Gidugu",
29
+ "Go Noto Current",
30
+ "Gubbi",
31
+ "Gurajada",
32
+ "Inconsolata",
33
+ "Jamrul",
34
+ "KacstArt",
35
+ "KacstBook",
36
+ "KacstDecorative",
37
+ "KacstDigital",
38
+ "KacstFarsi",
39
+ "KacstLetter",
40
+ "KacstNaskh",
41
+ "KacstOffice",
42
+ "KacstOne",
43
+ "KacstPen",
44
+ "KacstPoster",
45
+ "KacstQurn",
46
+ "KacstScreen",
47
+ "KacstTitle",
48
+ "KacstTitleL",
49
+ "Kalapi",
50
+ "Kalimati",
51
+ "Karumbi",
52
+ "Keraleeyam",
53
+ "Khmer OS",
54
+ "Khmer OS System",
55
+ "Kinnari",
56
+ "LKLUG",
57
+ "LakkiReddy",
58
+ "Laksaman",
59
+ "Liberation Mono",
60
+ "Liberation Sans",
61
+ "Liberation Sans Narrow",
62
+ "Liberation Serif",
63
+ "Likhan",
64
+ "Lohit Assamese",
65
+ "Lohit Bengali",
66
+ "Lohit Devanagari",
67
+ "Lohit Gujarati",
68
+ "Lohit Gurmukhi",
69
+ "Lohit Kannada",
70
+ "Lohit Malayalam",
71
+ "Lohit Odia",
72
+ "Lohit Tamil",
73
+ "Lohit Tamil Classical",
74
+ "Lohit Telugu",
75
+ "Loma",
76
+ "Mallanna",
77
+ "Mandali",
78
+ "Manjari",
79
+ "Meera",
80
+ "Mitra Mono",
81
+ "Monospace",
82
+ "Mukti Narrow",
83
+ "NATS",
84
+ "NTR",
85
+ "Nakula",
86
+ "Navilu",
87
+ "Nimbus Mono PS",
88
+ "Nimbus Roman",
89
+ "Nimbus Sans",
90
+ "Nimbus Sans Narrow",
91
+ "Norasi",
92
+ "Noto Color Emoji",
93
+ "Noto Mono",
94
+ "Noto Sans CJK HK",
95
+ "Noto Sans CJK JP",
96
+ "Noto Sans CJK KR",
97
+ "Noto Sans CJK SC",
98
+ "Noto Sans CJK TC",
99
+ "Noto Sans Mono",
100
+ "Noto Sans Mono CJK HK",
101
+ "Noto Sans Mono CJK JP",
102
+ "Noto Sans Mono CJK KR",
103
+ "Noto Sans Mono CJK SC",
104
+ "Noto Sans Mono CJK TC",
105
+ "Noto Serif CJK JP",
106
+ "Noto Serif CJK KR",
107
+ "Noto Serif CJK SC",
108
+ "Noto Serif CJK TC",
109
+ "OpenSymbol",
110
+ "P052",
111
+ "Padauk",
112
+ "Padauk Book",
113
+ "Pagul",
114
+ "Peddana",
115
+ "Phetsarath OT",
116
+ "Ponnala",
117
+ "Pothana2000",
118
+ "Potti Sreeramulu",
119
+ "Purisa",
120
+ "Rachana",
121
+ "RaghuMalayalamSans",
122
+ "Ramabhadra",
123
+ "Ramaraja",
124
+ "Rasa",
125
+ "RaviPrakash",
126
+ "Rekha",
127
+ "Saab",
128
+ "Sahadeva",
129
+ "Samanata",
130
+ "Samyak Devanagari",
131
+ "Samyak Gujarati",
132
+ "Samyak Malayalam",
133
+ "Samyak Tamil",
134
+ "Sans",
135
+ "Sarai",
136
+ "Sawasdee",
137
+ "Serif",
138
+ "Source Code Pro",
139
+ "Sree Krushnadevaraya",
140
+ "Standard Symbols PS",
141
+ "Suranna",
142
+ "Suravaram",
143
+ "Suruma",
144
+ "Syamala Ramana",
145
+ "System-ui",
146
+ "TenaliRamakrishna",
147
+ "Tibetan Machine Uni",
148
+ "Timmana",
149
+ "Tlwg Mono",
150
+ "Tlwg Typewriter",
151
+ "Tlwg Typist",
152
+ "Tlwg Typo",
153
+ "URW Bookman",
154
+ "URW Gothic",
155
+ "Ubuntu",
156
+ "Ubuntu Condensed",
157
+ "Ubuntu Mono",
158
+ "Umpush",
159
+ "Uroob",
160
+ "Vemana2000",
161
+ "Waree",
162
+ "Yrsa",
163
+ "Z003",
164
+ "aakar",
165
+ "mry_KacstQurn",
166
+ "ori1Uni",
167
+ "padmaa",
168
+ "padmaa-Bold.1.1"
169
+ ],
170
+ "max_seq_length": 64,
171
+ "pad_size": 3,
172
+ "pixels_per_patch": 16,
173
+ "rgb": false,
174
+ "text_renderer_type": "PangoCairoTextRenderer"
175
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.06,
3
+ "train_loss": 0.12790855224315936,
4
+ "train_runtime": 1337.6408,
5
+ "train_samples": 314315,
6
+ "train_samples_per_second": 248.796,
7
+ "train_steps_per_second": 1.944
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7974429202242631,
3
+ "best_model_checkpoint": "00-allnli-p9-allnli-p9-allnli-p9-allnli-old-best/checkpoint-2600",
4
+ "epoch": 1.0586319218241043,
5
+ "global_step": 2600,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 3e-05,
13
+ "loss": 0.129,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 2.75e-05,
19
+ "loss": 0.0665,
20
+ "step": 400
21
+ },
22
+ {
23
+ "epoch": 0.24,
24
+ "learning_rate": 2.5e-05,
25
+ "loss": 0.0754,
26
+ "step": 600
27
+ },
28
+ {
29
+ "epoch": 0.33,
30
+ "learning_rate": 2.25e-05,
31
+ "loss": 0.0806,
32
+ "step": 800
33
+ },
34
+ {
35
+ "epoch": 0.41,
36
+ "learning_rate": 1.9999999999999998e-05,
37
+ "loss": 0.0895,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 0.49,
42
+ "learning_rate": 1.7500000000000002e-05,
43
+ "loss": 0.0959,
44
+ "step": 1200
45
+ },
46
+ {
47
+ "epoch": 0.57,
48
+ "learning_rate": 1.5e-05,
49
+ "loss": 0.1116,
50
+ "step": 1400
51
+ },
52
+ {
53
+ "epoch": 0.65,
54
+ "learning_rate": 1.25e-05,
55
+ "loss": 0.1274,
56
+ "step": 1600
57
+ },
58
+ {
59
+ "epoch": 0.73,
60
+ "learning_rate": 9.999999999999999e-06,
61
+ "loss": 0.1436,
62
+ "step": 1800
63
+ },
64
+ {
65
+ "epoch": 0.81,
66
+ "learning_rate": 7.5e-06,
67
+ "loss": 0.1621,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 0.9,
72
+ "learning_rate": 4.9999999999999996e-06,
73
+ "loss": 0.1891,
74
+ "step": 2200
75
+ },
76
+ {
77
+ "epoch": 0.98,
78
+ "learning_rate": 2.4999999999999998e-06,
79
+ "loss": 0.2067,
80
+ "step": 2400
81
+ },
82
+ {
83
+ "epoch": 1.06,
84
+ "learning_rate": 0.0,
85
+ "loss": 0.1854,
86
+ "step": 2600
87
+ },
88
+ {
89
+ "epoch": 1.06,
90
+ "step": 2600,
91
+ "total_flos": 172275249862656.0,
92
+ "train_loss": 0.12790855224315936,
93
+ "train_runtime": 1337.6408,
94
+ "train_samples_per_second": 248.796,
95
+ "train_steps_per_second": 1.944
96
+ }
97
+ ],
98
+ "max_steps": 2600,
99
+ "num_train_epochs": 2,
100
+ "total_flos": 172275249862656.0,
101
+ "trial_name": null,
102
+ "trial_params": null
103
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3819c49352298be9c93a53aa22a51dcb1078d6e39a93e96a3cb9c6d9979fd6
3
+ size 3183