hongS commited on
Commit
cde2e30
1 Parent(s): de10912

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./donut_swinv2_bart_seed_0_6",
4
+ "architectures": [
5
+ "VisionEncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "",
9
+ "activation_dropout": 0.0,
10
+ "activation_function": "gelu",
11
+ "add_cross_attention": true,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": 0.0,
19
+ "cross_attention_hidden_size": null,
20
+ "d_model": 1024,
21
+ "decoder_attention_heads": 16,
22
+ "decoder_ffn_dim": 4096,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 12,
25
+ "decoder_start_token_id": 2,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.1,
29
+ "early_stopping": false,
30
+ "encoder_attention_heads": 16,
31
+ "encoder_ffn_dim": 4096,
32
+ "encoder_layerdrop": 0.0,
33
+ "encoder_layers": 12,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 2,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": 2,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1",
43
+ "2": "LABEL_2"
44
+ },
45
+ "init_std": 0.02,
46
+ "is_decoder": true,
47
+ "is_encoder_decoder": true,
48
+ "label2id": {
49
+ "LABEL_0": 0,
50
+ "LABEL_1": 1,
51
+ "LABEL_2": 2
52
+ },
53
+ "length_penalty": 1.0,
54
+ "max_length": 512,
55
+ "max_position_embeddings": 1024,
56
+ "min_length": 0,
57
+ "model_type": "bart",
58
+ "no_repeat_ngram_size": 0,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 12,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 1,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "scale_embedding": false,
75
+ "sep_token_id": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": true,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": null,
86
+ "torchscript": false,
87
+ "transformers_version": "4.26.0",
88
+ "typical_p": 1.0,
89
+ "use_bfloat16": false,
90
+ "use_cache": true,
91
+ "vocab_size": 57531
92
+ },
93
+ "decoder_start_token_id": 0,
94
+ "encoder": {
95
+ "_name_or_path": "",
96
+ "add_cross_attention": false,
97
+ "architectures": null,
98
+ "attention_probs_dropout_prob": 0.0,
99
+ "bad_words_ids": null,
100
+ "begin_suppress_tokens": null,
101
+ "bos_token_id": null,
102
+ "chunk_size_feed_forward": 0,
103
+ "cross_attention_hidden_size": null,
104
+ "decoder_start_token_id": null,
105
+ "depths": [
106
+ 2,
107
+ 2,
108
+ 6,
109
+ 2
110
+ ],
111
+ "diversity_penalty": 0.0,
112
+ "do_sample": false,
113
+ "drop_path_rate": 0.1,
114
+ "early_stopping": false,
115
+ "embed_dim": 96,
116
+ "encoder_no_repeat_ngram_size": 0,
117
+ "encoder_stride": 32,
118
+ "eos_token_id": null,
119
+ "exponential_decay_length_penalty": null,
120
+ "finetuning_task": null,
121
+ "forced_bos_token_id": null,
122
+ "forced_eos_token_id": null,
123
+ "hidden_act": "gelu",
124
+ "hidden_dropout_prob": 0.0,
125
+ "hidden_size": 768,
126
+ "id2label": {
127
+ "0": "LABEL_0",
128
+ "1": "LABEL_1"
129
+ },
130
+ "image_size": [
131
+ 960,
132
+ 720
133
+ ],
134
+ "initializer_range": 0.02,
135
+ "is_decoder": false,
136
+ "is_encoder_decoder": false,
137
+ "label2id": {
138
+ "LABEL_0": 0,
139
+ "LABEL_1": 1
140
+ },
141
+ "layer_norm_eps": 1e-05,
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "min_length": 0,
145
+ "mlp_ratio": 4.0,
146
+ "model_type": "swinv2",
147
+ "no_repeat_ngram_size": 0,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_channels": 3,
151
+ "num_heads": [
152
+ 3,
153
+ 6,
154
+ 12,
155
+ 24
156
+ ],
157
+ "num_layers": 4,
158
+ "num_return_sequences": 1,
159
+ "output_attentions": false,
160
+ "output_hidden_states": false,
161
+ "output_scores": false,
162
+ "pad_token_id": null,
163
+ "patch_size": 4,
164
+ "path_norm": true,
165
+ "prefix": null,
166
+ "pretrained_window_sizes": [
167
+ 0,
168
+ 0,
169
+ 0,
170
+ 0
171
+ ],
172
+ "problem_type": null,
173
+ "pruned_heads": {},
174
+ "qkv_bias": true,
175
+ "remove_invalid_values": false,
176
+ "repetition_penalty": 1.0,
177
+ "return_dict": true,
178
+ "return_dict_in_generate": false,
179
+ "sep_token_id": null,
180
+ "suppress_tokens": null,
181
+ "task_specific_params": null,
182
+ "temperature": 1.0,
183
+ "tf_legacy_loss": false,
184
+ "tie_encoder_decoder": false,
185
+ "tie_word_embeddings": true,
186
+ "tokenizer_class": null,
187
+ "top_k": 50,
188
+ "top_p": 1.0,
189
+ "torch_dtype": null,
190
+ "torchscript": false,
191
+ "transformers_version": "4.26.0",
192
+ "typical_p": 1.0,
193
+ "use_absolute_embeddings": false,
194
+ "use_bfloat16": false,
195
+ "window_size": 7
196
+ },
197
+ "is_encoder_decoder": true,
198
+ "model_type": "vision-encoder-decoder",
199
+ "pad_token_id": 1,
200
+ "tie_word_embeddings": false,
201
+ "torch_dtype": "float32",
202
+ "transformers_version": null
203
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a8c51beed6a0a091af4f7eb301251fba9b6c02ad55daeef8ba3faaab41556af
3
+ size 1159753823
runs/Nov03_19-24-24_Factory-2/1699007075.040546/events.out.tfevents.1699007075.Factory-2.1792.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa40a2d33f8b03591f8638bd8f49d3502e61285009f21070003058c268da567
3
+ size 5946
runs/Nov03_19-24-24_Factory-2/events.out.tfevents.1699007075.Factory-2.1792.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c6e1c8ef61bec74d6645f47a92cd53da600e82ec6246e1f409a8c855ff3d23
3
+ size 43674
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824d8356a24875e5ecd52329eb4b731dcc6b58f916cab2f4bf359142eaf57dc0
3
+ size 3695