bhavitvyamalik commited on
Commit
d11855c
1 Parent(s): a82b5ff

remove ckpt folder

Browse files
ckpt/ckpt-49499/config.json DELETED
@@ -1,316 +0,0 @@
1
- {
2
- "architectures": [
3
- "CLIPVisionMBartForConditionalGeneration"
4
- ],
5
- "clip_vision_config": {
6
- "_name_or_path": "",
7
- "add_cross_attention": false,
8
- "architectures": [
9
- "CLIPModel"
10
- ],
11
- "attention_dropout": 0.0,
12
- "bad_words_ids": null,
13
- "bos_token_id": null,
14
- "chunk_size_feed_forward": 0,
15
- "decoder_start_token_id": null,
16
- "diversity_penalty": 0.0,
17
- "do_sample": false,
18
- "dropout": 0.0,
19
- "early_stopping": false,
20
- "encoder_no_repeat_ngram_size": 0,
21
- "eos_token_id": null,
22
- "finetuning_task": null,
23
- "forced_bos_token_id": null,
24
- "forced_eos_token_id": null,
25
- "gradient_checkpointing": false,
26
- "hidden_act": "quick_gelu",
27
- "hidden_size": 768,
28
- "id2label": {
29
- "0": "LABEL_0",
30
- "1": "LABEL_1"
31
- },
32
- "image_size": 224,
33
- "initializer_factor": 1.0,
34
- "initializer_range": 0.02,
35
- "intermediate_size": 3072,
36
- "is_decoder": false,
37
- "is_encoder_decoder": false,
38
- "label2id": {
39
- "LABEL_0": 0,
40
- "LABEL_1": 1
41
- },
42
- "layer_norm_eps": 1e-05,
43
- "length_penalty": 1.0,
44
- "max_length": 20,
45
- "min_length": 0,
46
- "model_type": "clip_vision_model",
47
- "no_repeat_ngram_size": 0,
48
- "num_attention_heads": 12,
49
- "num_beam_groups": 1,
50
- "num_beams": 1,
51
- "num_hidden_layers": 12,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": null,
57
- "patch_size": 32,
58
- "prefix": null,
59
- "problem_type": null,
60
- "projection_dim": 512,
61
- "pruned_heads": {},
62
- "remove_invalid_values": false,
63
- "repetition_penalty": 1.0,
64
- "return_dict": true,
65
- "return_dict_in_generate": false,
66
- "sep_token_id": null,
67
- "task_specific_params": null,
68
- "temperature": 1.0,
69
- "text_config": {
70
- "_name_or_path": "",
71
- "add_cross_attention": false,
72
- "architectures": null,
73
- "attention_dropout": 0.0,
74
- "bad_words_ids": null,
75
- "bos_token_id": 0,
76
- "chunk_size_feed_forward": 0,
77
- "decoder_start_token_id": null,
78
- "diversity_penalty": 0.0,
79
- "do_sample": false,
80
- "dropout": 0.0,
81
- "early_stopping": false,
82
- "encoder_no_repeat_ngram_size": 0,
83
- "eos_token_id": 2,
84
- "finetuning_task": null,
85
- "forced_bos_token_id": null,
86
- "forced_eos_token_id": null,
87
- "gradient_checkpointing": false,
88
- "hidden_act": "quick_gelu",
89
- "hidden_size": 512,
90
- "id2label": {
91
- "0": "LABEL_0",
92
- "1": "LABEL_1"
93
- },
94
- "initializer_factor": 1.0,
95
- "initializer_range": 0.02,
96
- "intermediate_size": 2048,
97
- "is_decoder": false,
98
- "is_encoder_decoder": false,
99
- "label2id": {
100
- "LABEL_0": 0,
101
- "LABEL_1": 1
102
- },
103
- "layer_norm_eps": 1e-05,
104
- "length_penalty": 1.0,
105
- "max_length": 20,
106
- "max_position_embeddings": 77,
107
- "min_length": 0,
108
- "model_type": "clip_text_model",
109
- "no_repeat_ngram_size": 0,
110
- "num_attention_heads": 8,
111
- "num_beam_groups": 1,
112
- "num_beams": 1,
113
- "num_hidden_layers": 12,
114
- "num_return_sequences": 1,
115
- "output_attentions": false,
116
- "output_hidden_states": false,
117
- "output_scores": false,
118
- "pad_token_id": 1,
119
- "prefix": null,
120
- "problem_type": null,
121
- "pruned_heads": {},
122
- "remove_invalid_values": false,
123
- "repetition_penalty": 1.0,
124
- "return_dict": true,
125
- "return_dict_in_generate": false,
126
- "sep_token_id": null,
127
- "task_specific_params": null,
128
- "temperature": 1.0,
129
- "tie_encoder_decoder": false,
130
- "tie_word_embeddings": true,
131
- "tokenizer_class": null,
132
- "top_k": 50,
133
- "top_p": 1.0,
134
- "torchscript": false,
135
- "transformers_version": "4.7.0.dev0",
136
- "use_bfloat16": false,
137
- "vocab_size": 49408
138
- },
139
- "text_config_dict": null,
140
- "tie_encoder_decoder": false,
141
- "tie_word_embeddings": true,
142
- "tokenizer_class": null,
143
- "top_k": 50,
144
- "top_p": 1.0,
145
- "torch_dtype": null,
146
- "torchscript": false,
147
- "transformers_version": "4.9.0.dev0",
148
- "use_bfloat16": false,
149
- "vision_config": {
150
- "_name_or_path": "",
151
- "add_cross_attention": false,
152
- "architectures": null,
153
- "attention_dropout": 0.0,
154
- "bad_words_ids": null,
155
- "bos_token_id": null,
156
- "chunk_size_feed_forward": 0,
157
- "decoder_start_token_id": null,
158
- "diversity_penalty": 0.0,
159
- "do_sample": false,
160
- "dropout": 0.0,
161
- "early_stopping": false,
162
- "encoder_no_repeat_ngram_size": 0,
163
- "eos_token_id": null,
164
- "finetuning_task": null,
165
- "forced_bos_token_id": null,
166
- "forced_eos_token_id": null,
167
- "gradient_checkpointing": false,
168
- "hidden_act": "quick_gelu",
169
- "hidden_size": 768,
170
- "id2label": {
171
- "0": "LABEL_0",
172
- "1": "LABEL_1"
173
- },
174
- "image_size": 224,
175
- "initializer_factor": 1.0,
176
- "initializer_range": 0.02,
177
- "intermediate_size": 3072,
178
- "is_decoder": false,
179
- "is_encoder_decoder": false,
180
- "label2id": {
181
- "LABEL_0": 0,
182
- "LABEL_1": 1
183
- },
184
- "layer_norm_eps": 1e-05,
185
- "length_penalty": 1.0,
186
- "max_length": 20,
187
- "min_length": 0,
188
- "model_type": "clip_vision_model",
189
- "no_repeat_ngram_size": 0,
190
- "num_attention_heads": 12,
191
- "num_beam_groups": 1,
192
- "num_beams": 1,
193
- "num_hidden_layers": 12,
194
- "num_return_sequences": 1,
195
- "output_attentions": false,
196
- "output_hidden_states": false,
197
- "output_scores": false,
198
- "pad_token_id": null,
199
- "patch_size": 32,
200
- "prefix": null,
201
- "problem_type": null,
202
- "pruned_heads": {},
203
- "remove_invalid_values": false,
204
- "repetition_penalty": 1.0,
205
- "return_dict": true,
206
- "return_dict_in_generate": false,
207
- "sep_token_id": null,
208
- "task_specific_params": null,
209
- "temperature": 1.0,
210
- "tie_encoder_decoder": false,
211
- "tie_word_embeddings": true,
212
- "tokenizer_class": null,
213
- "top_k": 50,
214
- "top_p": 1.0,
215
- "torchscript": false,
216
- "transformers_version": "4.7.0.dev0",
217
- "use_bfloat16": false
218
- },
219
- "vision_config_dict": null
220
- },
221
- "is_encoder_decoder": true,
222
- "mbart_config": {
223
- "_name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large",
224
- "_num_labels": 3,
225
- "activation_dropout": 0.0,
226
- "activation_function": "gelu",
227
- "add_bias_logits": false,
228
- "add_cross_attention": false,
229
- "add_final_layer_norm": true,
230
- "architectures": [
231
- "MBartForConditionalGeneration"
232
- ],
233
- "attention_dropout": 0.0,
234
- "bad_words_ids": null,
235
- "bos_token_id": 0,
236
- "chunk_size_feed_forward": 0,
237
- "classif_dropout": 0.0,
238
- "classifier_dropout": 0.0,
239
- "d_model": 1024,
240
- "decoder_attention_heads": 16,
241
- "decoder_ffn_dim": 4096,
242
- "decoder_layerdrop": 0.0,
243
- "decoder_layers": 12,
244
- "decoder_start_token_id": 2,
245
- "diversity_penalty": 0.0,
246
- "do_sample": false,
247
- "dropout": 0.1,
248
- "early_stopping": true,
249
- "encoder_attention_heads": 16,
250
- "encoder_ffn_dim": 4096,
251
- "encoder_layerdrop": 0.0,
252
- "encoder_layers": 12,
253
- "encoder_no_repeat_ngram_size": 0,
254
- "eos_token_id": 2,
255
- "finetuning_task": null,
256
- "forced_bos_token_id": null,
257
- "forced_eos_token_id": 2,
258
- "gradient_checkpointing": false,
259
- "id2label": {
260
- "0": "LABEL_0",
261
- "1": "LABEL_1",
262
- "2": "LABEL_2"
263
- },
264
- "init_std": 0.02,
265
- "is_decoder": false,
266
- "is_encoder_decoder": true,
267
- "label2id": {
268
- "LABEL_0": 0,
269
- "LABEL_1": 1,
270
- "LABEL_2": 2
271
- },
272
- "length_penalty": 1.0,
273
- "max_length": 200,
274
- "max_position_embeddings": 1024,
275
- "min_length": 0,
276
- "model_type": "mbart",
277
- "no_repeat_ngram_size": 0,
278
- "normalize_before": true,
279
- "normalize_embedding": true,
280
- "num_beam_groups": 1,
281
- "num_beams": 5,
282
- "num_hidden_layers": 12,
283
- "num_return_sequences": 1,
284
- "output_attentions": false,
285
- "output_hidden_states": false,
286
- "output_past": true,
287
- "output_scores": false,
288
- "pad_token_id": 1,
289
- "prefix": null,
290
- "problem_type": null,
291
- "pruned_heads": {},
292
- "remove_invalid_values": false,
293
- "repetition_penalty": 1.0,
294
- "return_dict": true,
295
- "return_dict_in_generate": false,
296
- "scale_embedding": true,
297
- "sep_token_id": null,
298
- "static_position_embeddings": false,
299
- "task_specific_params": null,
300
- "temperature": 1.0,
301
- "tie_encoder_decoder": false,
302
- "tie_word_embeddings": true,
303
- "tokenizer_class": "MBart50Tokenizer",
304
- "top_k": 50,
305
- "top_p": 1.0,
306
- "torch_dtype": null,
307
- "torchscript": false,
308
- "transformers_version": "4.9.0.dev0",
309
- "use_bfloat16": false,
310
- "use_cache": true,
311
- "vocab_size": 250054
312
- },
313
- "model_type": "clip-vision-mbart",
314
- "seed": 42,
315
- "transformers_version": null
316
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/ckpt-49499/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9e476868cd065e62e2bb97c737b2b0f008b2a87b9ebf0ed0ee85b536313c250
3
- size 2188672582
 
 
 
 
ckpt/ckpt-49499/training_state.json DELETED
@@ -1 +0,0 @@
1
- {"step": 49500}