ritaramos commited on
Commit
616f816
·
verified ·
1 Parent(s): a840c4d

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SmallCap"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "facebook/xglm-2.9B",
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "gelu",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "XGLMForCausalLM"
12
+ ],
13
+ "attention_dropout": 0.1,
14
+ "attention_heads": 16,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "cross_attention_reduce_factor": 16,
21
+ "d_model": 2048,
22
+ "decoder_start_token_id": 2,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "dropout": 0.1,
26
+ "early_stopping": false,
27
+ "encoder_hidden_size": 768,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 2,
30
+ "exponential_decay_length_penalty": null,
31
+ "ffn_dim": 8192,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_decoder": true,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layerdrop": 0.0,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 2048,
50
+ "min_length": 0,
51
+ "model_type": "this_xglm",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_layers": 48,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "scale_embedding": true,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "typical_p": 1.0,
82
+ "use_bfloat16": false,
83
+ "use_cache": true,
84
+ "vocab_size": 256008
85
+ },
86
+ "encoder": {
87
+ "_name_or_path": "openai/clip-vit-base-patch32",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "CLIPModel"
91
+ ],
92
+ "bad_words_ids": null,
93
+ "begin_suppress_tokens": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "early_stopping": false,
101
+ "encoder_no_repeat_ngram_size": 0,
102
+ "eos_token_id": null,
103
+ "exponential_decay_length_penalty": null,
104
+ "finetuning_task": null,
105
+ "forced_bos_token_id": null,
106
+ "forced_eos_token_id": null,
107
+ "id2label": {
108
+ "0": "LABEL_0",
109
+ "1": "LABEL_1"
110
+ },
111
+ "initializer_factor": 1.0,
112
+ "is_decoder": false,
113
+ "is_encoder_decoder": false,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1
117
+ },
118
+ "length_penalty": 1.0,
119
+ "logit_scale_init_value": 2.6592,
120
+ "max_length": 20,
121
+ "min_length": 0,
122
+ "model_type": "clip",
123
+ "no_repeat_ngram_size": 0,
124
+ "num_beam_groups": 1,
125
+ "num_beams": 1,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": null,
131
+ "prefix": null,
132
+ "problem_type": null,
133
+ "projection_dim": 512,
134
+ "pruned_heads": {},
135
+ "remove_invalid_values": false,
136
+ "repetition_penalty": 1.0,
137
+ "return_dict": true,
138
+ "return_dict_in_generate": false,
139
+ "sep_token_id": null,
140
+ "suppress_tokens": null,
141
+ "task_specific_params": null,
142
+ "temperature": 1.0,
143
+ "text_config": {
144
+ "_name_or_path": "",
145
+ "add_cross_attention": false,
146
+ "architectures": null,
147
+ "attention_dropout": 0.0,
148
+ "bad_words_ids": null,
149
+ "begin_suppress_tokens": null,
150
+ "bos_token_id": 0,
151
+ "chunk_size_feed_forward": 0,
152
+ "cross_attention_hidden_size": null,
153
+ "decoder_start_token_id": null,
154
+ "diversity_penalty": 0.0,
155
+ "do_sample": false,
156
+ "dropout": 0.0,
157
+ "early_stopping": false,
158
+ "encoder_no_repeat_ngram_size": 0,
159
+ "eos_token_id": 2,
160
+ "exponential_decay_length_penalty": null,
161
+ "finetuning_task": null,
162
+ "forced_bos_token_id": null,
163
+ "forced_eos_token_id": null,
164
+ "hidden_act": "quick_gelu",
165
+ "hidden_size": 512,
166
+ "id2label": {
167
+ "0": "LABEL_0",
168
+ "1": "LABEL_1"
169
+ },
170
+ "initializer_factor": 1.0,
171
+ "initializer_range": 0.02,
172
+ "intermediate_size": 2048,
173
+ "is_decoder": false,
174
+ "is_encoder_decoder": false,
175
+ "label2id": {
176
+ "LABEL_0": 0,
177
+ "LABEL_1": 1
178
+ },
179
+ "layer_norm_eps": 1e-05,
180
+ "length_penalty": 1.0,
181
+ "max_length": 20,
182
+ "max_position_embeddings": 77,
183
+ "min_length": 0,
184
+ "model_type": "clip_text_model",
185
+ "no_repeat_ngram_size": 0,
186
+ "num_attention_heads": 8,
187
+ "num_beam_groups": 1,
188
+ "num_beams": 1,
189
+ "num_hidden_layers": 12,
190
+ "num_return_sequences": 1,
191
+ "output_attentions": false,
192
+ "output_hidden_states": false,
193
+ "output_scores": false,
194
+ "pad_token_id": 1,
195
+ "prefix": null,
196
+ "problem_type": null,
197
+ "projection_dim": 512,
198
+ "pruned_heads": {},
199
+ "remove_invalid_values": false,
200
+ "repetition_penalty": 1.0,
201
+ "return_dict": true,
202
+ "return_dict_in_generate": false,
203
+ "sep_token_id": null,
204
+ "suppress_tokens": null,
205
+ "task_specific_params": null,
206
+ "temperature": 1.0,
207
+ "tf_legacy_loss": false,
208
+ "tie_encoder_decoder": false,
209
+ "tie_word_embeddings": true,
210
+ "tokenizer_class": null,
211
+ "top_k": 50,
212
+ "top_p": 1.0,
213
+ "torch_dtype": null,
214
+ "torchscript": false,
215
+ "typical_p": 1.0,
216
+ "use_bfloat16": false,
217
+ "vocab_size": 49408
218
+ },
219
+ "tf_legacy_loss": false,
220
+ "tie_encoder_decoder": false,
221
+ "tie_word_embeddings": true,
222
+ "tokenizer_class": null,
223
+ "top_k": 50,
224
+ "top_p": 1.0,
225
+ "torch_dtype": null,
226
+ "torchscript": false,
227
+ "typical_p": 1.0,
228
+ "use_bfloat16": false,
229
+ "vision_config": {
230
+ "_name_or_path": "",
231
+ "add_cross_attention": false,
232
+ "architectures": null,
233
+ "attention_dropout": 0.0,
234
+ "bad_words_ids": null,
235
+ "begin_suppress_tokens": null,
236
+ "bos_token_id": null,
237
+ "chunk_size_feed_forward": 0,
238
+ "cross_attention_hidden_size": null,
239
+ "decoder_start_token_id": null,
240
+ "diversity_penalty": 0.0,
241
+ "do_sample": false,
242
+ "dropout": 0.0,
243
+ "early_stopping": false,
244
+ "encoder_no_repeat_ngram_size": 0,
245
+ "eos_token_id": null,
246
+ "exponential_decay_length_penalty": null,
247
+ "finetuning_task": null,
248
+ "forced_bos_token_id": null,
249
+ "forced_eos_token_id": null,
250
+ "hidden_act": "quick_gelu",
251
+ "hidden_size": 768,
252
+ "id2label": {
253
+ "0": "LABEL_0",
254
+ "1": "LABEL_1"
255
+ },
256
+ "image_size": 224,
257
+ "initializer_factor": 1.0,
258
+ "initializer_range": 0.02,
259
+ "intermediate_size": 3072,
260
+ "is_decoder": false,
261
+ "is_encoder_decoder": false,
262
+ "label2id": {
263
+ "LABEL_0": 0,
264
+ "LABEL_1": 1
265
+ },
266
+ "layer_norm_eps": 1e-05,
267
+ "length_penalty": 1.0,
268
+ "max_length": 20,
269
+ "min_length": 0,
270
+ "model_type": "clip_vision_model",
271
+ "no_repeat_ngram_size": 0,
272
+ "num_attention_heads": 12,
273
+ "num_beam_groups": 1,
274
+ "num_beams": 1,
275
+ "num_channels": 3,
276
+ "num_hidden_layers": 12,
277
+ "num_return_sequences": 1,
278
+ "output_attentions": false,
279
+ "output_hidden_states": false,
280
+ "output_scores": false,
281
+ "pad_token_id": null,
282
+ "patch_size": 32,
283
+ "prefix": null,
284
+ "problem_type": null,
285
+ "projection_dim": 512,
286
+ "pruned_heads": {},
287
+ "remove_invalid_values": false,
288
+ "repetition_penalty": 1.0,
289
+ "return_dict": true,
290
+ "return_dict_in_generate": false,
291
+ "sep_token_id": null,
292
+ "suppress_tokens": null,
293
+ "task_specific_params": null,
294
+ "temperature": 1.0,
295
+ "tf_legacy_loss": false,
296
+ "tie_encoder_decoder": false,
297
+ "tie_word_embeddings": true,
298
+ "tokenizer_class": null,
299
+ "top_k": 50,
300
+ "top_p": 1.0,
301
+ "torch_dtype": null,
302
+ "torchscript": false,
303
+ "typical_p": 1.0,
304
+ "use_bfloat16": false
305
+ }
306
+ },
307
+ "eos_token_id": 5,
308
+ "is_encoder_decoder": true,
309
+ "k": 4,
310
+ "max_length": 25,
311
+ "model_type": "smallcap",
312
+ "pad_token_id": 35,
313
+ "rag": true,
314
+ "retrieval_encoder": "RN50x64",
315
+ "tie_word_embeddings": false,
316
+ "torch_dtype": "float32",
317
+ "transformers_version": "4.33.0",
318
+ "vocab_size": 256008
319
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.33.0"
8
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d474568d499f97ace2e1310b51c3755bc20cf9a4967b53b4f6ae7da9f7ee8b
3
+ size 279731645
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPFeatureExtractor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3760574463d72bad2b25ebc27d0e5443c3022323223c47a7754c6d84c93d01a5
3
+ size 9941014151
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8f3a33278b55c4a8d5fa9b66825ba420ff175fd8846053522f3a00e27a5c56
3
+ size 2315024471
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3e083ecee792ac46a23564d14ea23bf936a14a5dcb9d22ecb5d0b405ce85d8
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466292544b965f4e9df43e45afb26946697b9cc6a4657692627351528083a33a
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9997457842555715,
5
+ "eval_steps": 500,
6
+ "global_step": 26550,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 6.667043314500941e-05,
14
+ "loss": 2.8102,
15
+ "step": 8850
16
+ },
17
+ {
18
+ "epoch": 2.0,
19
+ "learning_rate": 3.3348399246704334e-05,
20
+ "loss": 2.5375,
21
+ "step": 17701
22
+ },
23
+ {
24
+ "epoch": 3.0,
25
+ "learning_rate": 3.0131826741996235e-08,
26
+ "loss": 2.4492,
27
+ "step": 26550
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 26550,
32
+ "num_train_epochs": 3,
33
+ "save_steps": 500,
34
+ "total_flos": 0.0,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f5030928809cf82649959676027756da32186468df982efa4b176e89410072
3
+ size 4283