Hugging Face's logo

flax-community
/
spanish-image-captioning

TensorBoard
Model card Files Metrics Community
bhavitvyamalik commited on
Commit
463e23b
•
1 Parent(s): 3c9e5c5

42

Browse files
Files changed (13) hide show
  1. ckpt-1199/config.json +0 -320
  2. ckpt-1199/flax_model.msgpack +0 -3
  3. ckpt-1199/opt_state.msgpack +0 -3
  4. ckpt-1199/training_state.json +0 -1
  5. ckpt-2399/config.json +0 -320
  6. ckpt-2399/flax_model.msgpack +0 -3
  7. ckpt-2399/opt_state.msgpack +0 -3
  8. ckpt-2399/training_state.json +0 -1
  9. ckpt-3599/config.json +0 -320
  10. ckpt-3599/flax_model.msgpack +0 -3
  11. ckpt-3599/opt_state.msgpack +0 -3
  12. ckpt-3599/training_state.json +0 -1
  13. logs/events.out.tfevents.1626621454.t1v-n-8499dd91-w-0.1300695.3.v2 +0 -3
ckpt-1199/config.json DELETED
@@ -1,320 +0,0 @@
1
- {
2
- "architectures": [
3
- "CLIPVisionMarianMT"
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
- "marian_config": {
223
- "_name_or_path": "",
224
- "activation_dropout": 0.0,
225
- "activation_function": "swish",
226
- "add_bias_logits": false,
227
- "add_cross_attention": false,
228
- "add_final_layer_norm": false,
229
- "architectures": [
230
- "MarianMTModel"
231
- ],
232
- "attention_dropout": 0.0,
233
- "bad_words_ids": [
234
- [
235
- 65000
236
- ]
237
- ],
238
- "bos_token_id": 0,
239
- "chunk_size_feed_forward": 0,
240
- "classif_dropout": 0.0,
241
- "classifier_dropout": 0.0,
242
- "d_model": 512,
243
- "decoder_attention_heads": 8,
244
- "decoder_ffn_dim": 2048,
245
- "decoder_layerdrop": 0.0,
246
- "decoder_layers": 6,
247
- "decoder_start_token_id": 65000,
248
- "diversity_penalty": 0.0,
249
- "do_sample": false,
250
- "dropout": 0.1,
251
- "early_stopping": false,
252
- "encoder_attention_heads": 8,
253
- "encoder_ffn_dim": 2048,
254
- "encoder_layerdrop": 0.0,
255
- "encoder_layers": 6,
256
- "encoder_no_repeat_ngram_size": 0,
257
- "eos_token_id": 0,
258
- "extra_pos_embeddings": 65001,
259
- "finetuning_task": null,
260
- "force_bos_token_to_be_generated": false,
261
- "forced_bos_token_id": null,
262
- "forced_eos_token_id": 0,
263
- "gradient_checkpointing": false,
264
- "id2label": {
265
- "0": "LABEL_0",
266
- "1": "LABEL_1",
267
- "2": "LABEL_2"
268
- },
269
- "init_std": 0.02,
270
- "is_decoder": false,
271
- "is_encoder_decoder": true,
272
- "label2id": {
273
- "LABEL_0": 0,
274
- "LABEL_1": 1,
275
- "LABEL_2": 2
276
- },
277
- "length_penalty": 1.0,
278
- "max_length": 512,
279
- "max_position_embeddings": 512,
280
- "min_length": 0,
281
- "model_type": "marian",
282
- "no_repeat_ngram_size": 0,
283
- "normalize_before": false,
284
- "normalize_embedding": false,
285
- "num_beam_groups": 1,
286
- "num_beams": 4,
287
- "num_hidden_layers": 6,
288
- "num_return_sequences": 1,
289
- "output_attentions": false,
290
- "output_hidden_states": false,
291
- "output_scores": false,
292
- "pad_token_id": 65000,
293
- "prefix": null,
294
- "problem_type": null,
295
- "pruned_heads": {},
296
- "remove_invalid_values": false,
297
- "repetition_penalty": 1.0,
298
- "return_dict": true,
299
- "return_dict_in_generate": false,
300
- "scale_embedding": true,
301
- "sep_token_id": null,
302
- "static_position_embeddings": true,
303
- "task_specific_params": null,
304
- "temperature": 1.0,
305
- "tie_encoder_decoder": false,
306
- "tie_word_embeddings": true,
307
- "tokenizer_class": null,
308
- "top_k": 50,
309
- "top_p": 1.0,
310
- "torch_dtype": null,
311
- "torchscript": false,
312
- "transformers_version": "4.9.0.dev0",
313
- "use_bfloat16": false,
314
- "use_cache": true,
315
- "vocab_size": 65001
316
- },
317
- "model_type": "clip-vision-marian",
318
- "seed": 42,
319
- "transformers_version": null
320
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt-1199/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16fc3c2700ebc9f24431708db71b12782d8d595383adeec7bc83542cd82d3ad4
3
- size 585690275
 
 
 
 
ckpt-1199/opt_state.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b27876855f04821e94df5784997b40ac8eebd173e0c787c74184de007f3c96a
3
- size 1171380740
 
 
 
 
ckpt-1199/training_state.json DELETED
@@ -1 +0,0 @@
1
- {"step": 1200}
 
 
ckpt-2399/config.json DELETED
@@ -1,320 +0,0 @@
1
- {
2
- "architectures": [
3
- "CLIPVisionMarianMT"
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
- "marian_config": {
223
- "_name_or_path": "",
224
- "activation_dropout": 0.0,
225
- "activation_function": "swish",
226
- "add_bias_logits": false,
227
- "add_cross_attention": false,
228
- "add_final_layer_norm": false,
229
- "architectures": [
230
- "MarianMTModel"
231
- ],
232
- "attention_dropout": 0.0,
233
- "bad_words_ids": [
234
- [
235
- 65000
236
- ]
237
- ],
238
- "bos_token_id": 0,
239
- "chunk_size_feed_forward": 0,
240
- "classif_dropout": 0.0,
241
- "classifier_dropout": 0.0,
242
- "d_model": 512,
243
- "decoder_attention_heads": 8,
244
- "decoder_ffn_dim": 2048,
245
- "decoder_layerdrop": 0.0,
246
- "decoder_layers": 6,
247
- "decoder_start_token_id": 65000,
248
- "diversity_penalty": 0.0,
249
- "do_sample": false,
250
- "dropout": 0.1,
251
- "early_stopping": false,
252
- "encoder_attention_heads": 8,
253
- "encoder_ffn_dim": 2048,
254
- "encoder_layerdrop": 0.0,
255
- "encoder_layers": 6,
256
- "encoder_no_repeat_ngram_size": 0,
257
- "eos_token_id": 0,
258
- "extra_pos_embeddings": 65001,
259
- "finetuning_task": null,
260
- "force_bos_token_to_be_generated": false,
261
- "forced_bos_token_id": null,
262
- "forced_eos_token_id": 0,
263
- "gradient_checkpointing": false,
264
- "id2label": {
265
- "0": "LABEL_0",
266
- "1": "LABEL_1",
267
- "2": "LABEL_2"
268
- },
269
- "init_std": 0.02,
270
- "is_decoder": false,
271
- "is_encoder_decoder": true,
272
- "label2id": {
273
- "LABEL_0": 0,
274
- "LABEL_1": 1,
275
- "LABEL_2": 2
276
- },
277
- "length_penalty": 1.0,
278
- "max_length": 512,
279
- "max_position_embeddings": 512,
280
- "min_length": 0,
281
- "model_type": "marian",
282
- "no_repeat_ngram_size": 0,
283
- "normalize_before": false,
284
- "normalize_embedding": false,
285
- "num_beam_groups": 1,
286
- "num_beams": 4,
287
- "num_hidden_layers": 6,
288
- "num_return_sequences": 1,
289
- "output_attentions": false,
290
- "output_hidden_states": false,
291
- "output_scores": false,
292
- "pad_token_id": 65000,
293
- "prefix": null,
294
- "problem_type": null,
295
- "pruned_heads": {},
296
- "remove_invalid_values": false,
297
- "repetition_penalty": 1.0,
298
- "return_dict": true,
299
- "return_dict_in_generate": false,
300
- "scale_embedding": true,
301
- "sep_token_id": null,
302
- "static_position_embeddings": true,
303
- "task_specific_params": null,
304
- "temperature": 1.0,
305
- "tie_encoder_decoder": false,
306
- "tie_word_embeddings": true,
307
- "tokenizer_class": null,
308
- "top_k": 50,
309
- "top_p": 1.0,
310
- "torch_dtype": null,
311
- "torchscript": false,
312
- "transformers_version": "4.9.0.dev0",
313
- "use_bfloat16": false,
314
- "use_cache": true,
315
- "vocab_size": 65001
316
- },
317
- "model_type": "clip-vision-marian",
318
- "seed": 42,
319
- "transformers_version": null
320
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt-2399/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5865656fbc4cd6b64a5b5270bade0af6607c11aedf5b9c99db2d5c8a5a89a5aa
3
- size 585690275
 
 
 
 
ckpt-2399/opt_state.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:22adc71332291e6abfc9d5f9a4927702071985da5257b824c097fdea5462f4b5
3
- size 1171380740
 
 
 
 
ckpt-2399/training_state.json DELETED
@@ -1 +0,0 @@
1
- {"step": 2400}
 
 
ckpt-3599/config.json DELETED
@@ -1,320 +0,0 @@
1
- {
2
- "architectures": [
3
- "CLIPVisionMarianMT"
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
- "marian_config": {
223
- "_name_or_path": "",
224
- "activation_dropout": 0.0,
225
- "activation_function": "swish",
226
- "add_bias_logits": false,
227
- "add_cross_attention": false,
228
- "add_final_layer_norm": false,
229
- "architectures": [
230
- "MarianMTModel"
231
- ],
232
- "attention_dropout": 0.0,
233
- "bad_words_ids": [
234
- [
235
- 65000
236
- ]
237
- ],
238
- "bos_token_id": 0,
239
- "chunk_size_feed_forward": 0,
240
- "classif_dropout": 0.0,
241
- "classifier_dropout": 0.0,
242
- "d_model": 512,
243
- "decoder_attention_heads": 8,
244
- "decoder_ffn_dim": 2048,
245
- "decoder_layerdrop": 0.0,
246
- "decoder_layers": 6,
247
- "decoder_start_token_id": 65000,
248
- "diversity_penalty": 0.0,
249
- "do_sample": false,
250
- "dropout": 0.1,
251
- "early_stopping": false,
252
- "encoder_attention_heads": 8,
253
- "encoder_ffn_dim": 2048,
254
- "encoder_layerdrop": 0.0,
255
- "encoder_layers": 6,
256
- "encoder_no_repeat_ngram_size": 0,
257
- "eos_token_id": 0,
258
- "extra_pos_embeddings": 65001,
259
- "finetuning_task": null,
260
- "force_bos_token_to_be_generated": false,
261
- "forced_bos_token_id": null,
262
- "forced_eos_token_id": 0,
263
- "gradient_checkpointing": false,
264
- "id2label": {
265
- "0": "LABEL_0",
266
- "1": "LABEL_1",
267
- "2": "LABEL_2"
268
- },
269
- "init_std": 0.02,
270
- "is_decoder": false,
271
- "is_encoder_decoder": true,
272
- "label2id": {
273
- "LABEL_0": 0,
274
- "LABEL_1": 1,
275
- "LABEL_2": 2
276
- },
277
- "length_penalty": 1.0,
278
- "max_length": 512,
279
- "max_position_embeddings": 512,
280
- "min_length": 0,
281
- "model_type": "marian",
282
- "no_repeat_ngram_size": 0,
283
- "normalize_before": false,
284
- "normalize_embedding": false,
285
- "num_beam_groups": 1,
286
- "num_beams": 4,
287
- "num_hidden_layers": 6,
288
- "num_return_sequences": 1,
289
- "output_attentions": false,
290
- "output_hidden_states": false,
291
- "output_scores": false,
292
- "pad_token_id": 65000,
293
- "prefix": null,
294
- "problem_type": null,
295
- "pruned_heads": {},
296
- "remove_invalid_values": false,
297
- "repetition_penalty": 1.0,
298
- "return_dict": true,
299
- "return_dict_in_generate": false,
300
- "scale_embedding": true,
301
- "sep_token_id": null,
302
- "static_position_embeddings": true,
303
- "task_specific_params": null,
304
- "temperature": 1.0,
305
- "tie_encoder_decoder": false,
306
- "tie_word_embeddings": true,
307
- "tokenizer_class": null,
308
- "top_k": 50,
309
- "top_p": 1.0,
310
- "torch_dtype": null,
311
- "torchscript": false,
312
- "transformers_version": "4.9.0.dev0",
313
- "use_bfloat16": false,
314
- "use_cache": true,
315
- "vocab_size": 65001
316
- },
317
- "model_type": "clip-vision-marian",
318
- "seed": 42,
319
- "transformers_version": null
320
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt-3599/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d68b8fd6b1aeb57d4c42015541e321d8c94a8fa65b2b44e9b44ecff67ad67d
3
- size 585690275
 
 
 
 
ckpt-3599/opt_state.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2164270c9246c47d1afaf87d6070c9d00629bfad3b6336da9caa81a88e51a229
3
- size 1171380740
 
 
 
 
ckpt-3599/training_state.json DELETED
@@ -1 +0,0 @@
1
- {"step": 3600}
 
 
logs/events.out.tfevents.1626621454.t1v-n-8499dd91-w-0.1300695.3.v2 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fca17b540a1c04086e539b5c0ce8ca0c519831120089441dc67281ec57f8b208
3
- size 530459