edugp commited on
Commit
505012b
1 Parent(s): c309418

Add model using BERTIN language encoder trained on 146364 examples and obtaining a loss of 2.231235980987549

Browse files
clip_spanish_bertin_146364_examples_lr_5e-5/config.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridCLIP"
4
+ ],
5
+ "initializer_factor": 1.0,
6
+ "model_type": "hybrid-clip",
7
+ "projection_dim": 512,
8
+ "seed": 42,
9
+ "text_config": {
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "architectures": [
13
+ "RobertaForMaskedLM"
14
+ ],
15
+ "attention_probs_dropout_prob": 0.1,
16
+ "bad_words_ids": null,
17
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "gradient_checkpointing": false,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-05,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 514,
48
+ "min_length": 0,
49
+ "model_type": "roberta",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 1,
60
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.9.0.dev0",
79
+ "type_vocab_size": 1,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 50265
83
+ },
84
+ "transformers_version": null,
85
+ "vision_config": {
86
+ "_name_or_path": "",
87
+ "add_cross_attention": false,
88
+ "architectures": null,
89
+ "attention_dropout": 0.0,
90
+ "bad_words_ids": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "decoder_start_token_id": null,
94
+ "diversity_penalty": 0.0,
95
+ "do_sample": false,
96
+ "dropout": 0.0,
97
+ "early_stopping": false,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "eos_token_id": null,
100
+ "finetuning_task": null,
101
+ "forced_bos_token_id": null,
102
+ "forced_eos_token_id": null,
103
+ "gradient_checkpointing": false,
104
+ "hidden_act": "quick_gelu",
105
+ "hidden_size": 768,
106
+ "id2label": {
107
+ "0": "LABEL_0",
108
+ "1": "LABEL_1"
109
+ },
110
+ "image_size": 224,
111
+ "initializer_factor": 1.0,
112
+ "initializer_range": 0.02,
113
+ "intermediate_size": 3072,
114
+ "is_decoder": false,
115
+ "is_encoder_decoder": false,
116
+ "label2id": {
117
+ "LABEL_0": 0,
118
+ "LABEL_1": 1
119
+ },
120
+ "layer_norm_eps": 1e-05,
121
+ "length_penalty": 1.0,
122
+ "max_length": 20,
123
+ "min_length": 0,
124
+ "model_type": "clip_vision_model",
125
+ "no_repeat_ngram_size": 0,
126
+ "num_attention_heads": 12,
127
+ "num_beam_groups": 1,
128
+ "num_beams": 1,
129
+ "num_hidden_layers": 12,
130
+ "num_return_sequences": 1,
131
+ "output_attentions": false,
132
+ "output_hidden_states": false,
133
+ "output_scores": false,
134
+ "pad_token_id": null,
135
+ "patch_size": 32,
136
+ "prefix": null,
137
+ "problem_type": null,
138
+ "pruned_heads": {},
139
+ "remove_invalid_values": false,
140
+ "repetition_penalty": 1.0,
141
+ "return_dict": true,
142
+ "return_dict_in_generate": false,
143
+ "sep_token_id": null,
144
+ "task_specific_params": null,
145
+ "temperature": 1.0,
146
+ "tie_encoder_decoder": false,
147
+ "tie_word_embeddings": true,
148
+ "tokenizer_class": null,
149
+ "top_k": 50,
150
+ "top_p": 1.0,
151
+ "torch_dtype": null,
152
+ "torchscript": false,
153
+ "transformers_version": "4.9.0.dev0",
154
+ "use_bfloat16": false
155
+ }
156
+ }
clip_spanish_bertin_146364_examples_lr_5e-5/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55def72bbb5079de08c70573842ea2aa973f6c502d95505a9709e4cd2a2f6402
3
+ size 851566424