Hugging Face's logo

flax-community
/
clip-spanish

Transformers
JAX
Spanish
hybrid-clip
spanish
roberta
vit
Inference Endpoints
Model card Files Community
edugp commited on
Commit
864f8c7
•
1 Parent(s): 505012b

Keep only best performing model in main (all models still available in develop branch). Best performing model is clip_spanish_141230_samples with a loss of 2.231235980987549

Browse files
Files changed (17) hide show
  1. clip_spanish_141230_samples/config.json +0 -157
  2. clip_spanish_141230_samples/flax_model.msgpack +0 -3
  3. clip_spanish_1_percent/config.json +0 -157
  4. clip_spanish_1_percent/flax_model.msgpack +0 -3
  5. clip_spanish_20_percent/config.json +0 -157
  6. clip_spanish_20_percent/flax_model.msgpack +0 -3
  7. clip_spanish_20_percent/logs/events.out.tfevents.1626328032.t1v-n-5900a4fe-w-0.85514.3.v2 +0 -3
  8. clip_spanish_20_percent/logs/events.out.tfevents.1626328154.t1v-n-5900a4fe-w-0.86871.3.v2 +0 -3
  9. clip_spanish_20_percent_98_1_1_split/config.json +0 -157
  10. clip_spanish_20_percent_98_1_1_split/flax_model.msgpack +0 -3
  11. clip_spanish_20_percent_98_1_1_split/logs/events.out.tfevents.1626336561.t1v-n-5900a4fe-w-0.108111.3.v2 +0 -3
  12. clip_spanish_72972_samples/config.json +0 -157
  13. clip_spanish_72972_samples/flax_model.msgpack +0 -3
  14. clip_spanish_72972_samples/logs/events.out.tfevents.1626390780.t1v-n-5900a4fe-w-0.2167230.3.v2 +0 -3
  15. clip_spanish_bertin_146364_examples_lr_5e-5/config.json +0 -156
  16. clip_spanish_bertin_146364_examples_lr_5e-5/flax_model.msgpack +0 -3
  17. {clip_spanish_141230_samples/logs → logs}/events.out.tfevents.1626476231.t1v-n-5900a4fe-w-0.1105221.3.v2 +0 -0
clip_spanish_141230_samples/config.json DELETED
@@ -1,157 +0,0 @@
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": "dccuchile/bert-base-spanish-wwm-cased",
11
- "add_cross_attention": false,
12
- "architectures": [
13
- "BertForMaskedLM"
14
- ],
15
- "attention_probs_dropout_prob": 0.1,
16
- "bad_words_ids": null,
17
- "bos_token_id": null,
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": null,
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-12,
45
- "length_penalty": 1.0,
46
- "max_length": 20,
47
- "max_position_embeddings": 512,
48
- "min_length": 0,
49
- "model_type": "bert",
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_past": true,
59
- "output_scores": false,
60
- "pad_token_id": 1,
61
- "position_embedding_type": "absolute",
62
- "prefix": null,
63
- "problem_type": null,
64
- "pruned_heads": {},
65
- "remove_invalid_values": false,
66
- "repetition_penalty": 1.0,
67
- "return_dict": true,
68
- "return_dict_in_generate": false,
69
- "sep_token_id": null,
70
- "task_specific_params": null,
71
- "temperature": 1.0,
72
- "tie_encoder_decoder": false,
73
- "tie_word_embeddings": true,
74
- "tokenizer_class": null,
75
- "top_k": 50,
76
- "top_p": 1.0,
77
- "torch_dtype": null,
78
- "torchscript": false,
79
- "transformers_version": "4.9.0.dev0",
80
- "type_vocab_size": 2,
81
- "use_bfloat16": false,
82
- "use_cache": true,
83
- "vocab_size": 31002
84
- },
85
- "transformers_version": null,
86
- "vision_config": {
87
- "_name_or_path": "",
88
- "add_cross_attention": false,
89
- "architectures": null,
90
- "attention_dropout": 0.0,
91
- "bad_words_ids": null,
92
- "bos_token_id": null,
93
- "chunk_size_feed_forward": 0,
94
- "decoder_start_token_id": null,
95
- "diversity_penalty": 0.0,
96
- "do_sample": false,
97
- "dropout": 0.0,
98
- "early_stopping": false,
99
- "encoder_no_repeat_ngram_size": 0,
100
- "eos_token_id": null,
101
- "finetuning_task": null,
102
- "forced_bos_token_id": null,
103
- "forced_eos_token_id": null,
104
- "gradient_checkpointing": false,
105
- "hidden_act": "quick_gelu",
106
- "hidden_size": 768,
107
- "id2label": {
108
- "0": "LABEL_0",
109
- "1": "LABEL_1"
110
- },
111
- "image_size": 224,
112
- "initializer_factor": 1.0,
113
- "initializer_range": 0.02,
114
- "intermediate_size": 3072,
115
- "is_decoder": false,
116
- "is_encoder_decoder": false,
117
- "label2id": {
118
- "LABEL_0": 0,
119
- "LABEL_1": 1
120
- },
121
- "layer_norm_eps": 1e-05,
122
- "length_penalty": 1.0,
123
- "max_length": 20,
124
- "min_length": 0,
125
- "model_type": "clip_vision_model",
126
- "no_repeat_ngram_size": 0,
127
- "num_attention_heads": 12,
128
- "num_beam_groups": 1,
129
- "num_beams": 1,
130
- "num_hidden_layers": 12,
131
- "num_return_sequences": 1,
132
- "output_attentions": false,
133
- "output_hidden_states": false,
134
- "output_scores": false,
135
- "pad_token_id": null,
136
- "patch_size": 32,
137
- "prefix": null,
138
- "problem_type": null,
139
- "pruned_heads": {},
140
- "remove_invalid_values": false,
141
- "repetition_penalty": 1.0,
142
- "return_dict": true,
143
- "return_dict_in_generate": false,
144
- "sep_token_id": null,
145
- "task_specific_params": null,
146
- "temperature": 1.0,
147
- "tie_encoder_decoder": false,
148
- "tie_word_embeddings": true,
149
- "tokenizer_class": null,
150
- "top_k": 50,
151
- "top_p": 1.0,
152
- "torch_dtype": null,
153
- "torchscript": false,
154
- "transformers_version": "4.9.0.dev0",
155
- "use_bfloat16": false
156
- }
157
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
clip_spanish_141230_samples/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f528ad8bfefe1abf023fa9670cee2e2d4ef36c903cb47c4d980b47ad0eb0d04f
3
- size 792387416
 
 
 
 
clip_spanish_1_percent/config.json DELETED
@@ -1,157 +0,0 @@
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": "dccuchile/bert-base-spanish-wwm-cased",
11
- "add_cross_attention": false,
12
- "architectures": [
13
- "BertForMaskedLM"
14
- ],
15
- "attention_probs_dropout_prob": 0.1,
16
- "bad_words_ids": null,
17
- "bos_token_id": null,
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": null,
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-12,
45
- "length_penalty": 1.0,
46
- "max_length": 20,
47
- "max_position_embeddings": 512,
48
- "min_length": 0,
49
- "model_type": "bert",
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_past": true,
59
- "output_scores": false,
60
- "pad_token_id": 1,
61
- "position_embedding_type": "absolute",
62
- "prefix": null,
63
- "problem_type": null,
64
- "pruned_heads": {},
65
- "remove_invalid_values": false,
66
- "repetition_penalty": 1.0,
67
- "return_dict": true,
68
- "return_dict_in_generate": false,
69
- "sep_token_id": null,
70
- "task_specific_params": null,
71
- "temperature": 1.0,
72
- "tie_encoder_decoder": false,
73
- "tie_word_embeddings": true,
74
- "tokenizer_class": null,
75
- "top_k": 50,
76
- "top_p": 1.0,
77
- "torch_dtype": null,
78
- "torchscript": false,
79
- "transformers_version": "4.9.0.dev0",
80
- "type_vocab_size": 2,
81
- "use_bfloat16": false,
82
- "use_cache": true,
83
- "vocab_size": 31002
84
- },
85
- "transformers_version": null,
86
- "vision_config": {
87
- "_name_or_path": "",
88
- "add_cross_attention": false,
89
- "architectures": null,
90
- "attention_dropout": 0.0,
91
- "bad_words_ids": null,
92
- "bos_token_id": null,
93
- "chunk_size_feed_forward": 0,
94
- "decoder_start_token_id": null,
95
- "diversity_penalty": 0.0,
96
- "do_sample": false,
97
- "dropout": 0.0,
98
- "early_stopping": false,
99
- "encoder_no_repeat_ngram_size": 0,
100
- "eos_token_id": null,
101
- "finetuning_task": null,
102
- "forced_bos_token_id": null,
103
- "forced_eos_token_id": null,
104
- "gradient_checkpointing": false,
105
- "hidden_act": "quick_gelu",
106
- "hidden_size": 768,
107
- "id2label": {
108
- "0": "LABEL_0",
109
- "1": "LABEL_1"
110
- },
111
- "image_size": 224,
112
- "initializer_factor": 1.0,
113
- "initializer_range": 0.02,
114
- "intermediate_size": 3072,
115
- "is_decoder": false,
116
- "is_encoder_decoder": false,
117
- "label2id": {
118
- "LABEL_0": 0,
119
- "LABEL_1": 1
120
- },
121
- "layer_norm_eps": 1e-05,
122
- "length_penalty": 1.0,
123
- "max_length": 20,
124
- "min_length": 0,
125
- "model_type": "clip_vision_model",
126
- "no_repeat_ngram_size": 0,
127
- "num_attention_heads": 12,
128
- "num_beam_groups": 1,
129
- "num_beams": 1,
130
- "num_hidden_layers": 12,
131
- "num_return_sequences": 1,
132
- "output_attentions": false,
133
- "output_hidden_states": false,
134
- "output_scores": false,
135
- "pad_token_id": null,
136
- "patch_size": 32,
137
- "prefix": null,
138
- "problem_type": null,
139
- "pruned_heads": {},
140
- "remove_invalid_values": false,
141
- "repetition_penalty": 1.0,
142
- "return_dict": true,
143
- "return_dict_in_generate": false,
144
- "sep_token_id": null,
145
- "task_specific_params": null,
146
- "temperature": 1.0,
147
- "tie_encoder_decoder": false,
148
- "tie_word_embeddings": true,
149
- "tokenizer_class": null,
150
- "top_k": 50,
151
- "top_p": 1.0,
152
- "torch_dtype": null,
153
- "torchscript": false,
154
- "transformers_version": "4.9.0.dev0",
155
- "use_bfloat16": false
156
- }
157
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
clip_spanish_1_percent/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:29e4478aa3195ba626a7051a3d2a8d17bb540b4e68d8d75cca2d549104e586c2
3
- size 792387416
 
 
 
 
clip_spanish_20_percent/config.json DELETED
@@ -1,157 +0,0 @@
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": "dccuchile/bert-base-spanish-wwm-cased",
11
- "add_cross_attention": false,
12
- "architectures": [
13
- "BertForMaskedLM"
14
- ],
15
- "attention_probs_dropout_prob": 0.1,
16
- "bad_words_ids": null,
17
- "bos_token_id": null,
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": null,
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-12,
45
- "length_penalty": 1.0,
46
- "max_length": 20,
47
- "max_position_embeddings": 512,
48
- "min_length": 0,
49
- "model_type": "bert",
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_past": true,
59
- "output_scores": false,
60
- "pad_token_id": 1,
61
- "position_embedding_type": "absolute",
62
- "prefix": null,
63
- "problem_type": null,
64
- "pruned_heads": {},
65
- "remove_invalid_values": false,
66
- "repetition_penalty": 1.0,
67
- "return_dict": true,
68
- "return_dict_in_generate": false,
69
- "sep_token_id": null,
70
- "task_specific_params": null,
71
- "temperature": 1.0,
72
- "tie_encoder_decoder": false,
73
- "tie_word_embeddings": true,
74
- "tokenizer_class": null,
75
- "top_k": 50,
76
- "top_p": 1.0,
77
- "torch_dtype": null,
78
- "torchscript": false,
79
- "transformers_version": "4.9.0.dev0",
80
- "type_vocab_size": 2,
81
- "use_bfloat16": false,
82
- "use_cache": true,
83
- "vocab_size": 31002
84
- },
85
- "transformers_version": null,
86
- "vision_config": {
87
- "_name_or_path": "",
88
- "add_cross_attention": false,
89
- "architectures": null,
90
- "attention_dropout": 0.0,
91
- "bad_words_ids": null,
92
- "bos_token_id": null,
93
- "chunk_size_feed_forward": 0,
94
- "decoder_start_token_id": null,
95
- "diversity_penalty": 0.0,
96
- "do_sample": false,
97
- "dropout": 0.0,
98
- "early_stopping": false,
99
- "encoder_no_repeat_ngram_size": 0,
100
- "eos_token_id": null,
101
- "finetuning_task": null,
102
- "forced_bos_token_id": null,
103
- "forced_eos_token_id": null,
104
- "gradient_checkpointing": false,
105
- "hidden_act": "quick_gelu",
106
- "hidden_size": 768,
107
- "id2label": {
108
- "0": "LABEL_0",
109
- "1": "LABEL_1"
110
- },
111
- "image_size": 224,
112
- "initializer_factor": 1.0,
113
- "initializer_range": 0.02,
114
- "intermediate_size": 3072,
115
- "is_decoder": false,
116
- "is_encoder_decoder": false,
117
- "label2id": {
118
- "LABEL_0": 0,
119
- "LABEL_1": 1
120
- },
121
- "layer_norm_eps": 1e-05,
122
- "length_penalty": 1.0,
123
- "max_length": 20,
124
- "min_length": 0,
125
- "model_type": "clip_vision_model",
126
- "no_repeat_ngram_size": 0,
127
- "num_attention_heads": 12,
128
- "num_beam_groups": 1,
129
- "num_beams": 1,
130
- "num_hidden_layers": 12,
131
- "num_return_sequences": 1,
132
- "output_attentions": false,
133
- "output_hidden_states": false,
134
- "output_scores": false,
135
- "pad_token_id": null,
136
- "patch_size": 32,
137
- "prefix": null,
138
- "problem_type": null,
139
- "pruned_heads": {},
140
- "remove_invalid_values": false,
141
- "repetition_penalty": 1.0,
142
- "return_dict": true,
143
- "return_dict_in_generate": false,
144
- "sep_token_id": null,
145
- "task_specific_params": null,
146
- "temperature": 1.0,
147
- "tie_encoder_decoder": false,
148
- "tie_word_embeddings": true,
149
- "tokenizer_class": null,
150
- "top_k": 50,
151
- "top_p": 1.0,
152
- "torch_dtype": null,
153
- "torchscript": false,
154
- "transformers_version": "4.9.0.dev0",
155
- "use_bfloat16": false
156
- }
157
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
clip_spanish_20_percent/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3021620b309ed539e293a8632e6cd3d5fc48d53c49d76b04b62e54b8450d7c9
3
- size 792387416
 
 
 
 
clip_spanish_20_percent/logs/events.out.tfevents.1626328032.t1v-n-5900a4fe-w-0.85514.3.v2 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:30c708a37b4d12a149a9d1d34543fa861f78880c9d57b68bab1bd5f869e67116
3
- size 40
 
 
 
 
clip_spanish_20_percent/logs/events.out.tfevents.1626328154.t1v-n-5900a4fe-w-0.86871.3.v2 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fb4323f4c383a7d43afab49e1e61c3324a62a3b71cae5bc5fc238a0b934448d
3
- size 689172
 
 
 
 
clip_spanish_20_percent_98_1_1_split/config.json DELETED
@@ -1,157 +0,0 @@
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": "dccuchile/bert-base-spanish-wwm-cased",
11
- "add_cross_attention": false,
12
- "architectures": [
13
- "BertForMaskedLM"
14
- ],
15
- "attention_probs_dropout_prob": 0.1,
16
- "bad_words_ids": null,
17
- "bos_token_id": null,
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": null,
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-12,
45
- "length_penalty": 1.0,
46
- "max_length": 20,
47
- "max_position_embeddings": 512,
48
- "min_length": 0,
49
- "model_type": "bert",
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_past": true,
59
- "output_scores": false,
60
- "pad_token_id": 1,
61
- "position_embedding_type": "absolute",
62
- "prefix": null,
63
- "problem_type": null,
64
- "pruned_heads": {},
65
- "remove_invalid_values": false,
66
- "repetition_penalty": 1.0,
67
- "return_dict": true,
68
- "return_dict_in_generate": false,
69
- "sep_token_id": null,
70
- "task_specific_params": null,
71
- "temperature": 1.0,
72
- "tie_encoder_decoder": false,
73
- "tie_word_embeddings": true,
74
- "tokenizer_class": null,
75
- "top_k": 50,
76
- "top_p": 1.0,
77
- "torch_dtype": null,
78
- "torchscript": false,
79
- "transformers_version": "4.9.0.dev0",
80
- "type_vocab_size": 2,
81
- "use_bfloat16": false,
82
- "use_cache": true,
83
- "vocab_size": 31002
84
- },
85
- "transformers_version": null,
86
- "vision_config": {
87
- "_name_or_path": "",
88
- "add_cross_attention": false,
89
- "architectures": null,
90
- "attention_dropout": 0.0,
91
- "bad_words_ids": null,
92
- "bos_token_id": null,
93
- "chunk_size_feed_forward": 0,
94
- "decoder_start_token_id": null,
95
- "diversity_penalty": 0.0,
96
- "do_sample": false,
97
- "dropout": 0.0,
98
- "early_stopping": false,
99
- "encoder_no_repeat_ngram_size": 0,
100
- "eos_token_id": null,
101
- "finetuning_task": null,
102
- "forced_bos_token_id": null,
103
- "forced_eos_token_id": null,
104
- "gradient_checkpointing": false,
105
- "hidden_act": "quick_gelu",
106
- "hidden_size": 768,
107
- "id2label": {
108
- "0": "LABEL_0",
109
- "1": "LABEL_1"
110
- },
111
- "image_size": 224,
112
- "initializer_factor": 1.0,
113
- "initializer_range": 0.02,
114
- "intermediate_size": 3072,
115
- "is_decoder": false,
116
- "is_encoder_decoder": false,
117
- "label2id": {
118
- "LABEL_0": 0,
119
- "LABEL_1": 1
120
- },
121
- "layer_norm_eps": 1e-05,
122
- "length_penalty": 1.0,
123
- "max_length": 20,
124
- "min_length": 0,
125
- "model_type": "clip_vision_model",
126
- "no_repeat_ngram_size": 0,
127
- "num_attention_heads": 12,
128
- "num_beam_groups": 1,
129
- "num_beams": 1,
130
- "num_hidden_layers": 12,
131
- "num_return_sequences": 1,
132
- "output_attentions": false,
133
- "output_hidden_states": false,
134
- "output_scores": false,
135
- "pad_token_id": null,
136
- "patch_size": 32,
137
- "prefix": null,
138
- "problem_type": null,
139
- "pruned_heads": {},
140
- "remove_invalid_values": false,
141
- "repetition_penalty": 1.0,
142
- "return_dict": true,
143
- "return_dict_in_generate": false,
144
- "sep_token_id": null,
145
- "task_specific_params": null,
146
- "temperature": 1.0,
147
- "tie_encoder_decoder": false,
148
- "tie_word_embeddings": true,
149
- "tokenizer_class": null,
150
- "top_k": 50,
151
- "top_p": 1.0,
152
- "torch_dtype": null,
153
- "torchscript": false,
154
- "transformers_version": "4.9.0.dev0",
155
- "use_bfloat16": false
156
- }
157
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
clip_spanish_20_percent_98_1_1_split/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8458d464ffe8e6a15d30a3f1e75fb8abbc71abc5b79dbd47056908f401a0c57b
3
- size 792387416
 
 
 
 
clip_spanish_20_percent_98_1_1_split/logs/events.out.tfevents.1626336561.t1v-n-5900a4fe-w-0.108111.3.v2 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:36878d3c806297113f3a53869e598dec743d66ba02f7712ea51e626a1282d114
3
- size 842470
 
 
 
 
clip_spanish_72972_samples/config.json DELETED
@@ -1,157 +0,0 @@
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": "dccuchile/bert-base-spanish-wwm-cased",
11
- "add_cross_attention": false,
12
- "architectures": [
13
- "BertForMaskedLM"
14
- ],
15
- "attention_probs_dropout_prob": 0.1,
16
- "bad_words_ids": null,
17
- "bos_token_id": null,
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": null,
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-12,
45
- "length_penalty": 1.0,
46
- "max_length": 20,
47
- "max_position_embeddings": 512,
48
- "min_length": 0,
49
- "model_type": "bert",
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_past": true,
59
- "output_scores": false,
60
- "pad_token_id": 1,
61
- "position_embedding_type": "absolute",
62
- "prefix": null,
63
- "problem_type": null,
64
- "pruned_heads": {},
65
- "remove_invalid_values": false,
66
- "repetition_penalty": 1.0,
67
- "return_dict": true,
68
- "return_dict_in_generate": false,
69
- "sep_token_id": null,
70
- "task_specific_params": null,
71
- "temperature": 1.0,
72
- "tie_encoder_decoder": false,
73
- "tie_word_embeddings": true,
74
- "tokenizer_class": null,
75
- "top_k": 50,
76
- "top_p": 1.0,
77
- "torch_dtype": null,
78
- "torchscript": false,
79
- "transformers_version": "4.9.0.dev0",
80
- "type_vocab_size": 2,
81
- "use_bfloat16": false,
82
- "use_cache": true,
83
- "vocab_size": 31002
84
- },
85
- "transformers_version": null,
86
- "vision_config": {
87
- "_name_or_path": "",
88
- "add_cross_attention": false,
89
- "architectures": null,
90
- "attention_dropout": 0.0,
91
- "bad_words_ids": null,
92
- "bos_token_id": null,
93
- "chunk_size_feed_forward": 0,
94
- "decoder_start_token_id": null,
95
- "diversity_penalty": 0.0,
96
- "do_sample": false,
97
- "dropout": 0.0,
98
- "early_stopping": false,
99
- "encoder_no_repeat_ngram_size": 0,
100
- "eos_token_id": null,
101
- "finetuning_task": null,
102
- "forced_bos_token_id": null,
103
- "forced_eos_token_id": null,
104
- "gradient_checkpointing": false,
105
- "hidden_act": "quick_gelu",
106
- "hidden_size": 768,
107
- "id2label": {
108
- "0": "LABEL_0",
109
- "1": "LABEL_1"
110
- },
111
- "image_size": 224,
112
- "initializer_factor": 1.0,
113
- "initializer_range": 0.02,
114
- "intermediate_size": 3072,
115
- "is_decoder": false,
116
- "is_encoder_decoder": false,
117
- "label2id": {
118
- "LABEL_0": 0,
119
- "LABEL_1": 1
120
- },
121
- "layer_norm_eps": 1e-05,
122
- "length_penalty": 1.0,
123
- "max_length": 20,
124
- "min_length": 0,
125
- "model_type": "clip_vision_model",
126
- "no_repeat_ngram_size": 0,
127
- "num_attention_heads": 12,
128
- "num_beam_groups": 1,
129
- "num_beams": 1,
130
- "num_hidden_layers": 12,
131
- "num_return_sequences": 1,
132
- "output_attentions": false,
133
- "output_hidden_states": false,
134
- "output_scores": false,
135
- "pad_token_id": null,
136
- "patch_size": 32,
137
- "prefix": null,
138
- "problem_type": null,
139
- "pruned_heads": {},
140
- "remove_invalid_values": false,
141
- "repetition_penalty": 1.0,
142
- "return_dict": true,
143
- "return_dict_in_generate": false,
144
- "sep_token_id": null,
145
- "task_specific_params": null,
146
- "temperature": 1.0,
147
- "tie_encoder_decoder": false,
148
- "tie_word_embeddings": true,
149
- "tokenizer_class": null,
150
- "top_k": 50,
151
- "top_p": 1.0,
152
- "torch_dtype": null,
153
- "torchscript": false,
154
- "transformers_version": "4.9.0.dev0",
155
- "use_bfloat16": false
156
- }
157
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
clip_spanish_72972_samples/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c86841a3eeecb0b4d7dae0a581f18353e14cb04e377fc10c81693b7b00d707d8
3
- size 792387416
 
 
 
 
clip_spanish_72972_samples/logs/events.out.tfevents.1626390780.t1v-n-5900a4fe-w-0.2167230.3.v2 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f31bdd577b05bf2295578727398f9aefc4aa2ba5ee05d2af3573486271ef049
3
- size 1591262
 
 
 
 
clip_spanish_bertin_146364_examples_lr_5e-5/config.json DELETED
@@ -1,156 +0,0 @@
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 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:55def72bbb5079de08c70573842ea2aa973f6c502d95505a9709e4cd2a2f6402
3
- size 851566424
 
 
 
 
{clip_spanish_141230_samples/logs → logs}/events.out.tfevents.1626476231.t1v-n-5900a4fe-w-0.1105221.3.v2 RENAMED
File without changes