Hugging Face's logo

Galuh
/
clip-indonesian

Transformers
JAX
TensorBoard
hybrid-clip
Inference Endpoints
Model card Files Metrics Community
3
Galuh Sahid commited on
Commit
e551781
•
1 Parent(s): 6c7faf4

Add checkpoint from experiments

Browse files
Files changed (9) hide show
  1. training_v1/ckpt-5499/config.json +171 -0
  2. training_v1/ckpt-5499/flax_model.msgpack +3 -0
  3. training_v1/ckpt-5499/opt_state.msgpack +3 -0
  4. training_v1/ckpt-5499/training_state.json +1 -0
  5. training_v1/config.json +171 -0
  6. training_v1/flax_model.msgpack +3 -0
  7. training_v1/logs/events.out.tfevents.1629075504.t1v-n-aa35e684-w-0.491287.3.v2 +3 -0
  8. training_v1/logs/events.out.tfevents.1629075852.t1v-n-aa35e684-w-0.496381.3.v2 +3 -0
  9. training_v1/logs/events.out.tfevents.1629076281.t1v-n-aa35e684-w-0.501441.3.v2 +3 -0
training_v1/ckpt-5499/config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridCLIP"
4
+ ],
5
+ "freeze_backbones": true,
6
+ "initializer_factor": 1.0,
7
+ "model_type": "hybrid-clip",
8
+ "projection_dim": 512,
9
+ "seed": 42,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "_num_labels": 5,
13
+ "add_cross_attention": false,
14
+ "architectures": [
15
+ "BertModel"
16
+ ],
17
+ "attention_probs_dropout_prob": 0.1,
18
+ "bad_words_ids": null,
19
+ "bos_token_id": null,
20
+ "chunk_size_feed_forward": 0,
21
+ "decoder_start_token_id": null,
22
+ "directionality": "bidi",
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "gradient_checkpointing": false,
32
+ "hidden_act": "gelu",
33
+ "hidden_dropout_prob": 0.1,
34
+ "hidden_size": 1024,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1",
38
+ "2": "LABEL_2",
39
+ "3": "LABEL_3",
40
+ "4": "LABEL_4"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 4096,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1,
49
+ "LABEL_2": 2,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4
52
+ },
53
+ "layer_norm_eps": 1e-12,
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 512,
57
+ "min_length": 0,
58
+ "model_type": "bert",
59
+ "no_repeat_ngram_size": 0,
60
+ "num_attention_heads": 16,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_hidden_layers": 24,
64
+ "num_return_sequences": 1,
65
+ "output_attentions": false,
66
+ "output_hidden_states": false,
67
+ "output_past": true,
68
+ "output_scores": false,
69
+ "pad_token_id": 0,
70
+ "pooler_fc_size": 768,
71
+ "pooler_num_attention_heads": 12,
72
+ "pooler_num_fc_layers": 3,
73
+ "pooler_size_per_head": 128,
74
+ "pooler_type": "first_token_transform",
75
+ "position_embedding_type": "absolute",
76
+ "prefix": null,
77
+ "problem_type": null,
78
+ "pruned_heads": {},
79
+ "remove_invalid_values": false,
80
+ "repetition_penalty": 1.0,
81
+ "return_dict": true,
82
+ "return_dict_in_generate": false,
83
+ "sep_token_id": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tie_encoder_decoder": false,
87
+ "tie_word_embeddings": true,
88
+ "tokenizer_class": null,
89
+ "top_k": 50,
90
+ "top_p": 1.0,
91
+ "torch_dtype": null,
92
+ "torchscript": false,
93
+ "transformers_version": "4.9.1",
94
+ "type_vocab_size": 2,
95
+ "use_bfloat16": false,
96
+ "use_cache": true,
97
+ "vocab_size": 30522
98
+ },
99
+ "transformers_version": null,
100
+ "vision_config": {
101
+ "_name_or_path": "",
102
+ "add_cross_attention": false,
103
+ "architectures": null,
104
+ "attention_dropout": 0.0,
105
+ "bad_words_ids": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "decoder_start_token_id": null,
109
+ "diversity_penalty": 0.0,
110
+ "do_sample": false,
111
+ "dropout": 0.0,
112
+ "early_stopping": false,
113
+ "encoder_no_repeat_ngram_size": 0,
114
+ "eos_token_id": null,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "gradient_checkpointing": false,
119
+ "hidden_act": "quick_gelu",
120
+ "hidden_size": 768,
121
+ "id2label": {
122
+ "0": "LABEL_0",
123
+ "1": "LABEL_1"
124
+ },
125
+ "image_size": 224,
126
+ "initializer_factor": 1.0,
127
+ "initializer_range": 0.02,
128
+ "intermediate_size": 3072,
129
+ "is_decoder": false,
130
+ "is_encoder_decoder": false,
131
+ "label2id": {
132
+ "LABEL_0": 0,
133
+ "LABEL_1": 1
134
+ },
135
+ "layer_norm_eps": 1e-05,
136
+ "length_penalty": 1.0,
137
+ "max_length": 20,
138
+ "min_length": 0,
139
+ "model_type": "clip_vision_model",
140
+ "no_repeat_ngram_size": 0,
141
+ "num_attention_heads": 12,
142
+ "num_beam_groups": 1,
143
+ "num_beams": 1,
144
+ "num_hidden_layers": 12,
145
+ "num_return_sequences": 1,
146
+ "output_attentions": false,
147
+ "output_hidden_states": false,
148
+ "output_scores": false,
149
+ "pad_token_id": null,
150
+ "patch_size": 32,
151
+ "prefix": null,
152
+ "problem_type": null,
153
+ "pruned_heads": {},
154
+ "remove_invalid_values": false,
155
+ "repetition_penalty": 1.0,
156
+ "return_dict": true,
157
+ "return_dict_in_generate": false,
158
+ "sep_token_id": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.9.1",
169
+ "use_bfloat16": false
170
+ }
171
+ }
training_v1/ckpt-5499/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c6eb48db2a314059ebf75f120e520b7fda8b8b5d17992278a04ab07f97f859
3
+ size 1694082566
training_v1/ckpt-5499/opt_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ac0f4feef2fbeeb4f0a369d77683eff769883f9835d5e948aaf048f4e794a6
3
+ size 3388165359
training_v1/ckpt-5499/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 5500}
training_v1/config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridCLIP"
4
+ ],
5
+ "freeze_backbones": true,
6
+ "initializer_factor": 1.0,
7
+ "model_type": "hybrid-clip",
8
+ "projection_dim": 512,
9
+ "seed": 42,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "_num_labels": 5,
13
+ "add_cross_attention": false,
14
+ "architectures": [
15
+ "BertModel"
16
+ ],
17
+ "attention_probs_dropout_prob": 0.1,
18
+ "bad_words_ids": null,
19
+ "bos_token_id": null,
20
+ "chunk_size_feed_forward": 0,
21
+ "decoder_start_token_id": null,
22
+ "directionality": "bidi",
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "gradient_checkpointing": false,
32
+ "hidden_act": "gelu",
33
+ "hidden_dropout_prob": 0.1,
34
+ "hidden_size": 1024,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1",
38
+ "2": "LABEL_2",
39
+ "3": "LABEL_3",
40
+ "4": "LABEL_4"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 4096,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1,
49
+ "LABEL_2": 2,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4
52
+ },
53
+ "layer_norm_eps": 1e-12,
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 512,
57
+ "min_length": 0,
58
+ "model_type": "bert",
59
+ "no_repeat_ngram_size": 0,
60
+ "num_attention_heads": 16,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_hidden_layers": 24,
64
+ "num_return_sequences": 1,
65
+ "output_attentions": false,
66
+ "output_hidden_states": false,
67
+ "output_past": true,
68
+ "output_scores": false,
69
+ "pad_token_id": 0,
70
+ "pooler_fc_size": 768,
71
+ "pooler_num_attention_heads": 12,
72
+ "pooler_num_fc_layers": 3,
73
+ "pooler_size_per_head": 128,
74
+ "pooler_type": "first_token_transform",
75
+ "position_embedding_type": "absolute",
76
+ "prefix": null,
77
+ "problem_type": null,
78
+ "pruned_heads": {},
79
+ "remove_invalid_values": false,
80
+ "repetition_penalty": 1.0,
81
+ "return_dict": true,
82
+ "return_dict_in_generate": false,
83
+ "sep_token_id": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tie_encoder_decoder": false,
87
+ "tie_word_embeddings": true,
88
+ "tokenizer_class": null,
89
+ "top_k": 50,
90
+ "top_p": 1.0,
91
+ "torch_dtype": null,
92
+ "torchscript": false,
93
+ "transformers_version": "4.9.1",
94
+ "type_vocab_size": 2,
95
+ "use_bfloat16": false,
96
+ "use_cache": true,
97
+ "vocab_size": 30522
98
+ },
99
+ "transformers_version": null,
100
+ "vision_config": {
101
+ "_name_or_path": "",
102
+ "add_cross_attention": false,
103
+ "architectures": null,
104
+ "attention_dropout": 0.0,
105
+ "bad_words_ids": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "decoder_start_token_id": null,
109
+ "diversity_penalty": 0.0,
110
+ "do_sample": false,
111
+ "dropout": 0.0,
112
+ "early_stopping": false,
113
+ "encoder_no_repeat_ngram_size": 0,
114
+ "eos_token_id": null,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "gradient_checkpointing": false,
119
+ "hidden_act": "quick_gelu",
120
+ "hidden_size": 768,
121
+ "id2label": {
122
+ "0": "LABEL_0",
123
+ "1": "LABEL_1"
124
+ },
125
+ "image_size": 224,
126
+ "initializer_factor": 1.0,
127
+ "initializer_range": 0.02,
128
+ "intermediate_size": 3072,
129
+ "is_decoder": false,
130
+ "is_encoder_decoder": false,
131
+ "label2id": {
132
+ "LABEL_0": 0,
133
+ "LABEL_1": 1
134
+ },
135
+ "layer_norm_eps": 1e-05,
136
+ "length_penalty": 1.0,
137
+ "max_length": 20,
138
+ "min_length": 0,
139
+ "model_type": "clip_vision_model",
140
+ "no_repeat_ngram_size": 0,
141
+ "num_attention_heads": 12,
142
+ "num_beam_groups": 1,
143
+ "num_beams": 1,
144
+ "num_hidden_layers": 12,
145
+ "num_return_sequences": 1,
146
+ "output_attentions": false,
147
+ "output_hidden_states": false,
148
+ "output_scores": false,
149
+ "pad_token_id": null,
150
+ "patch_size": 32,
151
+ "prefix": null,
152
+ "problem_type": null,
153
+ "pruned_heads": {},
154
+ "remove_invalid_values": false,
155
+ "repetition_penalty": 1.0,
156
+ "return_dict": true,
157
+ "return_dict_in_generate": false,
158
+ "sep_token_id": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.9.1",
169
+ "use_bfloat16": false
170
+ }
171
+ }
training_v1/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8830977875a5f8ece1d00b3d15440f271316f4ba7c89b35dcd2fb9961b222ca8
3
+ size 1694082566
training_v1/logs/events.out.tfevents.1629075504.t1v-n-aa35e684-w-0.491287.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2554d19c120f2e833d66b556cd8af525de91ad77812958ec99582ef0176b4f3f
3
+ size 40
training_v1/logs/events.out.tfevents.1629075852.t1v-n-aa35e684-w-0.496381.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0810a2bed8f7e82124069f0c0d350b4fd614838bafbc55eafda0ce957d7c45b3
3
+ size 29323
training_v1/logs/events.out.tfevents.1629076281.t1v-n-aa35e684-w-0.501441.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371df7c98ec3bb362d337b78ed836a62b7c10ab15eaad4352160809a4841a3b9
3
+ size 712409