Training in progress, step 1500
Browse files- README.md +52 -0
- config.json +169 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- coco_dataset_script
|
6 |
+
model-index:
|
7 |
+
- name: clip-roberta-finetuned
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# clip-roberta-finetuned
|
15 |
+
|
16 |
+
This model was trained from scratch on the coco_dataset_script dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 64
|
37 |
+
- eval_batch_size: 64
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 3.0
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.34.0.dev0
|
50 |
+
- Pytorch 2.0.1+cu117
|
51 |
+
- Datasets 2.14.5
|
52 |
+
- Tokenizers 0.14.0
|
config.json
ADDED
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./clip-roberta",
|
3 |
+
"architectures": [
|
4 |
+
"VisionTextDualEncoderModel"
|
5 |
+
],
|
6 |
+
"logit_scale_init_value": 2.6592,
|
7 |
+
"model_type": "vision-text-dual-encoder",
|
8 |
+
"projection_dim": 512,
|
9 |
+
"text_config": {
|
10 |
+
"_name_or_path": "roberta-base",
|
11 |
+
"add_cross_attention": false,
|
12 |
+
"architectures": [
|
13 |
+
"RobertaForMaskedLM"
|
14 |
+
],
|
15 |
+
"attention_probs_dropout_prob": 0.1,
|
16 |
+
"bad_words_ids": null,
|
17 |
+
"begin_suppress_tokens": null,
|
18 |
+
"bos_token_id": 0,
|
19 |
+
"chunk_size_feed_forward": 0,
|
20 |
+
"classifier_dropout": null,
|
21 |
+
"cross_attention_hidden_size": null,
|
22 |
+
"decoder_start_token_id": null,
|
23 |
+
"diversity_penalty": 0.0,
|
24 |
+
"do_sample": false,
|
25 |
+
"early_stopping": false,
|
26 |
+
"encoder_no_repeat_ngram_size": 0,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"exponential_decay_length_penalty": null,
|
29 |
+
"finetuning_task": null,
|
30 |
+
"forced_bos_token_id": null,
|
31 |
+
"forced_eos_token_id": null,
|
32 |
+
"hidden_act": "gelu",
|
33 |
+
"hidden_dropout_prob": 0.1,
|
34 |
+
"hidden_size": 768,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1"
|
38 |
+
},
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 3072,
|
41 |
+
"is_decoder": false,
|
42 |
+
"is_encoder_decoder": false,
|
43 |
+
"label2id": {
|
44 |
+
"LABEL_0": 0,
|
45 |
+
"LABEL_1": 1
|
46 |
+
},
|
47 |
+
"layer_norm_eps": 1e-05,
|
48 |
+
"length_penalty": 1.0,
|
49 |
+
"max_length": 20,
|
50 |
+
"max_position_embeddings": 514,
|
51 |
+
"min_length": 0,
|
52 |
+
"model_type": "roberta",
|
53 |
+
"no_repeat_ngram_size": 0,
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_beam_groups": 1,
|
56 |
+
"num_beams": 1,
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"num_return_sequences": 1,
|
59 |
+
"output_attentions": false,
|
60 |
+
"output_hidden_states": false,
|
61 |
+
"output_scores": false,
|
62 |
+
"pad_token_id": 1,
|
63 |
+
"position_embedding_type": "absolute",
|
64 |
+
"prefix": null,
|
65 |
+
"problem_type": null,
|
66 |
+
"pruned_heads": {},
|
67 |
+
"remove_invalid_values": false,
|
68 |
+
"repetition_penalty": 1.0,
|
69 |
+
"return_dict": true,
|
70 |
+
"return_dict_in_generate": false,
|
71 |
+
"sep_token_id": null,
|
72 |
+
"suppress_tokens": null,
|
73 |
+
"task_specific_params": null,
|
74 |
+
"temperature": 1.0,
|
75 |
+
"tf_legacy_loss": false,
|
76 |
+
"tie_encoder_decoder": false,
|
77 |
+
"tie_word_embeddings": true,
|
78 |
+
"tokenizer_class": null,
|
79 |
+
"top_k": 50,
|
80 |
+
"top_p": 1.0,
|
81 |
+
"torch_dtype": null,
|
82 |
+
"torchscript": false,
|
83 |
+
"type_vocab_size": 1,
|
84 |
+
"typical_p": 1.0,
|
85 |
+
"use_bfloat16": false,
|
86 |
+
"use_cache": true,
|
87 |
+
"vocab_size": 50265
|
88 |
+
},
|
89 |
+
"token": "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",
|
90 |
+
"torch_dtype": "float32",
|
91 |
+
"transformers_version": "4.34.0.dev0",
|
92 |
+
"vision_config": {
|
93 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
94 |
+
"add_cross_attention": false,
|
95 |
+
"architectures": null,
|
96 |
+
"attention_dropout": 0.0,
|
97 |
+
"bad_words_ids": null,
|
98 |
+
"begin_suppress_tokens": null,
|
99 |
+
"bos_token_id": null,
|
100 |
+
"chunk_size_feed_forward": 0,
|
101 |
+
"cross_attention_hidden_size": null,
|
102 |
+
"decoder_start_token_id": null,
|
103 |
+
"diversity_penalty": 0.0,
|
104 |
+
"do_sample": false,
|
105 |
+
"dropout": 0.0,
|
106 |
+
"early_stopping": false,
|
107 |
+
"encoder_no_repeat_ngram_size": 0,
|
108 |
+
"eos_token_id": null,
|
109 |
+
"exponential_decay_length_penalty": null,
|
110 |
+
"finetuning_task": null,
|
111 |
+
"forced_bos_token_id": null,
|
112 |
+
"forced_eos_token_id": null,
|
113 |
+
"hidden_act": "quick_gelu",
|
114 |
+
"hidden_size": 768,
|
115 |
+
"id2label": {
|
116 |
+
"0": "LABEL_0",
|
117 |
+
"1": "LABEL_1"
|
118 |
+
},
|
119 |
+
"image_size": 224,
|
120 |
+
"initializer_factor": 1.0,
|
121 |
+
"initializer_range": 0.02,
|
122 |
+
"intermediate_size": 3072,
|
123 |
+
"is_decoder": false,
|
124 |
+
"is_encoder_decoder": false,
|
125 |
+
"label2id": {
|
126 |
+
"LABEL_0": 0,
|
127 |
+
"LABEL_1": 1
|
128 |
+
},
|
129 |
+
"layer_norm_eps": 1e-05,
|
130 |
+
"length_penalty": 1.0,
|
131 |
+
"max_length": 20,
|
132 |
+
"min_length": 0,
|
133 |
+
"model_type": "clip_vision_model",
|
134 |
+
"no_repeat_ngram_size": 0,
|
135 |
+
"num_attention_heads": 12,
|
136 |
+
"num_beam_groups": 1,
|
137 |
+
"num_beams": 1,
|
138 |
+
"num_channels": 3,
|
139 |
+
"num_hidden_layers": 12,
|
140 |
+
"num_return_sequences": 1,
|
141 |
+
"output_attentions": false,
|
142 |
+
"output_hidden_states": false,
|
143 |
+
"output_scores": false,
|
144 |
+
"pad_token_id": null,
|
145 |
+
"patch_size": 32,
|
146 |
+
"prefix": null,
|
147 |
+
"problem_type": null,
|
148 |
+
"projection_dim": 512,
|
149 |
+
"pruned_heads": {},
|
150 |
+
"remove_invalid_values": false,
|
151 |
+
"repetition_penalty": 1.0,
|
152 |
+
"return_dict": true,
|
153 |
+
"return_dict_in_generate": false,
|
154 |
+
"sep_token_id": null,
|
155 |
+
"suppress_tokens": null,
|
156 |
+
"task_specific_params": null,
|
157 |
+
"temperature": 1.0,
|
158 |
+
"tf_legacy_loss": false,
|
159 |
+
"tie_encoder_decoder": false,
|
160 |
+
"tie_word_embeddings": true,
|
161 |
+
"tokenizer_class": null,
|
162 |
+
"top_k": 50,
|
163 |
+
"top_p": 1.0,
|
164 |
+
"torch_dtype": null,
|
165 |
+
"torchscript": false,
|
166 |
+
"typical_p": 1.0,
|
167 |
+
"use_bfloat16": false
|
168 |
+
}
|
169 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4b24324037ec7161dc3d53b5da6a8fb35b8538d0f59f742876a7349f4197c76
|
3 |
+
size 851693457
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85fdb75205506024362c100da4445e29465d8900eef9c5768362f1249454125c
|
3 |
+
size 4027
|