Hugging Face's logo

kaveh
/
rclip

Zero-Shot Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
English
vision-text-dual-encoder
feature-extraction
clip
vision
medical
bert
Model card Files
xet
Metrics Community
2
Kaveh-Workstation commited on
Commit
e8b296b
·
1 Parent(s): 1f1c68b

initial commit

Browse files
Files changed (22) hide show
  1. README.md +59 -1
  2. all_results.json +11 -0
  3. checkpoint-3000/config.json +169 -0
  4. checkpoint-3000/optimizer.pt +3 -0
  5. checkpoint-3000/pytorch_model.bin +3 -0
  6. checkpoint-3000/rng_state.pth +3 -0
  7. checkpoint-3000/scheduler.pt +3 -0
  8. checkpoint-3000/trainer_state.json +100 -0
  9. checkpoint-3000/training_args.bin +3 -0
  10. config.json +169 -0
  11. eval_results.json +7 -0
  12. preprocessor_config.json +28 -0
  13. pytorch_model.bin +3 -0
  14. runs/Jul07_00-39-43_pop-os/events.out.tfevents.1688686792.pop-os.142684.0 +3 -0
  15. runs/Jul07_00-39-43_pop-os/events.out.tfevents.1688690222.pop-os.142684.1 +3 -0
  16. special_tokens_map.json +7 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +16 -0
  19. train_results.json +7 -0
  20. trainer_state.json +109 -0
  21. training_args.bin +3 -0
  22. vocab.txt +0 -0
README.md CHANGED
@@ -1,3 +1,61 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: output
6
+ results: []
7
  ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # output
13
+
14
+ This model is a fine-tuned version of [pretrained_weights/clip-allenai](https://huggingface.co/pretrained_weights/clip-allenai) on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.6386
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: 96
37
+ - eval_batch_size: 96
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: cosine
41
+ - lr_scheduler_warmup_steps: 500
42
+ - num_epochs: 5.0
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 1.7414 | 0.73 | 500 | 1.2403 |
49
+ | 1.0226 | 1.47 | 1000 | 0.9722 |
50
+ | 0.788 | 2.2 | 1500 | 0.8564 |
51
+ | 0.5693 | 2.94 | 2000 | 0.7434 |
52
+ | 0.3736 | 3.67 | 2500 | 0.6783 |
53
+ | 0.265 | 4.41 | 3000 | 0.6500 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.31.0.dev0
59
+ - Pytorch 2.0.1+cu117
60
+ - Datasets 2.13.1
61
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.6386235952377319,
4
+ "eval_runtime": 46.0178,
5
+ "eval_samples_per_second": 177.627,
6
+ "eval_steps_per_second": 1.869,
7
+ "train_loss": 0.7240408047355394,
8
+ "train_runtime": 3383.1338,
9
+ "train_samples_per_second": 96.687,
10
+ "train_steps_per_second": 1.006
11
+ }
checkpoint-3000/config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "pretrained_weights/clip-allenai",
4
+ "architectures": [
5
+ "VisionTextDualEncoderModel"
6
+ ],
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "vision-text-dual-encoder",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "_name_or_path": "allenai/scibert_scivocab_uncased",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_probs_dropout_prob": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "classifier_dropout": null,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.1,
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "is_decoder": false,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 512,
50
+ "min_length": 0,
51
+ "model_type": "bert",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 12,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 12,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 0,
62
+ "position_embedding_type": "absolute",
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.31.0.dev0",
83
+ "type_vocab_size": 2,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 31090
88
+ },
89
+ "torch_dtype": "float32",
90
+ "transformers_version": null,
91
+ "vision_config": {
92
+ "_name_or_path": "openai/clip-vit-base-patch32",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_dropout": 0.0,
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": null,
99
+ "chunk_size_feed_forward": 0,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "diversity_penalty": 0.0,
103
+ "do_sample": false,
104
+ "dropout": 0.0,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "eos_token_id": null,
108
+ "exponential_decay_length_penalty": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "hidden_act": "quick_gelu",
113
+ "hidden_size": 768,
114
+ "id2label": {
115
+ "0": "LABEL_0",
116
+ "1": "LABEL_1"
117
+ },
118
+ "image_size": 224,
119
+ "initializer_factor": 1.0,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3072,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "layer_norm_eps": 1e-05,
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "min_length": 0,
132
+ "model_type": "clip_vision_model",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 12,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_channels": 3,
138
+ "num_hidden_layers": 12,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": null,
144
+ "patch_size": 32,
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "projection_dim": 512,
148
+ "pruned_heads": {},
149
+ "remove_invalid_values": false,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict": true,
152
+ "return_dict_in_generate": false,
153
+ "sep_token_id": null,
154
+ "suppress_tokens": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": true,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": null,
164
+ "torchscript": false,
165
+ "transformers_version": "4.31.0.dev0",
166
+ "typical_p": 1.0,
167
+ "use_bfloat16": false
168
+ }
169
+ }
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691ec89d6168c22b24428d10eace30e0bf0337e84e39a900c74fa9ce7a56ac45
3
+ size 1585522757
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d64c8741624e03b7738ebc277e91939e0c596cdd69fb14e6d9e63e39a8ecb1
3
+ size 792784785
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f6ccd554ab17766492d673a6e13e5dcae4b3474d4c792d3a9e3aeffce4324a
3
+ size 14575
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b7333e7a26170435289fc6dadfc9a6c1e205a209f726a4953ea5f8adbdec01
3
+ size 627
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.405286343612334,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.73,
12
+ "learning_rate": 5e-05,
13
+ "loss": 1.7414,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.73,
18
+ "eval_loss": 1.2403221130371094,
19
+ "eval_runtime": 46.0291,
20
+ "eval_samples_per_second": 177.583,
21
+ "eval_steps_per_second": 1.868,
22
+ "step": 500
23
+ },
24
+ {
25
+ "epoch": 1.47,
26
+ "learning_rate": 4.643343608987585e-05,
27
+ "loss": 1.0226,
28
+ "step": 1000
29
+ },
30
+ {
31
+ "epoch": 1.47,
32
+ "eval_loss": 0.9721790552139282,
33
+ "eval_runtime": 46.5376,
34
+ "eval_samples_per_second": 175.643,
35
+ "eval_steps_per_second": 1.848,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 2.2,
40
+ "learning_rate": 3.67513746095034e-05,
41
+ "loss": 0.788,
42
+ "step": 1500
43
+ },
44
+ {
45
+ "epoch": 2.2,
46
+ "eval_loss": 0.8563552498817444,
47
+ "eval_runtime": 46.4494,
48
+ "eval_samples_per_second": 175.976,
49
+ "eval_steps_per_second": 1.851,
50
+ "step": 1500
51
+ },
52
+ {
53
+ "epoch": 2.94,
54
+ "learning_rate": 2.3716350843002614e-05,
55
+ "loss": 0.5693,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 2.94,
60
+ "eval_loss": 0.7433565855026245,
61
+ "eval_runtime": 63.0881,
62
+ "eval_samples_per_second": 129.565,
63
+ "eval_steps_per_second": 1.363,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 3.67,
68
+ "learning_rate": 1.104758441703049e-05,
69
+ "loss": 0.3736,
70
+ "step": 2500
71
+ },
72
+ {
73
+ "epoch": 3.67,
74
+ "eval_loss": 0.6783401966094971,
75
+ "eval_runtime": 46.4362,
76
+ "eval_samples_per_second": 176.027,
77
+ "eval_steps_per_second": 1.852,
78
+ "step": 2500
79
+ },
80
+ {
81
+ "epoch": 4.41,
82
+ "learning_rate": 2.3597925412401912e-06,
83
+ "loss": 0.265,
84
+ "step": 3000
85
+ },
86
+ {
87
+ "epoch": 4.41,
88
+ "eval_loss": 0.6500362753868103,
89
+ "eval_runtime": 46.0769,
90
+ "eval_samples_per_second": 177.399,
91
+ "eval_steps_per_second": 1.866,
92
+ "step": 3000
93
+ }
94
+ ],
95
+ "max_steps": 3405,
96
+ "num_train_epochs": 5,
97
+ "total_flos": 3.845297664e+16,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5914903516cec607e8cd570ef74ab3076afe5b03346e8869a07804013979e081
3
+ size 4027
config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "pretrained_weights/clip-allenai",
4
+ "architectures": [
5
+ "VisionTextDualEncoderModel"
6
+ ],
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "vision-text-dual-encoder",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "_name_or_path": "allenai/scibert_scivocab_uncased",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_probs_dropout_prob": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "classifier_dropout": null,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.1,
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "is_decoder": false,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 512,
50
+ "min_length": 0,
51
+ "model_type": "bert",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 12,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 12,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 0,
62
+ "position_embedding_type": "absolute",
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.31.0.dev0",
83
+ "type_vocab_size": 2,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 31090
88
+ },
89
+ "torch_dtype": "float32",
90
+ "transformers_version": null,
91
+ "vision_config": {
92
+ "_name_or_path": "openai/clip-vit-base-patch32",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_dropout": 0.0,
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": null,
99
+ "chunk_size_feed_forward": 0,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "diversity_penalty": 0.0,
103
+ "do_sample": false,
104
+ "dropout": 0.0,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "eos_token_id": null,
108
+ "exponential_decay_length_penalty": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "hidden_act": "quick_gelu",
113
+ "hidden_size": 768,
114
+ "id2label": {
115
+ "0": "LABEL_0",
116
+ "1": "LABEL_1"
117
+ },
118
+ "image_size": 224,
119
+ "initializer_factor": 1.0,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3072,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "layer_norm_eps": 1e-05,
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "min_length": 0,
132
+ "model_type": "clip_vision_model",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 12,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_channels": 3,
138
+ "num_hidden_layers": 12,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": null,
144
+ "patch_size": 32,
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "projection_dim": 512,
148
+ "pruned_heads": {},
149
+ "remove_invalid_values": false,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict": true,
152
+ "return_dict_in_generate": false,
153
+ "sep_token_id": null,
154
+ "suppress_tokens": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": true,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": null,
164
+ "torchscript": false,
165
+ "transformers_version": "4.31.0.dev0",
166
+ "typical_p": 1.0,
167
+ "use_bfloat16": false
168
+ }
169
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.6386235952377319,
4
+ "eval_runtime": 46.0178,
5
+ "eval_samples_per_second": 177.627,
6
+ "eval_steps_per_second": 1.869
7
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "VisionTextDualEncoderProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3171a6ee0156c6e9b4d2f340328191048e5c5cc656606904b203ef0cb686422
3
+ size 792784785
runs/Jul07_00-39-43_pop-os/events.out.tfevents.1688686792.pop-os.142684.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88f91ad12c5cd9df07af32511879be7f66cef214518fb249b892a715c25be66
3
+ size 10983
runs/Jul07_00-39-43_pop-os/events.out.tfevents.1688690222.pop-os.142684.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594541324e650715a8354cec1d1e5daccc3060cb06922075ceea489d24901cd3
3
+ size 359
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "processor_class": "VisionTextDualEncoderProcessor",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.7240408047355394,
4
+ "train_runtime": 3383.1338,
5
+ "train_samples_per_second": 96.687,
6
+ "train_steps_per_second": 1.006
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 3405,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.73,
12
+ "learning_rate": 5e-05,
13
+ "loss": 1.7414,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.73,
18
+ "eval_loss": 1.2403221130371094,
19
+ "eval_runtime": 46.0291,
20
+ "eval_samples_per_second": 177.583,
21
+ "eval_steps_per_second": 1.868,
22
+ "step": 500
23
+ },
24
+ {
25
+ "epoch": 1.47,
26
+ "learning_rate": 4.643343608987585e-05,
27
+ "loss": 1.0226,
28
+ "step": 1000
29
+ },
30
+ {
31
+ "epoch": 1.47,
32
+ "eval_loss": 0.9721790552139282,
33
+ "eval_runtime": 46.5376,
34
+ "eval_samples_per_second": 175.643,
35
+ "eval_steps_per_second": 1.848,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 2.2,
40
+ "learning_rate": 3.67513746095034e-05,
41
+ "loss": 0.788,
42
+ "step": 1500
43
+ },
44
+ {
45
+ "epoch": 2.2,
46
+ "eval_loss": 0.8563552498817444,
47
+ "eval_runtime": 46.4494,
48
+ "eval_samples_per_second": 175.976,
49
+ "eval_steps_per_second": 1.851,
50
+ "step": 1500
51
+ },
52
+ {
53
+ "epoch": 2.94,
54
+ "learning_rate": 2.3716350843002614e-05,
55
+ "loss": 0.5693,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 2.94,
60
+ "eval_loss": 0.7433565855026245,
61
+ "eval_runtime": 63.0881,
62
+ "eval_samples_per_second": 129.565,
63
+ "eval_steps_per_second": 1.363,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 3.67,
68
+ "learning_rate": 1.104758441703049e-05,
69
+ "loss": 0.3736,
70
+ "step": 2500
71
+ },
72
+ {
73
+ "epoch": 3.67,
74
+ "eval_loss": 0.6783401966094971,
75
+ "eval_runtime": 46.4362,
76
+ "eval_samples_per_second": 176.027,
77
+ "eval_steps_per_second": 1.852,
78
+ "step": 2500
79
+ },
80
+ {
81
+ "epoch": 4.41,
82
+ "learning_rate": 2.3597925412401912e-06,
83
+ "loss": 0.265,
84
+ "step": 3000
85
+ },
86
+ {
87
+ "epoch": 4.41,
88
+ "eval_loss": 0.6500362753868103,
89
+ "eval_runtime": 46.0769,
90
+ "eval_samples_per_second": 177.399,
91
+ "eval_steps_per_second": 1.866,
92
+ "step": 3000
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "step": 3405,
97
+ "total_flos": 4.36441284864e+16,
98
+ "train_loss": 0.7240408047355394,
99
+ "train_runtime": 3383.1338,
100
+ "train_samples_per_second": 96.687,
101
+ "train_steps_per_second": 1.006
102
+ }
103
+ ],
104
+ "max_steps": 3405,
105
+ "num_train_epochs": 5,
106
+ "total_flos": 4.36441284864e+16,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5914903516cec607e8cd570ef74ab3076afe5b03346e8869a07804013979e081
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff