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
Inference Endpoints
Model card Files Metrics Community
2
kaveh commited on
Commit
3eec08e
•
1 Parent(s): e8b296b

Model save

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. checkpoint-3000/config.json +0 -169
  3. checkpoint-3000/optimizer.pt +0 -3
  4. checkpoint-3000/pytorch_model.bin +0 -3
  5. checkpoint-3000/rng_state.pth +0 -3
  6. checkpoint-3000/trainer_state.json +0 -100
  7. checkpoint-3000/training_args.bin +0 -3
  8. pytorch_model.bin +1 -1
  9. checkpoint-3000/scheduler.pt → runs/Jul07_03-20-36_pop-os/events.out.tfevents.1688696444.pop-os.586616.0 +2 -2
  10. training_args.bin +1 -1
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
checkpoint-3000/config.json DELETED
@@ -1,169 +0,0 @@
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 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:691ec89d6168c22b24428d10eace30e0bf0337e84e39a900c74fa9ce7a56ac45
3
- size 1585522757
 
 
 
 
checkpoint-3000/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8d64c8741624e03b7738ebc277e91939e0c596cdd69fb14e6d9e63e39a8ecb1
3
- size 792784785
 
 
 
 
checkpoint-3000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8f6ccd554ab17766492d673a6e13e5dcae4b3474d4c792d3a9e3aeffce4324a
3
- size 14575
 
 
 
 
checkpoint-3000/trainer_state.json DELETED
@@ -1,100 +0,0 @@
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 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5914903516cec607e8cd570ef74ab3076afe5b03346e8869a07804013979e081
3
- size 4027
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3171a6ee0156c6e9b4d2f340328191048e5c5cc656606904b203ef0cb686422
3
  size 792784785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e744e104d89831300bfc10d892010ef847c85329e2c16a16f2707c5cfad086e2
3
  size 792784785
checkpoint-3000/scheduler.pt → runs/Jul07_03-20-36_pop-os/events.out.tfevents.1688696444.pop-os.586616.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07b7333e7a26170435289fc6dadfc9a6c1e205a209f726a4953ea5f8adbdec01
3
- size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90dbb79765d47658ca4c94cd3d2c278ac6b3909023eb28140e1774790d45fac5
3
+ size 9270
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5914903516cec607e8cd570ef74ab3076afe5b03346e8869a07804013979e081
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f3c1d4ceb7be6ac3c7be9b9e5cf5e45c26648236900f5c940e0066980c9625
3
  size 4027