Hugging Face's logo

superbigtree
/
clip-roberta-finetuned

Feature Extraction
Transformers
TensorBoard
Safetensors
vision-text-dual-encoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
superbigtree commited on
Commit
8af7072
·
verified ·
1 Parent(s): 7f3f17f

Training in progress, step 500

Browse files
Files changed (21) hide show
  1. model.safetensors +1 -1
  2. runs/Feb05_20-19-07_ec4ceb47e8ba/events.out.tfevents.1707164358.ec4ceb47e8ba.6912.0 +2 -2
  3. runs/Feb05_20-43-29_ec4ceb47e8ba/events.out.tfevents.1707165821.ec4ceb47e8ba.10220.0 +3 -0
  4. runs/Feb05_20-47-21_ec4ceb47e8ba/events.out.tfevents.1707166053.ec4ceb47e8ba.10577.0 +3 -0
  5. runs/Feb05_20-49-23_ec4ceb47e8ba/events.out.tfevents.1707166175.ec4ceb47e8ba.10924.0 +3 -0
  6. runs/Feb05_20-53-11_ec4ceb47e8ba/events.out.tfevents.1707166402.ec4ceb47e8ba.11469.0 +3 -0
  7. runs/Feb05_20-54-33_ec4ceb47e8ba/events.out.tfevents.1707166485.ec4ceb47e8ba.11704.0 +3 -0
  8. runs/Feb05_20-59-54_ec4ceb47e8ba/events.out.tfevents.1707166798.ec4ceb47e8ba.12482.0 +3 -0
  9. runs/Feb05_21-01-57_ec4ceb47e8ba/events.out.tfevents.1707166929.ec4ceb47e8ba.12696.0 +3 -0
  10. runs/Feb05_21-09-40_ec4ceb47e8ba/events.out.tfevents.1707167385.ec4ceb47e8ba.13734.0 +3 -0
  11. runs/Feb05_21-17-16_ec4ceb47e8ba/events.out.tfevents.1707167840.ec4ceb47e8ba.14388.0 +3 -0
  12. runs/Feb05_21-18-35_ec4ceb47e8ba/events.out.tfevents.1707167927.ec4ceb47e8ba.14633.0 +3 -0
  13. runs/Feb05_21-22-23_ec4ceb47e8ba/events.out.tfevents.1707168155.ec4ceb47e8ba.15273.0 +3 -0
  14. tmp-checkpoint-1500/config.json +168 -0
  15. tmp-checkpoint-1500/model.safetensors +3 -0
  16. tmp-checkpoint-1500/optimizer.pt +3 -0
  17. tmp-checkpoint-1500/rng_state.pth +3 -0
  18. tmp-checkpoint-1500/scheduler.pt +3 -0
  19. tmp-checkpoint-1500/trainer_state.json +39 -0
  20. tmp-checkpoint-1500/training_args.bin +3 -0
  21. training_args.bin +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d576eedd42468f186504d534444a147a3560128ebe78776b8ff475ea33ad9b34
3
  size 851603588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90436829ffa8dbfb6e37343d458d904327ce7b15eb67ca6a2eabf8bf22faf37f
3
  size 851603588
runs/Feb05_20-19-07_ec4ceb47e8ba/events.out.tfevents.1707164358.ec4ceb47e8ba.6912.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee4f1e2a8c7929e9ab2cbb33d90ab48ea8febf181d74df7278f5982252edabee
3
- size 8644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe5fd9507d63494a57a37a534d16241a5c95fbfc9d814d856b9438f95da4233
3
+ size 8801
runs/Feb05_20-43-29_ec4ceb47e8ba/events.out.tfevents.1707165821.ec4ceb47e8ba.10220.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944e5e38b730c1f46e8d6bd359b6be70e26a71dabc9928616453f5e0123d8c23
3
+ size 8330
runs/Feb05_20-47-21_ec4ceb47e8ba/events.out.tfevents.1707166053.ec4ceb47e8ba.10577.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c8b87a02a8ceae3944e084157a48399fa16dca0daed01f9eb31b6a933dbf0f
3
+ size 8330
runs/Feb05_20-49-23_ec4ceb47e8ba/events.out.tfevents.1707166175.ec4ceb47e8ba.10924.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e68ddd803dd22a955ca1d62aee666c4dc7b11dbfdd79a2f8e7fd4fcf2635020
3
+ size 8330
runs/Feb05_20-53-11_ec4ceb47e8ba/events.out.tfevents.1707166402.ec4ceb47e8ba.11469.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557e7bc2f18cd26815850c478abd2d760d0c76438a8ecade0596743c80c403dc
3
+ size 8330
runs/Feb05_20-54-33_ec4ceb47e8ba/events.out.tfevents.1707166485.ec4ceb47e8ba.11704.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8cf549e702d5c45d6ec199f66bc58dd1a06f464470bbfea1266d4ecf7749d00
3
+ size 8330
runs/Feb05_20-59-54_ec4ceb47e8ba/events.out.tfevents.1707166798.ec4ceb47e8ba.12482.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef84bce3162c89e98a50736052dea9bda75e63f324eb8ee804d4e87dbf6a9aa7
3
+ size 8330
runs/Feb05_21-01-57_ec4ceb47e8ba/events.out.tfevents.1707166929.ec4ceb47e8ba.12696.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232aaaba7769eba75ea94e5644178774877a513d5f69e79877e05709a4f2ebf7
3
+ size 8330
runs/Feb05_21-09-40_ec4ceb47e8ba/events.out.tfevents.1707167385.ec4ceb47e8ba.13734.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f44459690b16a0cf5eac85059e982c49775657a77e969bd7a8e7d28dabddea6
3
+ size 8330
runs/Feb05_21-17-16_ec4ceb47e8ba/events.out.tfevents.1707167840.ec4ceb47e8ba.14388.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10581a00fdb4a18ca5e4115040a451505b032d6eb80af23583a5cbbc10bfb9f
3
+ size 8330
runs/Feb05_21-18-35_ec4ceb47e8ba/events.out.tfevents.1707167927.ec4ceb47e8ba.14633.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a393779d248ae5fb37e96ec7a752fad0aa4c1a9338a301f77e1c49965f0da357
3
+ size 8330
runs/Feb05_21-22-23_ec4ceb47e8ba/events.out.tfevents.1707168155.ec4ceb47e8ba.15273.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51005b504316ca4bc7e1abab8c802e5912dc3136b15e329a009958500a0a0e71
3
+ size 8500
tmp-checkpoint-1500/config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
90
+ "transformers_version": "4.38.0.dev0",
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
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
tmp-checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab618aa593bb8511185195fb92f572c52da602c0eda9db3f28833c179e8ac9d
3
+ size 851603588
tmp-checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a656f198ccebd3699f67e7011993850183d44895d4050ac023ce48cabeb83b
3
+ size 1703439696
tmp-checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d786965806b12e13f6100de46eb6cd1b692c9d64ad72cda4d21e54789731ce
3
+ size 14575
tmp-checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6733b55e21573fa488e03e6717c1132149a3d1607c520639b4eb4f9a7f78e1a
3
+ size 627
tmp-checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.32439446366782004,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "learning_rate": 4.819780853517878e-05,
14
+ "loss": 1.1469,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.22,
19
+ "learning_rate": 4.639561707035756e-05,
20
+ "loss": 0.698,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.32,
25
+ "learning_rate": 4.459342560553633e-05,
26
+ "loss": 0.6134,
27
+ "step": 1500
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 13872,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 2.563531776e+16,
36
+ "train_batch_size": 128,
37
+ "trial_name": null,
38
+ "trial_params": null
39
+ }
tmp-checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068d209d129913c65b483eca3c3a4f684e27ed686f5c77cfbba64c044ae031af
3
+ size 4283
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:068d209d129913c65b483eca3c3a4f684e27ed686f5c77cfbba64c044ae031af
3
- size 4283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606e75812e373f11f2b717b04be9d5cffc62f44251344b4c92e22559fa491151
3
+ size 4347