karlkwon commited on
Commit
36102d6
1 Parent(s): 25b6d3c

Training in progress, step 50

Browse files
Files changed (4) hide show
  1. .gitignore +1 -0
  2. config.json +107 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "1f7fe8444292beb4a259e3a5b6eba440cd5999d4",
3
+ "_name_or_path": "microsoft/git-base",
4
+ "architectures": [
5
+ "GitForCausalLM"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 101,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 102,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 1024,
18
+ "model_type": "git",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 6,
21
+ "num_image_with_embedding": null,
22
+ "pad_token_id": 0,
23
+ "position_embedding_type": "absolute",
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": null,
27
+ "use_cache": true,
28
+ "vision_config": {
29
+ "_name_or_path": "",
30
+ "add_cross_attention": false,
31
+ "architectures": null,
32
+ "attention_dropout": 0.0,
33
+ "bad_words_ids": null,
34
+ "begin_suppress_tokens": null,
35
+ "bos_token_id": null,
36
+ "chunk_size_feed_forward": 0,
37
+ "cross_attention_hidden_size": null,
38
+ "decoder_start_token_id": null,
39
+ "diversity_penalty": 0.0,
40
+ "do_sample": false,
41
+ "dropout": 0.0,
42
+ "early_stopping": false,
43
+ "encoder_no_repeat_ngram_size": 0,
44
+ "eos_token_id": null,
45
+ "exponential_decay_length_penalty": null,
46
+ "finetuning_task": null,
47
+ "forced_bos_token_id": null,
48
+ "forced_eos_token_id": null,
49
+ "hidden_act": "quick_gelu",
50
+ "hidden_size": 768,
51
+ "id2label": {
52
+ "0": "LABEL_0",
53
+ "1": "LABEL_1"
54
+ },
55
+ "image_size": 224,
56
+ "initializer_factor": 1.0,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "is_decoder": false,
60
+ "is_encoder_decoder": false,
61
+ "label2id": {
62
+ "LABEL_0": 0,
63
+ "LABEL_1": 1
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "length_penalty": 1.0,
67
+ "max_length": 20,
68
+ "min_length": 0,
69
+ "model_type": "git_vision_model",
70
+ "no_repeat_ngram_size": 0,
71
+ "num_attention_heads": 12,
72
+ "num_beam_groups": 1,
73
+ "num_beams": 1,
74
+ "num_channels": 3,
75
+ "num_hidden_layers": 12,
76
+ "num_return_sequences": 1,
77
+ "output_attentions": false,
78
+ "output_hidden_states": false,
79
+ "output_scores": false,
80
+ "pad_token_id": null,
81
+ "patch_size": 16,
82
+ "prefix": null,
83
+ "problem_type": null,
84
+ "projection_dim": 512,
85
+ "pruned_heads": {},
86
+ "remove_invalid_values": false,
87
+ "repetition_penalty": 1.0,
88
+ "return_dict": true,
89
+ "return_dict_in_generate": false,
90
+ "sep_token_id": null,
91
+ "suppress_tokens": null,
92
+ "task_specific_params": null,
93
+ "temperature": 1.0,
94
+ "tf_legacy_loss": false,
95
+ "tie_encoder_decoder": false,
96
+ "tie_word_embeddings": true,
97
+ "tokenizer_class": null,
98
+ "top_k": 50,
99
+ "top_p": 1.0,
100
+ "torch_dtype": null,
101
+ "torchscript": false,
102
+ "transformers_version": "4.30.2",
103
+ "typical_p": 1.0,
104
+ "use_bfloat16": false
105
+ },
106
+ "vocab_size": 30522
107
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785248e6270a16c80e8231d66f947251d0c2ddc2cf4fef84ad6f6cd3ca5b4931
3
+ size 706594713
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31d575c82a5df575350a978118bb42c04b816a7f161625c16fec91fe7c24463
3
+ size 3899