edumunozsala commited on
Commit
f32de2a
1 Parent(s): 642c4ea

commit files to HF hub

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_gen_len": 31.0,
4
+ "eval_loss": 2.2760684490203857,
5
+ "eval_rouge1": 30.5801,
6
+ "eval_rouge2": 12.8922,
7
+ "eval_rougeL": 25.5137,
8
+ "eval_rougeLsum": 27.2771,
9
+ "eval_runtime": 992.4795,
10
+ "eval_samples_per_second": 5.038,
11
+ "eval_steps_per_second": 1.259
12
+ }
config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "DeepESP/gpt2-spanish",
7
+ "activation_function": "gelu_new",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "embd_pdrop": 0.1,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 50256,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "is_decoder": true,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_epsilon": 1e-05,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "model_type": "gpt2",
44
+ "n_ctx": 1024,
45
+ "n_embd": 768,
46
+ "n_head": 12,
47
+ "n_inner": null,
48
+ "n_layer": 12,
49
+ "n_positions": 1024,
50
+ "no_repeat_ngram_size": 0,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "reorder_and_upcast_attn": false,
63
+ "repetition_penalty": 1.0,
64
+ "resid_pdrop": 0.1,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "scale_attn_by_inverse_layer_idx": false,
68
+ "scale_attn_weights": true,
69
+ "sep_token_id": null,
70
+ "summary_activation": null,
71
+ "summary_first_dropout": 0.1,
72
+ "summary_proj_to_labels": true,
73
+ "summary_type": "cls_index",
74
+ "summary_use_proj": true,
75
+ "task_specific_params": {
76
+ "text-generation": {
77
+ "do_sample": true,
78
+ "max_length": 50
79
+ }
80
+ },
81
+ "temperature": 1.0,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": null,
88
+ "torchscript": false,
89
+ "transformers_version": "4.17.0",
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": true,
93
+ "vocab_size": 50257
94
+ },
95
+ "decoder_start_token_id": 50256,
96
+ "encoder": {
97
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
98
+ "add_cross_attention": false,
99
+ "architectures": [
100
+ "ViTModel"
101
+ ],
102
+ "attention_probs_dropout_prob": 0.0,
103
+ "bad_words_ids": null,
104
+ "bos_token_id": null,
105
+ "chunk_size_feed_forward": 0,
106
+ "cross_attention_hidden_size": null,
107
+ "decoder_start_token_id": null,
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "encoder_stride": 16,
113
+ "eos_token_id": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_act": "gelu",
118
+ "hidden_dropout_prob": 0.0,
119
+ "hidden_size": 768,
120
+ "id2label": {
121
+ "0": "LABEL_0",
122
+ "1": "LABEL_1"
123
+ },
124
+ "image_size": 224,
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 3072,
127
+ "is_decoder": false,
128
+ "is_encoder_decoder": false,
129
+ "label2id": {
130
+ "LABEL_0": 0,
131
+ "LABEL_1": 1
132
+ },
133
+ "layer_norm_eps": 1e-12,
134
+ "length_penalty": 1.0,
135
+ "max_length": 20,
136
+ "min_length": 0,
137
+ "model_type": "vit",
138
+ "no_repeat_ngram_size": 0,
139
+ "num_attention_heads": 12,
140
+ "num_beam_groups": 1,
141
+ "num_beams": 1,
142
+ "num_channels": 3,
143
+ "num_hidden_layers": 12,
144
+ "num_return_sequences": 1,
145
+ "output_attentions": false,
146
+ "output_hidden_states": false,
147
+ "output_scores": false,
148
+ "pad_token_id": null,
149
+ "patch_size": 16,
150
+ "prefix": null,
151
+ "problem_type": null,
152
+ "pruned_heads": {},
153
+ "qkv_bias": true,
154
+ "remove_invalid_values": false,
155
+ "repetition_penalty": 1.0,
156
+ "return_dict": true,
157
+ "return_dict_in_generate": false,
158
+ "sep_token_id": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.17.0",
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false
171
+ },
172
+ "is_encoder_decoder": true,
173
+ "length_penalty": 2.0,
174
+ "max_length": 32,
175
+ "model_type": "vision-encoder-decoder",
176
+ "no_repeat_ngram_size": 2,
177
+ "num_beams": 4,
178
+ "pad_token_id": 50256,
179
+ "tie_word_embeddings": false,
180
+ "torch_dtype": "float32",
181
+ "transformers_version": null,
182
+ "vocab_size": 50257
183
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 224
17
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459bcbbc3737c4ab671e0c22f86caf611a1049cc95ee4db6f7e9ac05083374ce
3
+ size 982143657
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39731ffd91686429430ad16f97de6954e04746bbaf3386e3a47af446140b06dd
3
+ size 3375