Hugging Face's logo

tomvoelker
/
gpt22gpt2-cnn-dailymail-seed42

TensorBoard
Safetensors
encoder-decoder
Model card Files Metrics Community
tomvoelker commited on
Commit
6c05623
·
verified ·
1 Parent(s): 13aed77

Training in progress, step 1000

Browse files
Files changed (9) hide show
  1. config.json +203 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Mar12_19-24-38_jn020/events.out.tfevents.1741807628.jn020.398992.0 +3 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +20 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "gpt2",
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
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 50256,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 50256,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "is_decoder": true,
35
+ "is_encoder_decoder": false,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1
39
+ },
40
+ "layer_norm_epsilon": 1e-05,
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "min_length": 0,
44
+ "model_type": "gpt2",
45
+ "n_ctx": 1024,
46
+ "n_embd": 768,
47
+ "n_head": 12,
48
+ "n_inner": null,
49
+ "n_layer": 12,
50
+ "n_positions": 1024,
51
+ "no_repeat_ngram_size": 0,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": null,
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "reorder_and_upcast_attn": false,
64
+ "repetition_penalty": 1.0,
65
+ "resid_pdrop": 0.1,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "scale_attn_by_inverse_layer_idx": false,
69
+ "scale_attn_weights": true,
70
+ "sep_token_id": null,
71
+ "summary_activation": null,
72
+ "summary_first_dropout": 0.1,
73
+ "summary_proj_to_labels": true,
74
+ "summary_type": "cls_index",
75
+ "summary_use_proj": true,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": {
78
+ "text-generation": {
79
+ "do_sample": true,
80
+ "max_length": 50
81
+ }
82
+ },
83
+ "temperature": 1.0,
84
+ "tf_legacy_loss": false,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": true,
87
+ "tokenizer_class": null,
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torch_dtype": null,
91
+ "torchscript": false,
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_size": 50257
96
+ },
97
+ "decoder_start_token_id": 50256,
98
+ "early_stopping": true,
99
+ "encoder": {
100
+ "_name_or_path": "gpt2",
101
+ "activation_function": "gelu_new",
102
+ "add_cross_attention": false,
103
+ "architectures": [
104
+ "GPT2LMHeadModel"
105
+ ],
106
+ "attn_pdrop": 0.1,
107
+ "bad_words_ids": null,
108
+ "begin_suppress_tokens": null,
109
+ "bos_token_id": 50256,
110
+ "chunk_size_feed_forward": 0,
111
+ "cross_attention_hidden_size": null,
112
+ "decoder_start_token_id": null,
113
+ "diversity_penalty": 0.0,
114
+ "do_sample": false,
115
+ "early_stopping": false,
116
+ "embd_pdrop": 0.1,
117
+ "encoder_no_repeat_ngram_size": 0,
118
+ "eos_token_id": 50256,
119
+ "exponential_decay_length_penalty": null,
120
+ "finetuning_task": null,
121
+ "forced_bos_token_id": null,
122
+ "forced_eos_token_id": null,
123
+ "id2label": {
124
+ "0": "LABEL_0",
125
+ "1": "LABEL_1"
126
+ },
127
+ "initializer_range": 0.02,
128
+ "is_decoder": false,
129
+ "is_encoder_decoder": false,
130
+ "label2id": {
131
+ "LABEL_0": 0,
132
+ "LABEL_1": 1
133
+ },
134
+ "layer_norm_epsilon": 1e-05,
135
+ "length_penalty": 1.0,
136
+ "max_length": 20,
137
+ "min_length": 0,
138
+ "model_type": "gpt2",
139
+ "n_ctx": 1024,
140
+ "n_embd": 768,
141
+ "n_head": 12,
142
+ "n_inner": null,
143
+ "n_layer": 12,
144
+ "n_positions": 1024,
145
+ "no_repeat_ngram_size": 0,
146
+ "num_beam_groups": 1,
147
+ "num_beams": 1,
148
+ "num_return_sequences": 1,
149
+ "output_attentions": false,
150
+ "output_hidden_states": false,
151
+ "output_scores": false,
152
+ "pad_token_id": null,
153
+ "prefix": null,
154
+ "problem_type": null,
155
+ "pruned_heads": {},
156
+ "remove_invalid_values": false,
157
+ "reorder_and_upcast_attn": false,
158
+ "repetition_penalty": 1.0,
159
+ "resid_pdrop": 0.1,
160
+ "return_dict": true,
161
+ "return_dict_in_generate": false,
162
+ "scale_attn_by_inverse_layer_idx": false,
163
+ "scale_attn_weights": true,
164
+ "sep_token_id": null,
165
+ "summary_activation": null,
166
+ "summary_first_dropout": 0.1,
167
+ "summary_proj_to_labels": true,
168
+ "summary_type": "cls_index",
169
+ "summary_use_proj": true,
170
+ "suppress_tokens": null,
171
+ "task_specific_params": {
172
+ "text-generation": {
173
+ "do_sample": true,
174
+ "max_length": 50
175
+ }
176
+ },
177
+ "temperature": 1.0,
178
+ "tf_legacy_loss": false,
179
+ "tie_encoder_decoder": false,
180
+ "tie_word_embeddings": true,
181
+ "tokenizer_class": null,
182
+ "top_k": 50,
183
+ "top_p": 1.0,
184
+ "torch_dtype": null,
185
+ "torchscript": false,
186
+ "typical_p": 1.0,
187
+ "use_bfloat16": false,
188
+ "use_cache": true,
189
+ "vocab_size": 50257
190
+ },
191
+ "eos_token_id": 50256,
192
+ "is_encoder_decoder": true,
193
+ "length_penalty": 2.0,
194
+ "max_length": 142,
195
+ "min_length": 56,
196
+ "model_type": "encoder-decoder",
197
+ "no_repeat_ngram_size": 3,
198
+ "num_beams": 4,
199
+ "pad_token_id": 50256,
200
+ "torch_dtype": "float32",
201
+ "transformers_version": "4.44.2",
202
+ "vocab_size": 50257
203
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe69c4be71be7fe57c0a1065dc4186dbd746d5f7f315f8848c930ecd543b561
3
+ size 1109028072
runs/Mar12_19-24-38_jn020/events.out.tfevents.1741807628.jn020.398992.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f88c8ed9368f5a627bbe5f463816ba45a67e75a800466fcf7e6c90798cd12d
3
+ size 10662
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ec21e70451935fe7ccf4f25e474b7a4ce1a008a140f12928eefecbc9a40e33
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff