Hugging Face's logo

tomvoelker
/
gpt22gpt2-gpt2-medium-cnn-dailymail-seed42_std_token

TensorBoard
Safetensors
encoder-decoder
Model card Files Metrics Community
tomvoelker commited on
Commit
a6b1c1a
·
verified ·
1 Parent(s): efce151

Training in progress, step 2000

Browse files
Files changed (9) hide show
  1. config.json +207 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Apr04_16-43-06_gpu09gmz.benchmarkcenter.megware.com/events.out.tfevents.1743785124.gpu09gmz.benchmarkcenter.megware.com.9648.0 +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 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "gpt2-medium",
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": 1024,
47
+ "n_head": 16,
48
+ "n_inner": null,
49
+ "n_layer": 24,
50
+ "n_positions": 1024,
51
+ "n_special": 0,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "predict_special_tokens": true,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "reorder_and_upcast_attn": false,
66
+ "repetition_penalty": 1.0,
67
+ "resid_pdrop": 0.1,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "scale_attn_by_inverse_layer_idx": false,
71
+ "scale_attn_weights": true,
72
+ "sep_token_id": null,
73
+ "summary_activation": null,
74
+ "summary_first_dropout": 0.1,
75
+ "summary_proj_to_labels": true,
76
+ "summary_type": "cls_index",
77
+ "summary_use_proj": true,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": {
80
+ "text-generation": {
81
+ "do_sample": true,
82
+ "max_length": 50
83
+ }
84
+ },
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": true,
89
+ "tokenizer_class": null,
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": null,
93
+ "torchscript": false,
94
+ "typical_p": 1.0,
95
+ "use_bfloat16": false,
96
+ "use_cache": true,
97
+ "vocab_size": 50257
98
+ },
99
+ "decoder_start_token_id": 50256,
100
+ "early_stopping": true,
101
+ "encoder": {
102
+ "_name_or_path": "gpt2-medium",
103
+ "activation_function": "gelu_new",
104
+ "add_cross_attention": false,
105
+ "architectures": [
106
+ "GPT2LMHeadModel"
107
+ ],
108
+ "attn_pdrop": 0.1,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": 50256,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": null,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "embd_pdrop": 0.1,
119
+ "encoder_no_repeat_ngram_size": 0,
120
+ "eos_token_id": 50256,
121
+ "exponential_decay_length_penalty": null,
122
+ "finetuning_task": null,
123
+ "forced_bos_token_id": null,
124
+ "forced_eos_token_id": null,
125
+ "id2label": {
126
+ "0": "LABEL_0",
127
+ "1": "LABEL_1"
128
+ },
129
+ "initializer_range": 0.02,
130
+ "is_decoder": false,
131
+ "is_encoder_decoder": false,
132
+ "label2id": {
133
+ "LABEL_0": 0,
134
+ "LABEL_1": 1
135
+ },
136
+ "layer_norm_epsilon": 1e-05,
137
+ "length_penalty": 1.0,
138
+ "max_length": 20,
139
+ "min_length": 0,
140
+ "model_type": "gpt2",
141
+ "n_ctx": 1024,
142
+ "n_embd": 1024,
143
+ "n_head": 16,
144
+ "n_inner": null,
145
+ "n_layer": 24,
146
+ "n_positions": 1024,
147
+ "n_special": 0,
148
+ "no_repeat_ngram_size": 0,
149
+ "num_beam_groups": 1,
150
+ "num_beams": 1,
151
+ "num_return_sequences": 1,
152
+ "output_attentions": false,
153
+ "output_hidden_states": false,
154
+ "output_scores": false,
155
+ "pad_token_id": null,
156
+ "predict_special_tokens": true,
157
+ "prefix": null,
158
+ "problem_type": null,
159
+ "pruned_heads": {},
160
+ "remove_invalid_values": false,
161
+ "reorder_and_upcast_attn": false,
162
+ "repetition_penalty": 1.0,
163
+ "resid_pdrop": 0.1,
164
+ "return_dict": true,
165
+ "return_dict_in_generate": false,
166
+ "scale_attn_by_inverse_layer_idx": false,
167
+ "scale_attn_weights": true,
168
+ "sep_token_id": null,
169
+ "summary_activation": null,
170
+ "summary_first_dropout": 0.1,
171
+ "summary_proj_to_labels": true,
172
+ "summary_type": "cls_index",
173
+ "summary_use_proj": true,
174
+ "suppress_tokens": null,
175
+ "task_specific_params": {
176
+ "text-generation": {
177
+ "do_sample": true,
178
+ "max_length": 50
179
+ }
180
+ },
181
+ "temperature": 1.0,
182
+ "tf_legacy_loss": false,
183
+ "tie_encoder_decoder": false,
184
+ "tie_word_embeddings": true,
185
+ "tokenizer_class": null,
186
+ "top_k": 50,
187
+ "top_p": 1.0,
188
+ "torch_dtype": null,
189
+ "torchscript": false,
190
+ "typical_p": 1.0,
191
+ "use_bfloat16": false,
192
+ "use_cache": true,
193
+ "vocab_size": 50257
194
+ },
195
+ "eos_token_id": 50256,
196
+ "is_encoder_decoder": true,
197
+ "length_penalty": 2.0,
198
+ "max_length": 142,
199
+ "min_length": 56,
200
+ "model_type": "encoder-decoder",
201
+ "no_repeat_ngram_size": 3,
202
+ "num_beams": 4,
203
+ "pad_token_id": 50256,
204
+ "torch_dtype": "float32",
205
+ "transformers_version": "4.44.2",
206
+ "vocab_size": 50257
207
+ }
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 sha256:41e37fd18c379b82b3148e7f1db84c49e24f780116b23a91017396dc024fdb61
3
+ size 3241914192
runs/Apr04_16-43-06_gpu09gmz.benchmarkcenter.megware.com/events.out.tfevents.1743785124.gpu09gmz.benchmarkcenter.megware.com.9648.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3addd6f0d0d6bce601ffd3ec4e9d3d7c589d832ba46733822be8e3d1b9d2c947
3
+ size 11289
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 sha256:46424b4d06d2c9d05d18602d70657e810575d3ddf95c76182d7ffbdce56dd255
3
+ size 5560
vocab.json ADDED
The diff for this file is too large to render. See raw diff