Hugging Face's logo

eagles
/
focus_sum_gpt2

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
1
eagles commited on
Commit
174d119
·
1 Parent(s): 0278805

Training complete!

Browse files
Files changed (17) hide show
  1. .gitignore +1 -0
  2. config.json +42 -0
  3. pytorch_model.bin +3 -0
  4. runs/Apr20_07-56-05_1a6066074207/1650441403.856109/events.out.tfevents.1650441403.1a6066074207.2679.23 +3 -0
  5. runs/Apr20_07-56-05_1a6066074207/1650441424.2395828/events.out.tfevents.1650441424.1a6066074207.2679.24 +3 -0
  6. runs/Apr20_07-56-05_1a6066074207/events.out.tfevents.1650441403.1a6066074207.2679.22 +3 -0
  7. runs/Apr20_07-59-21_1a6066074207/1650441585.1663806/events.out.tfevents.1650441585.1a6066074207.2679.26 +3 -0
  8. runs/Apr20_07-59-21_1a6066074207/events.out.tfevents.1650441585.1a6066074207.2679.25 +3 -0
  9. runs/Apr20_08-00-10_1a6066074207/1650441623.4531417/events.out.tfevents.1650441623.1a6066074207.2679.28 +3 -0
  10. runs/Apr20_08-00-10_1a6066074207/events.out.tfevents.1650441623.1a6066074207.2679.27 +3 -0
  11. runs/Apr20_08-01-31_1a6066074207/1650441704.00389/events.out.tfevents.1650441704.1a6066074207.4017.1 +3 -0
  12. runs/Apr20_08-01-31_1a6066074207/events.out.tfevents.1650441703.1a6066074207.4017.0 +3 -0
  13. special_tokens_map.json +1 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +1 -0
  16. training_args.bin +3 -0
  17. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uer/gpt2-chinese-cluecorpussmall",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "output_past": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 320
35
+ }
36
+ },
37
+ "tokenizer_class": "BertTokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.18.0",
40
+ "use_cache": true,
41
+ "vocab_size": 21128
42
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe2c10f95e5dcd0ca7cc0c93a96f8b6c55a055d5989351c7de67141967b1b88
3
+ size 420912233
runs/Apr20_07-56-05_1a6066074207/1650441403.856109/events.out.tfevents.1650441403.1a6066074207.2679.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962d2d07e71b887799c27782a2f0c811dbe925ec527bff5094823411e2971180
3
+ size 4831
runs/Apr20_07-56-05_1a6066074207/1650441424.2395828/events.out.tfevents.1650441424.1a6066074207.2679.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51840ef6bbfd474372ceb8a683dd3c574790426b58cc4335395489d5607a2a5c
3
+ size 4831
runs/Apr20_07-56-05_1a6066074207/events.out.tfevents.1650441403.1a6066074207.2679.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540762216870a92fea56752481769e8ccbc0b775685470ba954f84635785ae9e
3
+ size 7358
runs/Apr20_07-59-21_1a6066074207/1650441585.1663806/events.out.tfevents.1650441585.1a6066074207.2679.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ff5fd451ab189cea245088a79b3901bccb2f6115ea1cd4b627105277c82f96
3
+ size 4831
runs/Apr20_07-59-21_1a6066074207/events.out.tfevents.1650441585.1a6066074207.2679.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0139dcdbbfad957ccaaa7364196648fd0d949029395aa4b020cb59c7d5547032
3
+ size 3699
runs/Apr20_08-00-10_1a6066074207/1650441623.4531417/events.out.tfevents.1650441623.1a6066074207.2679.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7139e4a8e9a9fd31cd0eebcbe721f0da8b5fd90f41674c12888059a8caa67e7
3
+ size 4831
runs/Apr20_08-00-10_1a6066074207/events.out.tfevents.1650441623.1a6066074207.2679.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccc4dd8d4ce801994a6e17c5ef9dc398212e82fe6296898792a750774111872
3
+ size 3699
runs/Apr20_08-01-31_1a6066074207/1650441704.00389/events.out.tfevents.1650441704.1a6066074207.4017.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627818f2d3e83740d35dd2e5b54de908bbd04fefa44ae2bad2a3f76989d2c76b
3
+ size 4831
runs/Apr20_08-01-31_1a6066074207/events.out.tfevents.1650441703.1a6066074207.4017.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582d31f88a2ef141dcddacf89a3b7849fc02387b0667015764c51f1ef243f5b3
3
+ size 19831
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 1024, "special_tokens_map_file": "/root/.cache/huggingface/transformers/156e9d98e839ff793b8995298702e1f07904ae8da867d0c55ddd24262abcf176.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "uer/gpt2-chinese-cluecorpussmall", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66f479c1ad803457d77c20cbcd94374d6217acf42f8cc7dc3a0ca65ffdaa6f1
3
+ size 3055
vocab.txt ADDED
The diff for this file is too large to render. See raw diff