schnell commited on
Commit
47ae502
1 Parent(s): b9e2bc6

train 10 epochs

Browse files
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
36
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 1600,
15
+ "n_head": 20,
16
+ "n_inner": null,
17
+ "n_layer": 48,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.20.1",
30
+ "use_cache": true,
31
+ "vocab_size": 50000
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ad6bffa4a6228e9ac77b8a831342c4cee96c14c3fbe97f1e711b226e9aedcd
3
+ size 3164834114
runs/Jul30_01-18-20_ubuntu-2004/1659111617.4680064/events.out.tfevents.1659111617.ubuntu-2004.161192.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57a563ad741ccce1116f16881e441dc7de5199658763bd9e76c2f886457375d
3
+ size 5453
runs/Jul30_01-18-20_ubuntu-2004/events.out.tfevents.1659111617.ubuntu-2004.161192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abb93d26bb68bfc0c0f28875ae12f7c8f06984efb61c4a960aa04d6665fd1c4
3
+ size 2092286
runs/Sep29_10-26-21_ubuntu-2004/1664415289.5853715/events.out.tfevents.1664415289.ubuntu-2004.11360.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b762c8c4b1852a32febc0842525d0abf6b680e04516a9d3d79fa8cb23aa9040
3
+ size 5453
runs/Sep29_10-26-21_ubuntu-2004/events.out.tfevents.1664415289.ubuntu-2004.11360.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a498bf17e22e591db64aabc31221edeb0cd7ca788419775e8ba4c1695199911
3
+ size 8555584
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "model_max_length": 1024,
5
+ "name_or_path": "juman-bpe-wiki-cc100-50000",
6
+ "padding_side": "right",
7
+ "special_tokens_map_file": "juman-bpe-wiki-cc100-50000/special_tokens_map.json",
8
+ "tokenizer_class": "PreTrainedTokenizerFast",
9
+ "truncation_side": "right",
10
+ "unk_token": "<unk>"
11
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9820839083f702763b886d06eb3321f8162c32f6ab41807aa945e76f20b3a389
3
+ size 4527