huranokuma commited on
Commit
3d33c21
1 Parent(s): 77f81e0

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rinna/japanese-gpt2-medium",
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
+ "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": 1024,
17
+ "n_head": 16,
18
+ "n_inner": 4096,
19
+ "n_layer": 24,
20
+ "n_positions": 1024,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.22.0.dev0",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e13db8e2cd6952da31f9955c85e8e9a91d2097841ad65d7516eb0f5a5815a6d9
3
+ size 1369786201
runs/Aug10_08-23-04_3d6e44caf36e/1660120464.8975794/events.out.tfevents.1660120464.3d6e44caf36e.444.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:048f2f65438055f8ce1d73c1f74847d6c5d2096a3836a9c18713dc0819bf8eb4
3
+ size 5364
runs/Aug10_08-23-04_3d6e44caf36e/events.out.tfevents.1660120464.3d6e44caf36e.444.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb0167cef9079a859a233e072fde2e08fc2c6fc8c935eb8092dd9078ad812c5
3
+ size 4208
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "</s>",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "<unk>"
9
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
3
+ size 805634
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "</s>",
7
+ "extra_ids": 0,
8
+ "mask_token": "[MASK]",
9
+ "name_or_path": "rinna/japanese-gpt2-medium",
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "sp_model_kwargs": {},
13
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--rinna--japanese-gpt2-medium/snapshots/f464b76739c884d8b0479a0a7705b7fa71c3fd5a/special_tokens_map.json",
14
+ "tokenizer_class": "T5Tokenizer",
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d141a08ee9317cdfd02ce7302ce785a5cbb67a0d9851928e3a773c642418cb6
3
+ size 3375