tamo2-3yama commited on
Commit
117384b
1 Parent(s): 14c4d5c

End of training

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: line-corporation/japanese-large-lm-1.7b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: train_logs
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # train_logs
15
+
16
+ This model is a fine-tuned version of [line-corporation/japanese-large-lm-1.7b](https://huggingface.co/line-corporation/japanese-large-lm-1.7b) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0002
36
+ - train_batch_size: 1
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: cosine
41
+ - lr_scheduler_warmup_ratio: 0.03
42
+ - training_steps: 300
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.34.0
51
+ - Pytorch 2.2.1+cu121
52
+ - Datasets 2.14.5
53
+ - Tokenizers 0.14.1
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "line-corporation/japanese-large-lm-1.7b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.1,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 64,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "lm_head",
20
+ "wte",
21
+ "c_proj",
22
+ "c_attn",
23
+ "wpe",
24
+ "c_fc"
25
+ ],
26
+ "task_type": "CAUSAL_LM"
27
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b610d24bea5dd5eff2d6fb64eed05e8b4faaf955cf111ca7f67b11d289da2179
3
+ size 255071394
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<cls>": 6,
4
+ "<mask>": 5,
5
+ "<pad>": 3,
6
+ "<s>": 1,
7
+ "<sep>": 4,
8
+ "<unk>": 0
9
+ }
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": "<unk>",
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 sha256:0c5c56a739832923347681ed8a03a9cbf5afb6d1fe60089a5b01dd2dd063ab71
3
+ size 1208648
tokenizer_config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_eos_token": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": true,
7
+ "normalized": false,
8
+ "rstrip": true,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<sep>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<mask>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<cls>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [],
62
+ "bos_token": "<s>",
63
+ "clean_up_tokenization_spaces": true,
64
+ "cls_token": "<cls>",
65
+ "do_lower_case": false,
66
+ "eos_token": "</s>",
67
+ "extra_ids": 0,
68
+ "keep_accents": true,
69
+ "legacy": true,
70
+ "mask_token": "<mask>",
71
+ "model_max_length": 1000000000000000019884624838656,
72
+ "pad_token": "<unk>",
73
+ "sep_token": "<sep>",
74
+ "sp_model_kwargs": {},
75
+ "tokenizer_class": "T5Tokenizer",
76
+ "tokenizer_file": null,
77
+ "unk_token": "<unk>"
78
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05a2539e1cc0ce7b0095a384cb18fba0add113784b087f0d7c0e517beb838c9f
3
+ size 4536