Hugging Face's logo

thefrigidliquidation
/
opt-1.3b-lightnovels

Text Generation
Transformers
PyTorch
English
opt
text-generation-inference
Model card Files Community
thefrigidliquidation commited on
Commit
ea067a3
•
1 Parent(s): 0a51332

Add model

Browse files
Files changed (7) hide show
  1. README.md +15 -7
  2. config.json +29 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer_config.json +40 -0
  7. vocab.json +0 -0
README.md CHANGED
@@ -1,15 +1,23 @@
1
  ---
 
 
 
 
 
 
2
  license: other
 
3
  ---
4
 
5
  # OPT-1.3B fine-tuned on officially translated light novels.
6
 
7
  Fine-tuned [OPT-1.3b](https://huggingface.co/facebook/opt-1.3b) on 2,500 light novel volumes (~825MB of text).
8
 
9
- | Epoch | Test Loss | Train Loss |
10
- |-------|------------------|------------|
11
- | 1 | 2.16597485542297 | 2.0625 |
12
- | 2 | 2.07580518722534 | 1.8504 |
13
- | 3 | 2.02220439910889 | 1.7778 |
14
- | 4 | 1.97802829742432 | 1.5146 |
15
- | 5 | 1.94636332988739 | 1.5302 |
 
 
1
  ---
2
+ language: en
3
+ inference: false
4
+ tags:
5
+ - text-generation
6
+ - opt
7
+
8
  license: other
9
+ commercial: false
10
  ---
11
 
12
  # OPT-1.3B fine-tuned on officially translated light novels.
13
 
14
  Fine-tuned [OPT-1.3b](https://huggingface.co/facebook/opt-1.3b) on 2,500 light novel volumes (~825MB of text).
15
 
16
+ | Epoch | Test Loss | Train Loss |
17
+ |--------------------|-----------|------------|
18
+ | 0 (Not fine-tuned) | 4.9080 | N/A |
19
+ | 1 | 2.1659 | 2.0625 |
20
+ | 2 | 2.0758 | 1.8504 |
21
+ | 3 | 2.0222 | 1.7778 |
22
+ | 4 | 1.9780 | 1.5146 |
23
+ | 5 | 1.9463 | 1.5302 |
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-1.3b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "eos_token_id": 2,
14
+ "ffn_dim": 8192,
15
+ "hidden_size": 2048,
16
+ "init_std": 0.02,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 2048,
19
+ "model_type": "opt",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 24,
22
+ "pad_token_id": 1,
23
+ "prefix": "</s>",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.20.1",
26
+ "use_cache": false,
27
+ "vocab_size": 50272,
28
+ "word_embed_proj_dim": 2048
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808c97dbe05192d0686ef51eff55309f2de45213dd3107aaf4dfab3a4d5ac0f9
3
+ size 5263162257
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "</s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "name_or_path": "facebook/opt-1.3b",
22
+ "pad_token": {
23
+ "__type": "AddedToken",
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "special_tokens_map_file": null,
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff