Hugging Face's logo

dlwen
/
my_awesome_eli5_clm-model

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neo
Generated from Trainer
Model card Files Metrics Community
dlwen commited on
Commit
5319f30
·
verified ·
1 Parent(s): a7d37ef

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +47 -17
  2. model.safetensors +2 -2
  3. runs/Dec10_09-59-49_38cecd41f61e/events.out.tfevents.1733824790.38cecd41f61e.283.2 +3 -0
  4. special_tokens_map.json +13 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. training_args.bin +1 -1
  8. vocab.txt +0 -0
config.json CHANGED
@@ -1,25 +1,55 @@
1
  {
2
- "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
 
3
  "architectures": [
4
- "BertLMHeadModel"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 384,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
12
- "intermediate_size": 1536,
13
- "layer_norm_eps": 1e-12,
14
- "max_position_embeddings": 512,
15
- "model_type": "bert",
16
- "num_attention_heads": 12,
17
- "num_hidden_layers": 12,
18
- "pad_token_id": 0,
19
- "position_embedding_type": "absolute",
 
 
 
 
20
  "torch_dtype": "float32",
21
  "transformers_version": "4.46.3",
22
- "type_vocab_size": 2,
23
  "use_cache": true,
24
- "vocab_size": 30522
 
25
  }
 
1
  {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPTNeoForCausalLM"
6
  ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
+ "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
  "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
  "torch_dtype": "float32",
51
  "transformers_version": "4.46.3",
 
52
  "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4120d8b09359b6c17c26c143d70719f6f04abc8f93e49e96d493399a4db4ba7c
3
- size 133588624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f38a20041b3a4e29d43e0b9fe67ce451a1da20fcb521806f4ee08f7a9ece84
3
+ size 500811336
runs/Dec10_09-59-49_38cecd41f61e/events.out.tfevents.1733824790.38cecd41f61e.283.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512216c5885fb1aab016fbcf66067218ad82909a761cbb33242f0b76ab5d8f70
3
+ size 5730
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "sep_token": "[SEP]",
12
+ "unk_token": "[UNK]"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd9c36a7df913e9bf5343309276e98a739fda2914818e51e05cb41c92b06b91d
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a55bf51d64ee7375b1505572eaa86a0c79a6fa0df006f1a3d86ed191b862a3
3
  size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff