Hugging Face's logo

ssdatar
/
output

Transformers
PyTorch
TensorBoard
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
 Metrics Community
ssdatar commited on
Commit
38408f0
·
1 Parent(s): 53298b2

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. config.json +24 -23
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +28 -5
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +37 -10
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,31 +1,32 @@
1
  {
2
- "_name_or_path": "google/electra-large-generator",
 
 
 
3
  "architectures": [
4
- "ElectraForCausalLM"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "embedding_size": 1024,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 256,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 1024,
 
14
  "is_decoder": true,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 512,
17
- "model_type": "electra",
18
- "num_attention_heads": 4,
19
- "num_hidden_layers": 24,
20
- "pad_token_id": 0,
21
- "position_embedding_type": "absolute",
22
- "summary_activation": "gelu",
23
- "summary_last_dropout": 0.1,
24
- "summary_type": "first",
25
- "summary_use_proj": true,
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.33.3",
28
- "type_vocab_size": 2,
29
  "use_cache": true,
30
- "vocab_size": 30522
 
31
  }
 
1
  {
2
+ "_name_or_path": "facebook/opt-125m",
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
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
  "is_decoder": true,
19
+ "layer_norm_elementwise_affine": true,
20
+ "layerdrop": 0.0,
21
+ "max_position_embeddings": 2048,
22
+ "model_type": "opt",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 1,
26
+ "prefix": "</s>",
 
 
 
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.33.3",
 
29
  "use_cache": true,
30
+ "vocab_size": 50272,
31
+ "word_embed_proj_dim": 768
32
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f805a8edce68c776a23ebd6a911100ea9f69e6ee08d5aa6ecb92587b6c5bbda
3
- size 205317885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c82ed85663f15f5f40ad5ea4197edcaf87a4c3a151acfc0be7dbca7a924956
3
+ size 501023389
special_tokens_map.json CHANGED
@@ -1,7 +1,30 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
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.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc687b11de0bc1b3d8348f92e3b49ef1089a621506c7661fbf3248fcd54947e
3
- size 711649
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea44f4e9418dcfdd7c6f0ac9f445d0405e3cd75423f106c5d0bae9ff91eb8db5
3
+ size 2108883
tokenizer_config.json CHANGED
@@ -1,13 +1,40 @@
1
  {
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
6
- "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "ElectraTokenizer",
12
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  }
 
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
  "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e20146335638a737527b74cf88ca20db045bd09d3bd01f62c804d1edc5fa00b
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95e887eea742365588161a06974222af3ad866805f56f036bb87dbe7675c029
3
  size 4027