Hugging Face's logo

Timothy1337
/
finetuning-sentiment-imdb

Text Classification
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
Timothy1337 commited on
Commit
439b222
•
1 Parent(s): 8fe48d4

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. config.json +17 -31
  2. pytorch_model.bin +2 -2
  3. runs/Jan17_08-01-16_c82412888a34/events.out.tfevents.1673942494.c82412888a34.598.9 +3 -0
  4. runs/Jan17_08-28-33_c82412888a34/1673944118.3535943/events.out.tfevents.1673944118.c82412888a34.598.11 +3 -0
  5. runs/Jan17_08-28-33_c82412888a34/events.out.tfevents.1673944118.c82412888a34.598.10 +3 -0
  6. special_tokens_map.json +5 -18
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +11 -23
  9. training_args.bin +1 -1
  10. vocab.txt +0 -0
config.json CHANGED
@@ -1,40 +1,26 @@
1
  {
2
- "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
 
3
  "architectures": [
4
- "CamembertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "gradient_checkpointing": false,
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
- "id2label": {
15
- "0": "neg",
16
- "1": "neu",
17
- "2": "pos"
18
- },
19
  "initializer_range": 0.02,
20
- "intermediate_size": 3072,
21
- "label2id": {
22
- "LABEL_0": 0,
23
- "LABEL_1": 1,
24
- "LABEL_2": 2
25
- },
26
- "layer_norm_eps": 1e-12,
27
  "max_position_embeddings": 512,
28
- "model_type": "camembert",
29
- "num_attention_head": 12,
30
- "num_attention_heads": 12,
31
- "num_hidden_layers": 12,
32
- "pad_token_id": 1,
33
- "position_embedding_type": "absolute",
34
  "problem_type": "single_label_classification",
 
 
 
 
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.25.1",
37
- "type_vocab_size": 1,
38
- "use_cache": true,
39
- "vocab_size": 25005
40
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
 
 
 
 
 
 
 
12
  "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
 
18
  "problem_type": "single_label_classification",
19
+ "qa_dropout": 0.1,
20
+ "seq_classif_dropout": 0.2,
21
+ "sinusoidal_pos_embds": false,
22
+ "tie_weights_": true,
23
  "torch_dtype": "float32",
24
  "transformers_version": "4.25.1",
25
+ "vocab_size": 119547
 
 
26
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3c74bd7a74523f4331eb80526aa7c90cd2cbe976c3ff58883d97243ac4014a7
3
- size 421060277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11164ea85a071a190b385c802ba9818c03c8f097f3802f3e3a64c66726097917
3
+ size 541340333
runs/Jan17_08-01-16_c82412888a34/events.out.tfevents.1673942494.c82412888a34.598.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfe865761d7d915832a30a57d57532b31552845627eb1fc278ce9597e8044019
3
+ size 341
runs/Jan17_08-28-33_c82412888a34/1673944118.3535943/events.out.tfevents.1673944118.c82412888a34.598.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6472359d3d0a97d21ffbaaa7d9a9217c1697d3a1176d469e999d8e2fc85360a
3
+ size 5524
runs/Jan17_08-28-33_c82412888a34/events.out.tfevents.1673944118.c82412888a34.598.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6f219176aedccb551952fcf9366ce5ad93457e773fd03f069d4fd132278280
3
+ size 3661
special_tokens_map.json CHANGED
@@ -1,20 +1,7 @@
1
  {
2
- "additional_special_tokens": [
3
- "<s>NOTUSED",
4
- "</s>NOTUSED",
5
- "<_>"
6
- ],
7
- "bos_token": "<s>",
8
- "cls_token": "<s>",
9
- "eos_token": "</s>",
10
- "mask_token": {
11
- "content": "<mask>",
12
- "lstrip": true,
13
- "normalized": true,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- "pad_token": "<pad>",
18
- "sep_token": "</s>",
19
- "unk_token": "<unk>"
20
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,26 +1,14 @@
1
  {
2
- "additional_special_tokens": [
3
- "<s>NOTUSED",
4
- "</s>NOTUSED",
5
- "<_>"
6
- ],
7
- "bos_token": "<s>",
8
- "cls_token": "<s>",
9
- "eos_token": "</s>",
10
- "mask_token": {
11
- "__type": "AddedToken",
12
- "content": "<mask>",
13
- "lstrip": true,
14
- "normalized": true,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "model_max_length": 416,
19
- "name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
20
- "pad_token": "<pad>",
21
- "sep_token": "</s>",
22
- "sp_model_kwargs": {},
23
  "special_tokens_map_file": null,
24
- "tokenizer_class": "CamembertTokenizer",
25
- "unk_token": "<unk>"
 
 
26
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-multilingual-cased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
14
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5874f05e1ca6a2b9e76bb241099316447b849fcf68bcb5518e8f1bd83500ac3b
3
  size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d885670e51c1fe0290e28fc861f8db75a73f99b2bbbaa4cdeb92ab538d7ff4
3
  size 3451
vocab.txt ADDED
The diff for this file is too large to render. See raw diff