QuimBallester commited on
Commit
1fc470c
·
verified ·
1 Parent(s): 94da507

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +33 -16
  2. model.safetensors +2 -2
  3. tokenizer.json +1 -6
  4. training_args.bin +2 -2
config.json CHANGED
@@ -1,32 +1,49 @@
1
  {
2
- "activation": "gelu",
 
 
 
3
  "architectures": [
4
- "DistilBertForSequenceClassification"
5
  ],
6
- "attention_dropout": 0.1,
7
- "dim": 768,
 
 
 
 
 
 
 
 
8
  "dropout": 0.1,
9
- "hidden_dim": 3072,
 
 
 
 
 
 
10
  "id2label": {
11
  "0": "concrete",
12
  "1": "general"
13
  },
14
- "initializer_range": 0.02,
 
15
  "label2id": {
16
  "concrete": 0,
17
  "general": 1
18
  },
19
- "max_position_embeddings": 512,
20
- "model_type": "distilbert",
21
- "n_heads": 12,
22
- "n_layers": 6,
23
- "pad_token_id": 0,
 
24
  "problem_type": "single_label_classification",
25
- "qa_dropout": 0.1,
26
- "seq_classif_dropout": 0.2,
27
- "sinusoidal_pos_embds": false,
28
- "tie_weights_": true,
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.52.3",
31
- "vocab_size": 30522
 
32
  }
 
1
  {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_final_layer_norm": false,
6
  "architectures": [
7
+ "BartForSequenceClassification"
8
  ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 0,
11
+ "classif_dropout": 0.0,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 12,
18
+ "decoder_start_token_id": 2,
19
  "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 12,
24
+ "eos_token_id": 2,
25
+ "forced_eos_token_id": 2,
26
+ "gradient_checkpointing": false,
27
  "id2label": {
28
  "0": "concrete",
29
  "1": "general"
30
  },
31
+ "init_std": 0.02,
32
+ "is_encoder_decoder": true,
33
  "label2id": {
34
  "concrete": 0,
35
  "general": 1
36
  },
37
+ "max_position_embeddings": 1024,
38
+ "model_type": "bart",
39
+ "normalize_before": false,
40
+ "num_hidden_layers": 12,
41
+ "output_past": false,
42
+ "pad_token_id": 1,
43
  "problem_type": "single_label_classification",
44
+ "scale_embedding": false,
 
 
 
45
  "torch_dtype": "float32",
46
  "transformers_version": "4.52.3",
47
+ "use_cache": true,
48
+ "vocab_size": 50265
49
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fa6b7c707b38412ebabda9214f041c8ee0a5ca3db35c33bfbae8f2fc4bd7cdb
3
- size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701f37720dce70bca9a902bc20f84275fea74c90d60ae3d14ed92e1a7ca48ac3
3
+ size 1629432864
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d73e898825e0542d249b9e1ac33508e036cfaba83971b0c33cb078e4715e839
3
- size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa43ed8d6f60616f5ba486ea02a88f3120c74d254376330ea7905b833f90496
3
+ size 5649